# Assistant conversation 897UN4 - Canonical URL: - Resource IRI: - Type: assistant conversation - Mode: chat ## Transcript ### 1. User Import the attached PDF documents. [Uploaded PDFs] - ChatGPT and Scenario-Based Programming.pdf: Sheaf file #WKM6WJ - Relaxing synchronization.pdf: Sheaf file #GABTMR - Adaptive BP.pdf: Sheaf file #ZQRBW2 - Distributing Scenario-Based Models.pdf: Sheaf file #RKXU9J - SB and LLMs.pdf: Sheaf file #MQ54L9 - BPDistSCP.pdf: Sheaf file #3KKXGK - Challenges in Modeling and Unmodeling.pdf: Sheaf file #ZYHPXB - tracer-sosym.pdf: Sheaf file #8CMH9F ### 2. Assistant tool calls #### Tool call: `document_import` ```json { "action": "stage", "file_ids": [ "WKM6WJ", "GABTMR", "ZQRBW2", "RKXU9J", "MQ54L9", "3KKXGK", "ZYHPXB", "8CMH9F" ], "name": "Batch import: SBP/BP papers" } ``` ### 3. Tool result: document_import { "status": { "counts": { "pending": 8 }, "files": [ { "error": null, "status": "pending", "file_id": "3KKXGK", "execution_id": null }, { "error": null, "status": "pending", "file_id": "8CMH9F", "execution_id": null }, { "error": null, "status": "pending", "file_id": "GABTMR", "execution_id": null }, { "error": null, "status": "pending", "file_id": "MQ54L9", "execution_id": null }, { "error": null, "status": "pending", "file_id": "RKXU9J", "execution_id": null }, { "error": null, "status": "pending", "file_id": "WKM6WJ", "execution_id": null }, { "error": null, "status": "pending", "file_id": "ZQRBW2", "execution_id": null }, { "error": null, "status": "pending", "file_id": "ZYHPXB", "execution_id": null } ] }, "sources": [], "action": "stage", "run_id": "93E66X", "file_ids": [ "WKM6WJ", "GABTMR", "ZQRBW2", "RKXU9J", "MQ54L9", "3KKXGK", "ZYHPXB", "8CMH9F" ], "run_iri": "https://m.sheaf.less.rest/93E66X" } ### 4. Assistant tool calls #### Tool call: `document_import` ```json { "action": "extract", "run_id": "93E66X" } ``` ### 5. Tool result: document_import { "status": { "counts": { "completed": 8 }, "files": [ { "error": null, "status": "completed", "file_id": "3KKXGK", "execution_id": "pex_RL_W9PtK8zo0" }, { "error": null, "status": "completed", "file_id": "8CMH9F", "execution_id": "pex_m9WMtkcUWVfB" }, { "error": null, "status": "completed", "file_id": "GABTMR", "execution_id": "pex_Xm_ELp4rAAM7" }, { "error": null, "status": "completed", "file_id": "MQ54L9", "execution_id": "pex_ZPoPW4J0u1Wv" }, { "error": null, "status": "completed", "file_id": "RKXU9J", "execution_id": "pex_FsTAl2Ia1oqB" }, { "error": null, "status": "completed", "file_id": "WKM6WJ", "execution_id": "pex_UNCK4VMAuuF4" }, { "error": null, "status": "completed", "file_id": "ZQRBW2", "execution_id": "pex___eS-S4F68V1" }, { "error": null, "status": "completed", "file_id": "ZYHPXB", "execution_id": "pex_k4tsk_p6Tn6W" } ] }, "action": "extract", "completed": 1, "run_id": "93E66X", "submitted": 8 } ### 6. Assistant tool calls #### Tool call: `document_import` ```json { "action": "inspect", "run_id": "93E66X" } ``` ### 7. Tool result: document_import { "status": { "counts": { "completed": 8 }, "files": [ { "error": null, "status": "completed", "file_id": "3KKXGK", "execution_id": "pex_RL_W9PtK8zo0" }, { "error": null, "status": "completed", "file_id": "8CMH9F", "execution_id": "pex_m9WMtkcUWVfB" }, { "error": null, "status": "completed", "file_id": "GABTMR", "execution_id": "pex_Xm_ELp4rAAM7" }, { "error": null, "status": "completed", "file_id": "MQ54L9", "execution_id": "pex_ZPoPW4J0u1Wv" }, { "error": null, "status": "completed", "file_id": "RKXU9J", "execution_id": "pex_FsTAl2Ia1oqB" }, { "error": null, "status": "completed", "file_id": "WKM6WJ", "execution_id": "pex_UNCK4VMAuuF4" }, { "error": null, "status": "completed", "file_id": "ZQRBW2", "execution_id": "pex___eS-S4F68V1" }, { "error": null, "status": "completed", "file_id": "ZYHPXB", "execution_id": "pex_k4tsk_p6Tn6W" } ] }, "action": "inspect", "run_id": "93E66X", "files": [ { "status": "completed", "file_id": "3KKXGK", "quality": { "blocks": 511, "pages": 58, "math_expressions": 568, "page_continuations": 35, "block_types": { "Caption": 14, "Equation": 11, "Figure": 10, "Footnote": 3, "ListGroup": 22, "PageFooter": 59, "Picture": 1, "SectionHeader": 57, "Table": 1, "Text": 333 }, "empty_equation_blocks": 0, "equation_blocks": 11, "pages_with_math": 29 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/3KKXGK.datalab.json" }, { "status": "completed", "file_id": "8CMH9F", "quality": { "blocks": 331, "pages": 22, "math_expressions": 0, "page_continuations": 12, "block_types": { "Caption": 16, "Figure": 12, "ListGroup": 4, "PageFooter": 23, "PageHeader": 23, "Picture": 4, "SectionHeader": 51, "Text": 198 }, "empty_equation_blocks": 0, "equation_blocks": 0, "pages_with_math": 0 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/8CMH9F.datalab.json" }, { "status": "completed", "file_id": "GABTMR", "quality": { "blocks": 140, "pages": 17, "math_expressions": 232, "page_continuations": 7, "block_types": { "Caption": 8, "Equation": 5, "Footnote": 1, "ListGroup": 7, "SectionHeader": 15, "Table": 1, "Text": 103 }, "empty_equation_blocks": 0, "equation_blocks": 5, "pages_with_math": 11 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/GABTMR.datalab.json" }, { "status": "completed", "file_id": "MQ54L9", "quality": { "blocks": 222, "pages": 26, "math_expressions": 37, "page_continuations": 9, "block_types": { "Caption": 3, "Figure": 2, "Footnote": 2, "ListGroup": 12, "PageFooter": 1, "PageHeader": 37, "Picture": 1, "SectionHeader": 33, "Table": 2, "Text": 129 }, "empty_equation_blocks": 0, "equation_blocks": 0, "pages_with_math": 4 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/MQ54L9.datalab.json" }, { "status": "completed", "file_id": "RKXU9J", "quality": { "blocks": 186, "pages": 16, "math_expressions": 209, "page_continuations": 8, "block_types": { "Caption": 2, "Equation": 11, "Figure": 1, "ListGroup": 14, "SectionHeader": 17, "Table": 1, "Text": 140 }, "empty_equation_blocks": 0, "equation_blocks": 11, "pages_with_math": 12 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/RKXU9J.datalab.json" }, { "status": "completed", "file_id": "WKM6WJ", "quality": { "blocks": 146, "pages": 12, "math_expressions": 29, "page_continuations": 6, "block_types": { "Caption": 2, "Figure": 1, "Footnote": 1, "ListGroup": 8, "PageHeader": 1, "SectionHeader": 23, "Table": 2, "Text": 108 }, "empty_equation_blocks": 0, "equation_blocks": 0, "pages_with_math": 2 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/WKM6WJ.datalab.json" }, { "status": "completed", "file_id": "ZQRBW2", "quality": { "blocks": 125, "pages": 8, "math_expressions": 68, "page_continuations": 6, "block_types": { "Caption": 7, "Figure": 6, "ListGroup": 4, "PageFooter": 10, "PageHeader": 1, "Picture": 1, "SectionHeader": 22, "Text": 74 }, "empty_equation_blocks": 0, "equation_blocks": 0, "pages_with_math": 4 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/ZQRBW2.datalab.json" }, { "status": "completed", "file_id": "ZYHPXB", "quality": { "blocks": 136, "pages": 8, "math_expressions": 20, "page_continuations": 5, "block_types": { "Caption": 1, "Figure": 1, "Footnote": 5, "ListGroup": 3, "PageFooter": 14, "PageHeader": 7, "SectionHeader": 20, "Text": 85 }, "empty_equation_blocks": 0, "equation_blocks": 0, "pages_with_math": 2 }, "output_path": "/home/mbrock/sheaf.mikael/var/datalab/93E66X/ZYHPXB.datalab.json" } ] } ### 8. Assistant tool calls #### Tool call: `document_import` ```json { "action": "import", "run_id": "93E66X" } ``` ### 9. Tool result: document_import { "next": "Resolve metadata, rebuild indexes, and validate reader pages.", "action": "import", "documents": [ { "status": "imported", "title": null, "file_id": "3KKXGK", "document_id": "M5788P", "document_iri": "https://m.sheaf.less.rest/M5788P" }, { "status": "imported", "title": null, "file_id": "8CMH9F", "document_id": "QV3BWZ", "document_iri": "https://m.sheaf.less.rest/QV3BWZ" }, { "status": "imported", "title": null, "file_id": "GABTMR", "document_id": "TDS4H2", "document_iri": "https://m.sheaf.less.rest/TDS4H2" }, { "status": "imported", "title": null, "file_id": "MQ54L9", "document_id": "CSJARA", "document_iri": "https://m.sheaf.less.rest/CSJARA" }, { "status": "imported", "title": null, "file_id": "RKXU9J", "document_id": "D4VB7S", "document_iri": "https://m.sheaf.less.rest/D4VB7S" }, { "status": "imported", "title": null, "file_id": "WKM6WJ", "document_id": "3JCRAD", "document_iri": "https://m.sheaf.less.rest/3JCRAD" }, { "status": "imported", "title": null, "file_id": "ZQRBW2", "document_id": "P2W4J5", "document_iri": "https://m.sheaf.less.rest/P2W4J5" }, { "status": "imported", "title": null, "file_id": "ZYHPXB", "document_id": "XQ5NKX", "document_iri": "https://m.sheaf.less.rest/XQ5NKX" } ], "run_id": "93E66X" } ### 10. Assistant tool calls #### Tool call: `document_import` ```json { "action": "metadata", "run_id": "93E66X" } ``` ### 11. Tool result: document_import { "action": "metadata", "documents": [ { "match": { "reason": "no DOI or ISBN found", "source": "none", "score": 0.0, "accept?": false }, "metadata": { "title": "Towards Behavioral Programming in Distributed Architectures", "usage": { "cost": { "total": 6.79e-4, "tokens": 6.79e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.44e-4, "output_cost": 2.35e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1777, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.44e-4, "quantity": 1777 }, { "count": 157, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.35e-4, "quantity": 157 } ] }, "output_tokens": 157, "input_tokens": 1777, "total_cost": 6.79e-4, "reasoning_tokens": 0, "input_cost": 4.44e-4, "output_cost": 2.35e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1934, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2014", "model": "google:gemini-3.1-flash-lite-preview", "notes": "Preprint submitted to Journal of Science of Computer Programming, March 13, 2014.", "issue": null, "pages": null, "authors": [ "David Harel", "Amir Kantor", "Guy Katz", "Assaf Marron", "Gera Weiss", "Guy Wiener" ], "doi": null, "volume": null, "isbn": null, "source_filename": "8a633e26427a69156fbdb9e4bca7db1bf93d99a2199fa2eab1013108341150fd.pdf", "publication": "Journal of Science of Computer Programming", "confidence": "high" }, "document_id": "M5788P", "wrote": false }, { "match": { "reason": "title match accepted for Crossref type journal-article", "source": "doi", "identifier": "10.1007/s10270-010-0151-2", "score": 1.0, "doi": "10.1007/s10270-010-0151-2", "accept?": true, "crossref_title": "On tracing reactive systems", "crossref_type": "journal-article" }, "metadata": { "title": "On tracing reactive systems", "usage": { "cost": { "total": 7.11e-4, "tokens": 7.11e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.5e-4, "output_cost": 2.61e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1801, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.5e-4, "quantity": 1801 }, { "count": 174, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.61e-4, "quantity": 174 } ] }, "output_tokens": 174, "input_tokens": 1801, "total_cost": 7.11e-4, "reasoning_tokens": 0, "input_cost": 4.5e-4, "output_cost": 2.61e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1975, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2010", "model": "google:gemini-3.1-flash-lite-preview", "notes": "Information extracted from the article metadata on page 1. Volume and issue inferred from the context of the Springer journal structure and online publication date of 2010.", "issue": "1", "pages": "1-18", "authors": [ "Shahar Maoz", "David Harel" ], "doi": "10.1007/s10270-010-0151-2", "volume": "10", "isbn": null, "source_filename": "d7d212cac6e4ecfb23f44c8bbc7ea958b3d4db35d82aa77bf1c6132ac9a83436.pdf", "publication": "Software and Systems Modeling", "confidence": "high" }, "document_id": "QV3BWZ", "wrote": true }, { "match": { "reason": "no DOI or ISBN found", "source": "none", "score": 0.0, "accept?": false }, "metadata": { "title": "Relaxing Synchronization Constraints in Behavioral Programs", "usage": { "cost": { "total": 6.34e-4, "tokens": 6.34e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.44e-4, "output_cost": 1.9e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1777, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.44e-4, "quantity": 1777 }, { "count": 127, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 1.9e-4, "quantity": 127 } ] }, "output_tokens": 127, "input_tokens": 1777, "total_cost": 6.34e-4, "reasoning_tokens": 0, "input_cost": 4.44e-4, "output_cost": 1.9e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1904, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": null, "model": "google:gemini-3.1-flash-lite-preview", "notes": "No DOI, ISBN, year, publication, volume, issue, or page range is provided within the text of the PDF.", "issue": null, "pages": null, "authors": [ "David Harel", "Amir Kantor", "Guy Katz" ], "doi": null, "volume": null, "isbn": null, "source_filename": "7f429a29fb08033bc3987c89b58567c409f571d759d4ed9d83d0bbf245191eac.pdf", "publication": null, "confidence": "medium" }, "document_id": "TDS4H2", "wrote": false }, { "match": { "reason": "title match accepted for Crossref type book-chapter", "source": "doi", "identifier": "10.1007/978-3-031-96841-9_3", "score": 1.0, "doi": "10.1007/978-3-031-96841-9_3", "accept?": true, "crossref_title": "Enhancing Scenario-Based Modeling Using Large Language Models", "crossref_type": "book-chapter" }, "metadata": { "title": "Enhancing Scenario-Based Modeling Using Large Language Models", "usage": { "cost": { "total": 7.15e-4, "tokens": 7.15e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.58e-4, "output_cost": 2.57e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1834, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.58e-4, "quantity": 1834 }, { "count": 171, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.57e-4, "quantity": 171 } ] }, "output_tokens": 171, "input_tokens": 1834, "total_cost": 7.15e-4, "reasoning_tokens": 0, "input_cost": 4.58e-4, "output_cost": 2.57e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 2005, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2026", "model": "google:gemini-3.1-flash-lite-preview", "notes": null, "issue": null, "pages": "43–68", "authors": [ "David Harel", "Guy Katz", "Assaf Marron", "Smadar Szekely" ], "doi": "10.1007/978-3-031-96841-9_3", "volume": "CCIS 2547", "isbn": null, "source_filename": "35282d75b0ff0612f04ac4a3bcd3b376df19a617ae42ddf8fea64fb259548ffc.pdf", "publication": "MODELSWARD 2024", "confidence": "high" }, "document_id": "CSJARA", "wrote": true }, { "match": { "reason": "no DOI or ISBN found", "source": "none", "score": 0.0, "accept?": false }, "metadata": { "title": "Distributing Scenario-Based Models: A Replicate-and-Project Approach", "usage": { "cost": { "total": 6.84e-4, "tokens": 6.84e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.44e-4, "output_cost": 2.4e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1777, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.44e-4, "quantity": 1777 }, { "count": 160, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.4e-4, "quantity": 160 } ] }, "output_tokens": 160, "input_tokens": 1777, "total_cost": 6.84e-4, "reasoning_tokens": 0, "input_cost": 4.44e-4, "output_cost": 2.4e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1937, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2017", "model": "google:gemini-3.1-flash-lite-preview", "notes": "No journal or conference publication details provided in the text. Year inferred from recent references and context.", "issue": null, "pages": null, "authors": [ "Shlomi Steinberg", "Joel Greenyer", "Daniel Gritzner", "David Harel", "Guy Katz", "Assaf Marron" ], "doi": null, "volume": null, "isbn": null, "source_filename": "8496801ae567209cb54108ee5f3fb5f90b0e1b340b5282cce880d6787111803b.pdf", "publication": "Unknown", "confidence": "medium" }, "document_id": "D4VB7S", "wrote": false }, { "match": { "reason": "no DOI or ISBN found", "source": "none", "score": 0.0, "accept?": false }, "metadata": { "title": "On Augmenting Scenario-Based Modeling with Generative AI", "usage": { "cost": { "total": 6.62e-4, "tokens": 6.62e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.44e-4, "output_cost": 2.18e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1777, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.44e-4, "quantity": 1777 }, { "count": 145, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.18e-4, "quantity": 145 } ] }, "output_tokens": 145, "input_tokens": 1777, "total_cost": 6.62e-4, "reasoning_tokens": 0, "input_cost": 4.44e-4, "output_cost": 2.18e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1922, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2024", "model": "google:gemini-3.1-flash-lite-preview", "notes": "This is a preprint available on arXiv.", "issue": null, "pages": null, "authors": [ "David Harel", "Guy Katz", "Assaf Marron", "Smadar Szekely" ], "doi": null, "volume": "2401.02245v1", "isbn": null, "source_filename": "cc367b8c326dfea60c9caea8bfb54986c0499dd33a0dfb8d2a3310404da3a59e.pdf", "publication": "arXiv", "confidence": "high" }, "document_id": "3JCRAD", "wrote": false }, { "match": { "reason": "title match accepted for Crossref type proceedings-article", "source": "doi", "identifier": "10.1109/ictai.2011.109", "score": 1.0, "doi": "10.1109/ictai.2011.109", "accept?": true, "crossref_title": "Adaptive Behavioral Programming", "crossref_type": "proceedings-article" }, "metadata": { "title": "Adaptive Behavioral Programming", "usage": { "cost": { "total": 6.72e-4, "tokens": 6.72e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.35e-4, "output_cost": 2.37e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1741, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.35e-4, "quantity": 1741 }, { "count": 158, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 2.37e-4, "quantity": 158 } ] }, "output_tokens": 158, "input_tokens": 1741, "total_cost": 6.72e-4, "reasoning_tokens": 0, "input_cost": 4.35e-4, "output_cost": 2.37e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1899, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2011", "model": "google:gemini-3.1-flash-lite-preview", "notes": "Pages 685-687 extracted from the provided document.", "issue": null, "pages": "685-687", "authors": [ "Nir Eitan", "David Harel" ], "doi": "10.1109/ictai.2011.109", "volume": null, "isbn": null, "source_filename": "c92843e82a87f4063c912d5be6180059fd310dcaef9799a9bf83d2716e318ff5.pdf", "publication": "2011 23rd IEEE International Conference on Tools with Artificial Intelligence", "confidence": "high" }, "document_id": "P2W4J5", "wrote": true }, { "match": { "reason": "title match accepted for Crossref type proceedings-article", "source": "doi", "identifier": "10.5220/0011728900003402", "score": 1.0, "doi": "10.5220/0011728900003402", "accept?": true, "crossref_title": "Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems", "crossref_type": "proceedings-article" }, "metadata": { "title": "Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems", "usage": { "cost": { "total": 7.6e-4, "tokens": 7.6e-4, "tools": 0.0, "storage": 0.0, "images": 0.0, "input_cost": 4.44e-4, "output_cost": 3.16e-4, "reasoning_cost": 0.0, "line_items": [ { "count": 1777, "id": "token.input", "kind": "tokens", "component": "token.input", "cost": 4.44e-4, "quantity": 1777 }, { "count": 211, "id": "token.output", "kind": "tokens", "component": "token.output", "cost": 3.16e-4, "quantity": 211 } ] }, "output_tokens": 211, "input_tokens": 1777, "total_cost": 7.6e-4, "reasoning_tokens": 0, "input_cost": 4.44e-4, "output_cost": 3.16e-4, "reasoning_cost": 0.0, "cached_tokens": 0, "total_tokens": 1988, "tool_usage": {}, "image_usage": {}, "cache_creation_tokens": 0 }, "year": "2023", "model": "google:gemini-3.1-flash-lite-preview", "notes": null, "issue": null, "pages": "202-209", "authors": [ "Assaf Marron", "Irun Cohen", "Guy Frankel", "David Harel", "Smadar Szekely" ], "doi": "10.5220/0011728900003402", "volume": null, "isbn": "9789897586330", "source_filename": "3be7a7090e7eae49c62193fa8612da51cff3bb3723fd9d206bcde929e63f01a6.pdf", "publication": "Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering (MODELSWARD 2023)", "confidence": "High" }, "document_id": "XQ5NKX", "wrote": true } ], "run_id": "93E66X" } ### 12. Assistant tool calls #### Tool call: `web_search` ```json { "query": "\"Towards Behavioral Programming in Distributed Architectures\" Harel Kantor Katz Marron Weiss Wiener DOI Science of Computer Programming" } ``` #### Tool call: `web_search` ```json { "query": "\"Relaxing Synchronization Constraints in Behavioral Programs\" Harel Kantor Katz DOI" } ``` #### Tool call: `web_search` ```json { "query": "\"Distributing Scenario-Based Models\" \"Replicate-and-Project\" Steinberg Greenyer Gritzner Harel Katz Marron DOI" } ``` #### Tool call: `web_search` ```json { "query": "\"On Augmenting Scenario-Based Modeling with Generative AI\" arXiv 2401.02245 Harel Katz Marron Szekely" } ``` ### 13. Tool result: web_search WEB SEARCH RESULTS Query: "Towards Behavioral Programming in Distributed Architectures" Harel Kantor Katz Marron Weiss Wiener DOI Science of Computer Programming **DOI:** `10.1016/j.scico.2014.03.003` **Full citation:** Harel, D., Kantor, A., Katz, G., Marron, A., Weiss, G., & Wiener, G. (2015). Towards behavioral programming in distributed architectures. *Science of Computer Programming, 98*(Part 2), 233–267. https://doi.org/10.1016/j.scico.2014.03.003 ([sciencedirect.com](https://www.sciencedirect.com/science/article/pii/S0167642314001075?utm_source=openai)) Cited sources: - Towards behavioral programming in distributed architectures - ScienceDirect: https://www.sciencedirect.com/science/article/pii/S0167642314001075?utm_source=openai ### 14. Tool result: web_search WEB SEARCH RESULTS Query: "Relaxing Synchronization Constraints in Behavioral Programs" Harel Kantor Katz DOI The DOI for **“Relaxing Synchronization Constraints in Behavioral Programs”** by David Harel, Amir Kantor, and Guy Katz is: **10.1007/978-3-642-45221-5_25** ([weizmann.elsevierpure.com](https://weizmann.elsevierpure.com/en/publications/relaxing-synchronization-constraints-in-behavioral-programs/?utm_source=openai)) Cited sources: - Relaxing synchronization constraints in behavioral programs - Weizmann Institute of Science: https://weizmann.elsevierpure.com/en/publications/relaxing-synchronization-constraints-in-behavioral-programs/?utm_source=openai ### 15. Tool result: web_search WEB SEARCH RESULTS Query: "Distributing Scenario-Based Models" "Replicate-and-Project" Steinberg Greenyer Gritzner Harel Katz Marron DOI **DOI:** `10.5220/0006271301820195` ([scitepress.org](https://www.scitepress.org/Link.aspx?doi=10.5220%2F0006271301820195&utm_source=openai)) **Citation:** Steinberg, S., Greenyer, J., Gritzner, D., Harel, D., Katz, G., & Marron, A. (2017). *Distributing scenario-based models: A replicate-and-project approach*. In **Proceedings of the 5th International Conference on Model-Driven Engineering and Software Development (MODELSWARD 2017)** (pp. 182–195). SciTePress. https://doi.org/10.5220/0006271301820195 Cited sources: - SciTePress - Publication Details: https://www.scitepress.org/Link.aspx?doi=10.5220%2F0006271301820195&utm_source=openai ### 16. Tool result: web_search WEB SEARCH RESULTS Query: "On Augmenting Scenario-Based Modeling with Generative AI" arXiv 2401.02245 Harel Katz Marron Szekely ## Paper details **David Harel, Guy Katz, Assaf Marron, and Smadar Szekely.** “On Augmenting Scenario-Based Modeling with Generative AI.” *Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering (MODELSWARD 2024)*, pp. 235–246. arXiv:2401.02245. DOI: 10.5220/0012427100003645. ([arxiv.org](https://arxiv.org/abs/2401.02245?utm_source=openai)) ### Main idea The paper proposes a structured way to use generative-AI chatbots in system modeling: 1. A chatbot generates or modifies scenario-based model components. 2. The resulting model undergoes automated analysis and human inspection. 3. Detected errors, omissions, and inconsistencies are fed back to the chatbot. 4. This iterative process continues until a more accurate model is produced. The authors argue that scenario-based modeling is especially suitable because its models can be executed and formally analyzed, reducing the risks associated with hallucinated or inconsistent AI-generated specifications. The paper reports favorable preliminary results but presents the approach primarily as a research direction rather than a fully validated methodology. ([arxiv.org](https://arxiv.org/abs/2401.02245?utm_source=openai)) ### BibTeX ```bibtex @inproceedings{harel2024augmenting, author = {David Harel and Guy Katz and Assaf Marron and Smadar Szekely}, title = {On Augmenting Scenario-Based Modeling with Generative AI}, booktitle = {Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering (MODELSWARD)}, pages = {235--246}, year = {2024}, publisher = {SciTePress}, doi = {10.5220/0012427100003645}, eprint = {2401.02245}, archivePrefix = {arXiv} } ``` Cited sources: - On Augmenting Scenario-Based Modeling with Generative AI: https://arxiv.org/abs/2401.02245?utm_source=openai ### 17. Assistant tool calls #### Tool call: `update_document_metadata` ```json { "authors": [ "David Harel", "Amir Kantor", "Guy Katz", "Assaf Marron", "Gera Weiss", "Guy Wiener" ], "document_id": "M5788P", "doi": "10.1016/j.scico.2014.03.003", "kind": "journal_article", "title": "Towards Behavioral Programming in Distributed Architectures", "venue": "Science of Computer Programming", "year": "2015" } ``` #### Tool call: `update_document_metadata` ```json { "authors": [ "David Harel", "Amir Kantor", "Guy Katz" ], "document_id": "TDS4H2", "doi": "10.1007/978-3-642-45221-5_25", "kind": "research_paper", "title": "Relaxing Synchronization Constraints in Behavioral Programs", "venue": "LPAR 2013 (Logic for Programming, Artificial Intelligence, and Reasoning)", "year": "2013" } ``` #### Tool call: `update_document_metadata` ```json { "authors": [ "Shlomi Steinberg", "Joel Greenyer", "Daniel Gritzner", "David Harel", "Guy Katz", "Assaf Marron" ], "document_id": "D4VB7S", "doi": "10.5220/0006271301820195", "kind": "research_paper", "title": "Distributing Scenario-Based Models: A Replicate-and-Project Approach", "venue": "MODELSWARD 2017", "year": "2017" } ``` #### Tool call: `update_document_metadata` ```json { "authors": [ "David Harel", "Guy Katz", "Assaf Marron", "Smadar Szekely" ], "document_id": "3JCRAD", "doi": "10.5220/0012427100003645", "kind": "research_paper", "title": "On Augmenting Scenario-Based Modeling with Generative AI", "venue": "MODELSWARD 2024", "year": "2024" } ``` ### 18. Tool result: update_document_metadata Updated metadata for #M5788P: kind, title, authors, year, venue, doi ### 19. Tool result: update_document_metadata Updated metadata for #TDS4H2: kind, title, authors, year, venue, doi ### 20. Tool result: update_document_metadata Updated metadata for #D4VB7S: kind, title, authors, year, venue, doi ### 21. Tool result: update_document_metadata Updated metadata for #3JCRAD: kind, title, authors, year, venue, doi ### 22. Assistant tool calls #### Tool call: `document_import` ```json { "action": "validate", "run_id": "93E66X" } ``` ### 23. Tool result: document_import { "action": "validate", "documents": [ { "title": "Towards Behavioral Programming in Distributed Architectures", "valid": true, "document_id": "M5788P", "readable_chunks": 417, "reader_path": "/M5788P", "source_pages": 58 }, { "title": "On tracing reactive systems", "valid": true, "document_id": "QV3BWZ", "readable_chunks": 273, "reader_path": "/QV3BWZ", "source_pages": 22 }, { "title": "Relaxing Synchronization Constraints in Behavioral Programs", "valid": true, "document_id": "TDS4H2", "readable_chunks": 133, "reader_path": "/TDS4H2", "source_pages": 17 }, { "title": "Enhancing Scenario-Based Modeling Using Large Language Models", "valid": true, "document_id": "CSJARA", "readable_chunks": 175, "reader_path": "/CSJARA", "source_pages": 26 }, { "title": "Distributing Scenario-Based Models: A Replicate-and-Project Approach", "valid": true, "document_id": "D4VB7S", "readable_chunks": 178, "reader_path": "/D4VB7S", "source_pages": 16 }, { "title": "On Augmenting Scenario-Based Modeling with Generative AI", "valid": true, "document_id": "3JCRAD", "readable_chunks": 139, "reader_path": "/3JCRAD", "source_pages": 12 }, { "title": "Adaptive Behavioral Programming", "valid": true, "document_id": "P2W4J5", "readable_chunks": 108, "reader_path": "/P2W4J5", "source_pages": 8 }, { "title": "Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems", "valid": true, "document_id": "XQ5NKX", "readable_chunks": 110, "reader_path": "/XQ5NKX", "source_pages": 8 } ], "run_id": "93E66X", "embedding_status": "completed", "embedding_errors": 0, "search_rows": 9548 } ### 24. Assistant All 8 PDFs imported and validated (run 93E66X), with metadata resolved — four via Crossref, four verified by web search: | Document | Title | Year / Venue | |---|---|---| | #M5788P | Towards Behavioral Programming in Distributed Architectures | 2015, Sci. Comput. Program. | | #QV3BWZ | On tracing reactive systems (Maoz & Harel) | 2010, SoSyM | | #TDS4H2 | Relaxing Synchronization Constraints in Behavioral Programs | 2013, LPAR | | #CSJARA | Enhancing Scenario-Based Modeling Using Large Language Models | 2026, CCIS 2547 | | #D4VB7S | Distributing Scenario-Based Models: Replicate-and-Project | 2017, MODELSWARD | | #3JCRAD | On Augmenting Scenario-Based Modeling with Generative AI | 2024, MODELSWARD | | #P2W4J5 | Adaptive Behavioral Programming (Eitan & Harel) | 2011, ICTAI | | #XQ5NKX | Challenges in Modeling and Unmodeling Emergence… | 2023, MODELSWARD | All documents pass validation and are fully searchable (embeddings complete, 0 errors). ### 25. User great. let's skim them enough to write good microabstracts and generate cover art ### 26. Assistant tool calls #### Tool call: `read` ```json { "blocks": [ "M5788P", "QV3BWZ", "TDS4H2", "CSJARA", "D4VB7S", "3JCRAD", "P2W4J5", "XQ5NKX" ] } ``` ### 27. Tool result: read {"error":"resource M5788P not found"} ### 28. Assistant tool calls #### Tool call: `list_documents` ```json {} ``` ### 29. Tool result: list_documents FOLDERS - Accounting Algebra & Property Theory - Living Structure, Wholeness & Beauty - Living Structure, Wholeness & Beauty - Procedural Generation & Co-Creation - Roads, Trails & Movement - Technology, Scale & Conviviality - Terrain, Hydrology & Erosion - Water Simulation & Rendering Accounting Algebra & Property Theory (4) - #GANFP9 A Fundamental Duality in the Mathematical and Natural Sciences: From Logic to Biology - 2024 | David Ellerman | 53 pp. Micro abstract: Traces an overlooked subset–partition duality—from logic and category theory through entropy and quantum indefiniteness to selectionist and generative mechanisms in biology. - #NBH3BE Algebraic Models for Accounting Systems - 2010 | Derek J. S. Robinson, José García Pérez, Robert A. Nehmer, Salvador Cruz Rambaud | World Scientific | 255 pp. Micro abstract: Develops accounting theory algebraically: balance vectors as modules, transactions as a group, and whole accounting systems as automata with quotients, homomorphisms, and decision algorithms for audit and control. - #7ESDBJ Economics, Accounting, and Property Theory - 1982 | David P. Ellerman | Lexington Books | 110 pp. Micro abstract: Ellerman's vector-accounting monograph: double entry generalized to property vectors ("accounting without valuation"), grounding a property-theoretic account of appropriation, the firm, and goodwill. - #C8FHDZ On implication and negation in partition logic - 2025 | , David Ellerman | Open Journal of Mathematical Sciences | 9 pp. | doi:10.30538/oms2025.0250 Micro abstract: Develops implication as a refinement-sensitive operation on set partitions, showing how relative negation yields local Boolean cores within the non-distributive algebra of partitions. Living Structure, Wholeness & Beauty (9) - #MH5J8D Beautimeter: Harnessing GPT for Assessing Architectural and Urban Beauty Based on the 15 Properties of Living Structure - 2025 | Bin Jiang | AI | 12 pp. | doi:10.3390/ai6040074 Micro abstract: Presents Beautimeter, a GPT-based tool that scores buildings and urban scenes against Christopher Alexander’s 15 properties of living structure to assess their coherence and beauty. - #XW22YY Generative Codes: The Path to Building Welcoming, Beautiful, Sustainable Neighborhoods - 2005 | Brian Hanson, Christopher Alexander, Maggie Moore Alexander, Michael Mehaffy, Randall Schmidt | Center for Environmental Structure | 21 pp. Micro abstract: Argues that living neighborhoods arise from generative codes: ordered, participatory steps that let buildings and public spaces unfold from local people, land, and context. - #SKRF4C Geography as a Science of the Earth’s Surface Founded on the Third View of Space - 2022 | Bin Jiang | Annals of GIS | 14 pp. | doi:10.1080/19475683.2021.1966502 Micro abstract: Recasts geography around an organismic view of space, using scaling and spatial dependence to understand—and deliberately create—places with greater living structure. - #PXG56P Harmony-Seeking Computations: A Science of Non-Classical Dynamics Based on the Progressive Evolution of the Larger Whole - 2009 | Christopher Alexander | Unpublished manuscript | 66 pp. Micro abstract: Proposes harmony-seeking computation as a creative process that repeatedly strengthens latent centers in a configuration while preserving and deepening the larger whole. - #MJKTBB Living Images: A Recursive Approach to Computing the Structural Beauty of Images or the Livingness of Space - 2023 | Bin Jiang, Chris de Rijke | Annals of the American Association of Geographers | 19 pp. | doi:10.1080/24694452.2023.2178376 Micro abstract: Measures an image’s structural beauty by recursively extracting its nested substructures, revealing a compact hierarchy that also captures visual saliency. - #3XSLTA Structural Beauty: A Structure-Based Computational Approach to Quantifying the Beauty of an Image - 2021 | Bin Jiang, Chris de Rijke | Journal of Imaging | 15 pp. | doi:10.3390/jimaging7050078 Micro abstract: Proposes a quantitative measure of structural beauty based on how many substructures an image contains and how strongly they form a hierarchy across scales. - #ZU8GZV Structure-Preserving Transformations - 2002 | Christopher Alexander | The Nature of Order, Book Two: The Process of Creating Life | 4 pp. | doi:10.2307/j.ctv27ftw6c.5 Micro abstract: Explains structure-preserving transformations: incremental changes that extend the centers and relationships already present in a place rather than weakening its wholeness. - #AULNWD The Nature of Poetic Order - 1998 | Richard P. Gabriel | Warren Wilson Alumni Conference, Mount Holyoke | 99 pp. Micro abstract: Gabriel's slide essay relating poetry's formal order to Christopher Alexander's ideas of generative structure, exploring how constraint and pattern produce living order in creative work. - #BYG3BQ Wholeness as a Hierarchical Graph to Capture the Nature of Space - 2015 | Bin Jiang | International Journal of Geographical Information Science | 14 pp. | doi:10.1080/13658816.2015.1038542 Micro abstract: Models spatial wholeness as a hierarchical graph of mutually reinforcing centers, using PageRank and scaling depth to quantify the life of parts and wholes. Procedural Generation & Co-Creation (14) - #ABD2B8 Between Tech and Art: The Vegetation of Horizon Zero Dawn - 2018 | Gilbert Sanders, Guerrilla Games | Game Developers Conference (GDC) 2018 | 87 pp. Micro abstract: A production breakdown of Horizon Zero Dawn’s vegetation pipeline, covering global wind simulation, layered foliage motion, coverage-preserving alpha mipmaps, shading, asset LODs, placement, and cascaded shadows. - #4TH488 Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation - 2018 | Antonios Liapis, G. Michael Youngblood, Jichen Zhu, Rafael Bidarra, Sebastian Risi | 2018 IEEE Conference on Computational Intelligence and Games (CIG) | 8 pp. | doi:10.1109/CIG.2018.8490433 Micro abstract: Defines explainable AI for game designers, mapping co-creative systems by their explainability, initiative, and domain overlap so explanations serve concrete design tasks. - #9NQ94D Extracting Physics from Blended Platformer Game Levels - 2020 | Adam Summerville, Anurag Sarkar, Joseph C. Osborn, Sam Snodgrass | Joint Proceedings of the AIIDE 2020 Workshops (CEUR Workshop Proceedings, Vol. 2862) | 7 pp. Micro abstract: Infers playable jump physics from generated platformer levels, including hybrid physics models for levels that blend the geometry and style of multiple games. - #66Q3W3 Ghost of Tsushima: Procedural Grass - 2021 | Eric Wohllaib, Sucker Punch Productions | Game Developers Conference (GDC) 2021 | 55 pp. Micro abstract: Explains Ghost of Tsushima’s compute-driven grass pipeline, from tiled placement and culling to indirect drawing, cubic Bézier blade geometry, variable LOD, wind animation, and material shading. - #QHMFH2 Improved Alpha Testing Using Hashed Sampling - 2019 | Chris Wyman, Morgan McGuire | IEEE Transactions on Visualization and Computer Graphics | 12 pp. | doi:10.1109/TVCG.2017.2739149 Micro abstract: Develops hashed alpha testing, a stable quasi-random thresholding method that preserves distant alpha-mapped foliage and hair while controlling flicker, anisotropy, and interactions with TAA and alpha-to-coverage. - #7GR3AQ Procedural Content Generation through Quality Diversity - 2019 | Ahmed Khalifa, Antonios Liapis, Daniele Gravina, Georgios N. Yannakakis, Julian Togelius | 2019 IEEE Conference on Games (CoG) | 8 pp. | doi:10.1109/CIG.2019.8848053 Micro abstract: Argues for quality-diversity algorithms in procedural generation, producing broad collections of varied, playable content while exposing the design space for exploration and co-creation. - #CQBDX4 Procedural Content Generation via Machine Learning (PCGML) - 2018 | Aaron Isaksen, Adam Summerville, Amy K. Hoover, Andy Nealen, Christoffer Holmgård, Julian Togelius, Matthew Guzdial, Sam Snodgrass | IEEE Transactions on Games | 15 pp. | doi:10.1109/TG.2018.2846639 Micro abstract: Defines and surveys PCGML: generating functional game content directly from models trained on existing examples, with uses spanning creation, completion, repair, critique, and compression. - #EARFEK Procedural Generation of Villages on Arbitrary Terrains - 2012 | Adrien Bernhardt, Adrien Peytavie, Arnaud Emilien, Eric Galin, Marie-Paule Cani | The Visual Computer | 10 pp. | doi:10.1007/s00371-012-0699-7 Micro abstract: Presents a three-stage procedural model that grows terrain-responsive village roads and settlements, partitions land into plausible parcels, and generates slope-adapted buildings with open shape grammars. - #EDURTK Real-Time GPU Tree Generation - 2025 | Bastian Kuth, Carsten Faber, Dominik Baumeister, Max Oberberger, Pirmin Pfeifer, Quirin Meyer, Seyedmasih Tabaei | High-Performance Graphics – Symposium Papers | 10 pp. | doi:10.2312/hpg.20251168 Micro abstract: Introduces a GPU work-graph pipeline that generates, animates, edits, and continuously LODs detailed seasonal trees every frame, replacing gigabytes of baked geometry with kilobytes of parameters. - #GBXEP3 Realistic Modeling and Rendering of Plant Ecosystems - 1998 | Bernd Lintermann, Matt Pharr, Oliver Deussen, Pat Hanrahan, Przemyslaw Prusinkiewicz, Radomír Měch | Proceedings of SIGGRAPH ’98 | 12 pp. | doi:10.1145/280814.280898 Micro abstract: Presents a foundational pipeline for authoring plant ecosystems through terrain design, ecological simulation, procedural plant models, approximate instancing, and efficient rendering of billion-primitive scenes. - #BDBBL6 Real‐time Realistic Rendering and Lighting of Forests - 2012 | Eric Bruneton, Fabrice Neyret | Computer Graphics Forum | 11 pp. | doi:10.1111/j.1467-8659.2012.03016.x Micro abstract: Combines detailed z-field trees with terrain shader-maps to render immense forests in real time, preserving sun, sky, canopy, and ground-lighting effects through seamless, scale-consistent transitions. - #PQ68ZH Responsive Real-Time Grass Rendering for General 3D Scenes - 2017 | Klemens Jahrmann, Michael Wimmer | Proceedings of the 2017 Symposium on Interactive 3D Graphics and Games (I3D ’17) | 10 pp. | doi:10.1145/3023368.3023380 Micro abstract: Renders every grass blade as responsive tessellated geometry on arbitrary 3D surfaces, with per-blade wind, gravity, and collision physics plus aggressive culling that retains dense fields in real time. - #WZ8DHP Runtime Evaluation of Procedural Content Generation in an Endless Runner Game Using Autonomous Agents - 2026 | Rishabh Kar | arXiv | 25 pp. | doi:10.48550/arXiv.2605.01783 Micro abstract: Integrates procedural generation and validation in an endless runner, using aerial and ground agents to detect blocked or unnavigable content before the player reaches it. - #NRBMD5 Towards Friendly Mixed Initiative Procedural Content Generation: Three Pillars of Industry - 2020 | Frederic Fol Leymarie, Gorm Lai, William Latham | Proceedings of the International Conference on the Foundations of Digital Games (FDG '20) | 4 pp. | doi:10.1145/3402942.3402946 Micro abstract: Distills three requirements for industry-friendly co-creative PCG tools: preserve designer control, keep feedback loops short, and fit into existing production pipelines. Roads, Trails & Movement (8) - #G3TBNG A Sequential Two-Step Algorithm for Fast Generation of Vehicle Racing Trajectories - 2016 | J. Christian Gerdes, John Subosits, Nitin R. Kapania | Journal of Dynamic Systems, Measurement, and Control | 12 pp. | doi:10.1115/1.4033311 Micro abstract: Generates near-optimal racing trajectories quickly by alternating between a minimum-time speed profile and a convex path update that reduces curvature. - #B6P8L4 Active walker model for the formation of human and animal trail systems - 1997 | Dirk Helbing, Frank Schweitzer, Joachim Keltsch, Péter Molnár | Physical Review E | 34 pp. | doi:10.1103/physreve.56.2527 Micro abstract: Models trail systems as self-organization: walkers reinforce attractive routes while unused traces fade, producing dendritic ant trails and low-detour pedestrian networks. - #V4TQYB Interactive procedural street modeling - 2008 | Eugene Zhang, Gregory Esch, Guoning Chen, Pascal Müller, Peter Wonka | ACM Transactions on Graphics | 10 pp. | doi:10.1145/1360612.1360702 Micro abstract: Lets designers generate and edit large street networks through tensor fields, combining procedural speed with brush-like global and local control over street patterns. - #UYLTYJ Modelling the Evolution of Human Trail Systems - 1997 | Dirk Helbing, Joachim Keltsch, Péter Molnár | Nature | 11 pp. | doi:10.1038/40353 Micro abstract: Shows how pedestrian trails emerge through feedback between destination-seeking walkers, existing paths, and vegetation recovery, yielding a compromise between directness and shared infrastructure. - #GY93FG Mountain Trail Formation and the Active Walker Model - 2009 | J. P. Hague, S. J. Gilks | International Journal of Modern Physics C | 22 pp. | doi:10.1142/S0129183109014059 Micro abstract: Extends the active-walker model to steep terrain, explaining zigzag mountain trails through slope avoidance, directional persistence, and mutual reinforcement by ascending and descending walkers. - #LXV9AT Principles of Trail Layout and Design - 2019 | California State Parks | California State Parks Trails Handbook | 64 pp. Micro abstract: A field-oriented guide to durable trail design, emphasizing curvilinear alignment, natural drainage, sustainable grades, control points, and close reading of landform and soils. - #XDEFZS Procedural Generation of Roads - 2010 | A. Peytavie, E. Galin, E. Guérin, N. Maréchal | Computer Graphics Forum | 10 pp. | doi:10.1111/j.1467-8659.2009.01612.x Micro abstract: Automatically routes and constructs roads with an anisotropic shortest-path method that weighs slope and obstacles while treating surface segments, bridges, and tunnels consistently. - #ARP5U7 The Topography of Minoan Peak Sanctuaries - 1983 | A. A. D. Peatfield | The Annual of the British School at Athens | 8 pp. | doi:10.1017/s0068245400019729 Micro abstract: Argues that Minoan peak sanctuaries were chosen for visibility and proximity to local settlements, forming a beacon-like sacred network whose contraction tracked settlement abandonment rather than cultic collapse. Technology, Scale & Conviviality (2) - #WYH36B The City as Convivial Centre - 1974 | Leopold Kohr | Tract, no. 12 (Gryphon Press) | 18 pp. Micro abstract: Kohr's essay arguing that cities exist for convivial life rather than economic function, and that human-scale size is what lets a city serve as a centre of leisure, culture, and encounter. - #67REFX The Question Concerning Technology - 1977 | Martin Heidegger | The Question Concerning Technology and Other Essays (Harper & Row) | 23 pp. Micro abstract: Heidegger's essay on the essence of technology as Enframing (Gestell), a mode of revealing that reduces the world to standing-reserve, and on art as a possible saving power. Terrain, Hydrology & Erosion (8) - #NV2YRW FastFlow: GPU Acceleration of Flow and Depression Routing for Landscape Simulation - 2024 | Aryamaan Jain, Bernhard Kerbl, Brandon Finley, Guillaume Cordonnier, James Gain | Computer Graphics Forum | 13 pp. | doi:10.1111/cgf.15243 Micro abstract: A GPU framework for routing surface flow through terrain and its depressions fast enough to make erosion, river, lake, and ecosystem simulations interactive. - #2284QZ From features to fingerprints: A general diagnostic framework for anthropogenic geomorphology - 2019 | Damian Evans, Erle C Ellis, Giulia Sofia, Paolo Tarolli, Wenfang Cao | Progress in Physical Geography: Earth and Environment | 34 pp. | doi:10.1177/0309133318825284 Micro abstract: Integrates geomorphology, archaeology, and high-resolution remote sensing into a framework for reading anthropogenic landforms as landscape-scale sociocultural fingerprints. - #96ZMGK Large Scale Terrain Generation from Tectonic Uplift and Fluvial Erosion - 2016 | Adrien Peytavie, Bedrich Benes, Guillaume Cordonnier, Jean Braun, Marie-Paule Cani, Éric Galin, Éric Guérin | Computer Graphics Forum | 11 pp. | doi:10.1111/cgf.12820 Micro abstract: Generates large, controllable mountain terrains by coupling user-painted tectonic uplift with fluvial erosion, then turning the resulting stream graph into detailed landforms. - #K82AS7 Legacy sediment: Definitions and processes of episodically produced anthropogenic sediment - 2013 | L. Allan James | Anthropocene | 11 pp. | doi:10.1016/j.ancene.2013.04.001 Micro abstract: Broadens legacy sediment to episodically produced anthropogenic alluvium and colluvium, and explains its deposition, storage, and remobilization through sediment delivery–transport capacity dynamics. - #DWXKYQ Physically-based analytical erosion for fast terrain generation - 2024 | Boris Gailleton, Guillaume Cordonnier, Petros Tzathas, Philippe Steer | Computer Graphics Forum | 14 pp. | doi:10.1111/cgf.15033 Micro abstract: Turns the stream power law into an interactive terrain tool, replacing thousands of erosion time steps with analytical solutions and a direct control for landscape age. - #MTDKDE Priority-Flood: An Optimal Depression-Filling and Watershed-Labeling Algorithm for Digital Elevation Models - 2014 | Clarence Lehman, David Mulla, Richard Barnes | Computers & Geosciences | 17 pp. | doi:10.1016/j.cageo.2013.04.024 Micro abstract: Introduces Priority-Flood, a simple, optimal algorithm that removes drainage-blocking depressions from elevation models and can also derive watersheds and flow directions. - #AK7NGE Procedural Riverscapes - 2019 | A. Peytavie, B. Benes, E. Galin, E. Guérin, J. Gain, T. Dupont, Y. Cortial | Computer Graphics Forum | 12 pp. | doi:10.1111/cgf.13814 Micro abstract: Builds editable, animated riverscapes from bare terrain by carving hydrologically plausible channels and blending real-time procedural water primitives instead of simulating fluids. - #DMTA8Y Terrain Generation Using Procedural Models Based on Hydrology - 2013 | Adrien Peytavie, Bedřich Beneš, Jean-David Génevaux, Éric Galin, Éric Guérin | ACM Transactions on Graphics | 10 pp. | doi:10.1145/2461912.2461996 Micro abstract: Generates controllable, multiscale terrain from a sketched drainage network, representing rivers and landforms as an editable hierarchy of continuous procedural primitives. Water Simulation & Rendering (12) - #RBS5K6 A Layered Particle-Based Fluid Model for Real-Time Rendering of Water - 2010 | Daniel Scherzer, Florian Bagar, Michael Wimmer | Computer Graphics Forum | 7 pp. | doi:10.1111/j.1467-8659.2010.01734.x Micro abstract: Renders particle-based water and volumetric foam in real time using perspective-aware surface smoothing, physically guided foam formation, and layered depth compositing. - #C4AY2M A Survey of Ocean Simulation and Rendering Techniques in Computer Graphics - 2011 | B. Crespin, D. Ghazanfarpour, E. Darles, J.-C. Gonzato | Computer Graphics Forum | 17 pp. | doi:10.1111/j.1467-8659.2010.01828.x Micro abstract: Surveys ocean graphics from spectral deep-water models to near-shore fluid simulation, then covers the foam, spray, and light transport needed for convincing rendering. - #WZMZGY Advected river textures - 2009 | Dirk Arnold, Stephen Brooks, Tim Burrell | Computer Animation and Virtual Worlds | 11 pp. | doi:10.1002/cav.288 Micro abstract: Combines a 2D Navier–Stokes solver, hydrostatic pressure columns, and advected procedural textures to render detailed, terrain-responsive rivers at real-time frame rates. - #92XRH7 Lagrangian Texture Advection: Preserving both Spectrum and Velocity Field - 2011 | Qizhi Yu, E. Bruneton, F. Neyret, N. Holzschuch | IEEE Transactions on Visualization and Computer Graphics | 13 pp. | doi:10.1109/tvcg.2010.263 Micro abstract: Advects fluid textures with deformable particle grids, preserving both the input texture’s visual spectrum and exact motion along the velocity field without cumulative stretching. - #8SERGP Real-time Breaking Waves for Shallow Water Simulations - 2007 | Markus Gross, Matthias Müller-Fischer, Nils Thürey, Simon Schirm | 15th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2007) | 8 pp. | doi:10.1109/PG.2007.33 Micro abstract: Adds real-time overturning waves to shallow-water heightfields by detecting steep fronts and spawning connected particle sheets that collapse into splashes and foam. - #CWC7H9 Real-time Rendering of Enhanced Shallow Water Fluid Simulations - 2013 | Antonio Susín, Jesús Ojeda | Computers & Graphics | 9 pp. Micro abstract: Builds a real-time rendering pipeline for shallow-water simulations, adding fine surface detail, advected foam, photon-based caustics, and screen-space reflection and refraction. - #MVUJ8Z Real-time Rendering of River Networks - 2010 | Quintijn Hendrickx, Rafael Bidarra, Ruben M. Smelik | Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games | 1 pp. Micro abstract: Renders branching river networks efficiently with quadratic Bézier curves, GPU distance fields, and streaming normal maps instead of dense geometry or particle simulation. - #5MGCZ5 Real-time River Representation by Dynamic Control of Data on Waves - 2008 | Makoto Kosugi, Nobuhiko Mukai, Yasuhiro Kato | 4 pp. | doi:10.3169/itej.62.2063 Micro abstract: Dynamically switches river-wave models by viewing distance, preserving nearby reflection and wave detail while retaining wind-driven motion across the full landscape. - #XDESU9 Scalable real‐time animation of rivers - 2009 | Eric Bruneton, Fabrice Neyret, Nicolas Holzschuch, Qizhi Yu | Computer Graphics Forum | 11 pp. | doi:10.1111/j.1467-8659.2009.01363.x Micro abstract: Animates rivers across vast terrains by computing steady flow locally and advecting fine surface detail only where visible, at a screen-space sampling density. - #869NHK Very Fast Real-Time Ocean Wave Foam Rendering Using Halftoning - 2011 | Ian Parberry, Jennifer R. Alford, Mary Yingst | Proceedings of the 6th International North American Conference on Intelligent Games and Simulation (GAMEON-NA) | 7 pp. Micro abstract: Uses a spectrally controlled halftone mask to make texture-based ocean foam dissipate as clumped bubbles that pop, rather than merely fading transparently. - #A2QB8L Water Flow in Portal 2 - 2010 | Alex Vlachos | ACM SIGGRAPH 2010 Course: Advances in Real-Time Rendering in 3D Graphics and Games | 54 pp. Micro abstract: Explains Portal 2’s production-friendly water shader: artist-painted flow maps advect layered normal maps, while offsets and noise suppress repetition and pulsing on limited hardware. - #PBM2TC Water surface wavelets - 2018 | Chris Wojtan, Matthias Müller-Fischer, Miles Macklin, Nuttapong Chentanez, Stefan Jeschke, Tomáš Skřivan | ACM Transactions on Graphics | 13 pp. | doi:10.1145/3197517.3201336 Micro abstract: Represents water waves as spatially varying directional amplitudes, enabling vast interactive simulations with fine detail, moving obstacles, solid coupling, and direct artistic control. Unfiled (8) - #P2W4J5 Adaptive Behavioral Programming - 2011 | David Harel, Nir Eitan | 8 pp. | doi:10.1109/ictai.2011.109 - #XQ5NKX Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems - 2023 | Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely | 8 pp. | doi:10.5220/0011728900003402 - #D4VB7S Distributing Scenario-Based Models: A Replicate-and-Project Approach - 2017 | Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg | MODELSWARD 2017 | 16 pp. | doi:10.5220/0006271301820195 - #CSJARA Enhancing Scenario-Based Modeling Using Large Language Models - 2026 | Assaf Marron, David Harel, Guy Katz, Smadar Szekely | Communications in Computer and Information Science | Springer Nature Switzerland | pp. 43-68 | 26 pp. | doi:10.1007/978-3-031-96841-9_3 - #3JCRAD On Augmenting Scenario-Based Modeling with Generative AI - 2024 | Assaf Marron, David Harel, Guy Katz, Smadar Szekely | MODELSWARD 2024 | 12 pp. | doi:10.5220/0012427100003645 - #QV3BWZ On tracing reactive systems - 2011 | David Harel, Shahar Maoz | Software & Systems Modeling | 22 pp. | doi:10.1007/s10270-010-0151-2 - #TDS4H2 Relaxing Synchronization Constraints in Behavioral Programs - 2013 | Amir Kantor, David Harel, Guy Katz | LPAR 2013 (Logic for Programming, Artificial Intelligence, and Reasoning) | 17 pp. | doi:10.1007/978-3-642-45221-5_25 - #M5788P Towards Behavioral Programming in Distributed Architectures - 2015 | Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener | Science of Computer Programming | 58 pp. | doi:10.1016/j.scico.2014.03.003 ### 30. Assistant tool calls #### Tool call: `search_text` ```json { "document_id": "M5788P", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "QV3BWZ", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "TDS4H2", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "CSJARA", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "D4VB7S", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "3JCRAD", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "P2W4J5", "limit": 3, "query": "abstract we propose in this paper" } ``` #### Tool call: `search_text` ```json { "document_id": "XQ5NKX", "limit": 3, "query": "abstract we propose in this paper" } ``` ### 31. Tool result: search_text Exact matches 1. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 1 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #5SGDUB 1. Introduction Matching excerpt #3NR3XZ: The principles of BP were first introduced in the visual language of live sequence charts (LSC) [14, 21], where parallel processes represent multi-modal scenarios of desired, mandatory or forbidden behavior of the system. These principles were later implemented in other programming languages and frameworks, such as Java [23], JavaScript with Blockly [38], SBT [35], and in the C language in the PiCos environment [42]. As part of this extension the term behavior threads or b-threads , defined formally below, was introduced. For an extensive review of the BP approach see [27]. In this paper, we begin the handling of distributed environments by describing, in Section 2, the BP development approach as a design pattern in Erlang [4]. Erlang was chosen because its entire architecture and development mindset is based on decomposing the application into relatively independent parallel processes, which indeed fits well with the basic principles of BP. We then explore how the two paradigms coexist. We demonstrate how enabling behavioral programming in Erlang enhances the capabilities for incremental development and how it allows alignment of the code with the scenarios described in the requirements documents. BP will thus join and complement other design patterns and packages in Erlang, such as gen_server or gen_fsm , aimed to assist in coordinating distributed processes ( gen_server is an Erlang package for implementing the server of a client-server relation, and gen_fsm is a package for implementing a finite state machine). Specifically, we propose to implement b-threads as Erlang processes. The system is executed using an infrastructure module that uses standard Erlang message passing to constantly synchronize and coordinate the b-threads. We also introduce a proof-of-concept mechanism for visualizing the flow of individual scenarios coded in Erlang as self-explanatory transition systems, aimed at improving the comprehension of applications written in this manner. That section thus shows that the natural, incremental development facilitated by BP applies also in the context of distributed architectures based on message passing. 2. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 42 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #B7CAR2 Acknowledgements Matching excerpt #86HTX9: We thank the anonymous reviewers for valuable comments and suggestions on an earlier version of this paper. These comments have led to a substantial enhancement of the paper. We would like to thank Einat Fuchs, whose lecture about coordination of cockroach locomotion [17] inspired some of the ideas in this paper. We thank Dan Brownstein and Nir Svirsky for their programming work on the MATLAB simulation and the control software of the behaviorally-controlled quadrotor, and Nadav Shechter and Oren Othnay for their work on flying a real quadrotor with BP. 3. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 50 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #9XXUP6 Appendix C. Nondeterministic Threads #Q8L7S4 Appendix C.1. Eager Execution of Programs with Nondeterministic Threads Matching excerpt #C5RLGX: As we briefly mentioned in the paper, eager execution can be adapted to programs with nondeterministic threads. We now discuss this adaptation more thoroughly. Approximate matches 1. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 52 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #L77LJ3 Appendix D. Modularity Formalized Score: 0.03 Related excerpt #VRAJE8: In this section we use the formalization of eager execution described in Section 4.2.2 in order to rigorously formulate and prove Proposition 1. 2. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 54 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #TQXT4D Appendix E. The Distributed Execution Mechanism Score: 0.028 Related excerpt #Y58CV2: In the next section we describe an example of a distributed application; and in Appendix E.1 we formally define the model and prove Lemma 3. 3. Source: Towards Behavioral Programming in Distributed Architectures (#M5788P), Amir Kantor, Assaf Marron, David Harel, Gera Weiss, Guy Katz, Guy Wiener, p. 2 Context: #GVFU8Q Towards Behavioral Programming in Distributed Architectures1 #5SGDUB 1. Introduction Score: 0.028 Related excerpt #4AA6PZ: In Section 6 we discuss how BP coexists with and complements actor-oriented, agent-oriented and aspect-oriented programming, as well as other decentralized control development approaches. ### 32. Tool result: search_text Exact matches 1. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 1 Context: #59KNHA On tracing reactive systems #5ZYGKU 1 Introduction #BNZ6TP 1.1 Example application Matching excerpt #5QRSH7: We consider the PacMan game to be a well-known, intuitive, relatively small, and yet complex enough reactive system. Hence it is a good choice for the purpose of demonstrating the model-based trace visualization techniques we present in this paper. 2. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 14 Context: #59KNHA On tracing reactive systems #FJCNVT 7 Evaluation #23P959 7.1 The Tracer prototype implementation Matching excerpt #ULAFF5: In order to evaluate and test our ideas we have implemented a prototype tool called the Tracer . All screenshots shown in this paper are taken from the Tracer. Additional documentation, including screenshots and screencasts of the Tracer demonstrating its various features, are available on our Tracer website [9]. 3. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 12 Context: #59KNHA On tracing reactive systems #QSS5MU 5 Trace exploration #8HMNDS 5.3 Comparisons Matching excerpt #6TCR7D: Our work is deliberately limited to the abstraction level defined by the specification model used for tracing, and the kinds of comparisons we are discussing here are no exception; they are carried out with respect to the same abstraction. Thus, as mentioned in Sect. 2.2.1, different concrete runtime traces may result in identical model-based traces—in our case, scenario-based traces—if the concrete runs are equivalent from the more abstract point of view of the model used for trace generation. Our comparison features indeed reveal this important property. Approximate matches 1. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 14 Context: #59KNHA On tracing reactive systems #FJCNVT 7 Evaluation #23P959 7.1 The Tracer prototype implementation Score: 0.016 Related excerpt #ULAFF5: In order to evaluate and test our ideas we have implemented a prototype tool called the Tracer . All screenshots shown in this paper are taken from the Tracer. Additional documentation, including screenshots and screencasts of the Tracer demonstrating its various features, are available on our Tracer website [9]. 2. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 8 Context: #59KNHA On tracing reactive systems #E5FF5G 4 Trace visualization: advanced features #LP2BS9 4.2 Time-based and event-normalized tracing Score: 0.016 Related excerpt #M7Z5L7: This kind of abstraction is not new and is typically reflected in the language chosen to specify a system's behavior. For example, the basic variants of temporal logics , LTL (linear temporal logic) and CTL (computation tree logic), indeed do not consider the actual durations of happenings but only their order [17]. Similarly, the variant of LSC used in our work does not consider real-time. For example, the LSC shown in Fig. 5 specifies that whenever a collision hap- 3. Source: On tracing reactive systems (#QV3BWZ), David Harel, Shahar Maoz, p. 0 Context: #59KNHA On tracing reactive systems #5ZYGKU 1 Introduction Score: 0.016 Related excerpt #CVYQ4A: Preliminary version appeared in VL/HCC '07: Proc. IEEE Symp. on Visual Languages and Human-Centric Computing (September 2007) [46]. This research was supported in part by the John von Neumann Minerva Center for the Development of Reactive Systems at the Weizmann Institute of Science, and by an Advanced Research Grant from the European Research Council (ERC) under the European Community's Seventh Framework Programme (FP7/2007-2013). ### 33. Tool result: search_text Exact matches 1. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 0 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs Matching excerpt #9H9YU2: Abstract. In behavioral programming , a program consists of separate modules called behavior threads , each representing a part of the system's allowed, necessary or forbidden behavior. An execution of the program is a series of synchronizations between these threads, where at each synchronization point an event is selected to be carried out. As a result, the execution speed is dictated by the slowest thread. We propose an eager execution mechanism for such programs, which builds upon the realization that it is often possible to predict the outcome of a synchronization point even without waiting for slower threads to synchronize. This allows faster threads to continue running uninterrupted, whereas slower ones catch up at a later time. Consequently, eager execution brings about increased system performance, better support for the modular design of programs, and the ability to distribute programs across several machines. It also allows to apply behavioral programming to a variety of problems that were previously outside its scope. We illustrate the method by concrete examples, implemented in a behavioral programming framework in C ++ . 2. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 1 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs #GJBGMA 1 Introduction Matching excerpt #8RLVTV: The paper is organized as follows. A short description of behavioral programming and the BPC tool appears in Section 2. We define the eager execution mechanism and present the two analysis methods in Section 3. In Section 4, we show how eager execution allows for a modular design of programs. Related work is discussed in Section 5, and we conclude in Section 6. Proofs are included in the appendices to this paper. 3. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 1 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs #GJBGMA 1 Introduction Matching excerpt #VTA4CC: Relaxing synchronization is helpful in several contexts. First, it improves system performance and reduces processor idle time. Moreover, it gives rise to better modular design of the system, by grouping together related threads into components, which we call behavioral modules , and allowing these to operate independently on different time scales. Finally, the techniques presented in this paper can be leveraged to support a decentralized assimilation of the modules on different machines by distributing BP’s execution mechanism. Distributed execution has been implemented and tested in BPC. It is not included in this paper due to space limitations; it is discussed in Appendix I of [2]. Approximate matches 1. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 3 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs #YZJE2D 2 Behavioral Programming #KWNH5E 2.1 Behavioral Programming Formalized Score: 0.016 Related excerpt #V238NV: described and analyzed in terms of transition systems. We present an abstract formalization of behavioral programs and their semantics, similarly to [9, 11]. 2. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 13 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs #877H7Z 6 Conclusion and Future Work Score: 0.016 Related excerpt #NM6PMA: In this paper we made no assumptions on how the coordinator chooses the next event to be triggered from among the enabled events. In practice, however, such assumptions can sometimes simplify system development. One example is the prioritized event selection used in [9]. We believe that our methods can be naturally adapted to such mechanisms too. 3. Source: Relaxing Synchronization Constraints in Behavioral Programs (#TDS4H2), Amir Kantor, David Harel, Guy Katz, p. 2 Context: #KBEBVQ Relaxing Synchronization Constraints in Behavioral Programs #YZJE2D 2 Behavioral Programming Score: 0.016 Related excerpt #7WKGLC: Various implementations of reactive systems as behavioral programs have been carried out, using frameworks built on top of high-level programming languages such as Java, Erlang and Blockly; see [10] and references therein. These frameworks allow the user to use the full flexibility offered by the underlying programming language in writing threads. In this paper, we demonstrate our techniques using a BP framework in C ++ , termed BPC [1]. ### 34. Tool result: search_text Exact matches 1. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 9 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #UN8V7M 4 Using the Method in the Development Cycle #HPV4H8 4.1 Code Generation Matching excerpt #AWGKBY: Code generation is one of the most straightforward capabilities of chatbots that we propose to integrate into a system’s development cycle. In Sect. 3 we demonstrated that ChatGPT can generate an executable, scenario-based model—and similar capabilities have been demonstrated with other languages [6, 39, 45]. One advantage in the context of scenario-based systems is that it is possible to generate stand-alone scenarios, which can then be tested and reviewed separately, and later be added, incrementally, to the system at hand. In our preliminary experimentation for this paper, we tested code generation for requirements in the realms of algorithms on data structures, autonomous vehicles, control systems, and simulating natural phenomena. For each of these realms, the chatbot/SBM integration proved useful. 2. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 1 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #64PYXR 1 Introduction Matching excerpt #LD5CBS: In this paper, we advocate for the design of an encompassing modeling scheme, which would allow engineers to combine chatbots such as ChatGPT with more manual, “traditional” techniques for systems modeling [5, 44], in such a way that will achieve the aforementioned goal. The core idea is to make use of ChatGPT in a more controlled way; i.e., by repeatedly invoking it for various tasks, but to also repeatedly analyze and inspect its results, in order to ensure their accuracy and soundness. We believe that such schemes, if properly designed, could allow software engineers to benefit from the capabilities of ChatGPT without jeopardizing the quality of the resulting systems. In the longer run, we argue that such a scheme could constitute a step towards the vision of Wise Computing [25], which includes the turning of the computer into a proactive member of the engineering team—which can propose possible courses of action, detect under-specified sections of the model, and support the various routine actions that arise as part of the development cycle of modern software. 3. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 7 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #FPHT3K 3 Integrating ChatGPT and SBM #LLLLH2 3.2 The Proposed Methodology Matching excerpt #TMBRUS: Further extending the basic integration between SBM and ChatGPT, we now propose an outline for a structured, language-agnostic and LLM-agnostic methodology for creating complex models of reactive systems that interact with their environment repeatedly, and may receive external inputs [35]. Many critical, modern systems can be regarded as reactive [1], and as a result there has been extensive work on devising methods and tools for modeling such systems. In spite of this tremendous effort, there still remain significant gaps; and these could result in models that are either inaccurate or difficult to maintain, or both. In this paper, which can be regarded as an element within the Wise Computing vision [25], we seek to mitigate these gaps, by creating advanced and intelligent tools, which will begin to undertake system development tasks that are traditionally reserved for humans. The approach is based on having system components generated, incrementally and iteratively, through the use of an LLM; and to have the LLM's outputs checked systematically, and semi-automatically, using various methods and tools (see Fig. 2). Approximate matches 1. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 21 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #H5D7PV 6 Related Work Score: 0.016 Related excerpt #YXTBG7: Finally, this paper can be regarded as yet another step towards the overarching vision of Wise Computing [23–25]. Wise computing is an attempt to transform the computer into a proactive member of the software engineering team—making suggestions and observations, raising questions, and even carrying out verification-like processes without an explicit request from a human engineer. 2. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 2 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #64PYXR 1 Introduction Score: 0.016 Related excerpt #PQGBJQ: In the rest of the paper, we discuss the key concepts of our proposed approach, and lay out a high-level plan for future steps. We start with an introduction to the concepts of SBM and language model-based chatbots, in Sect. 2. We then present the proposed integration of ChatGPT and SBM in Sect. 3, and continue with a discussion of the more advanced aspects of such an integration in Sect. 4. In Sect. 5 we present technical and methodological challenges that emerged in our experiments as well as directions for addressing these challenges in further refinement of the methodology. Next, we discuss related work in Sect. 6, followed by a conclusion in Sect. 7. 3. Source: Enhancing Scenario-Based Modeling Using Large Language Models (#CSJARA), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 7 Context: #ZHMNW8 Enhancing Scenario-Based Modeling Using Large Language Models #FPHT3K 3 Integrating ChatGPT and SBM #LLLLH2 3.2 The Proposed Methodology Score: 0.016 Related excerpt #TMBRUS: Further extending the basic integration between SBM and ChatGPT, we now propose an outline for a structured, language-agnostic and LLM-agnostic methodology for creating complex models of reactive systems that interact with their environment repeatedly, and may receive external inputs [35]. Many critical, modern systems can be regarded as reactive [1], and as a result there has been extensive work on devising methods and tools for modeling such systems. In spite of this tremendous effort, there still remain significant gaps; and these could result in models that are either inaccurate or difficult to maintain, or both. In this paper, which can be regarded as an element within the Wise Computing vision [25], we seek to mitigate these gaps, by creating advanced and intelligent tools, which will begin to undertake system development tasks that are traditionally reserved for humans. The approach is based on having system components generated, incrementally and iteratively, through the use of an LLM; and to have the LLM's outputs checked systematically, and semi-automatically, using various methods and tools (see Fig. 2). ### 35. Tool result: search_text Exact matches 1. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 3 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach #B87VZR 3 DISTRIBUTION VIA REPLICATE-AND-PROJECT Matching excerpt #WMLYZY: In this section we propose a distribution process that transforms a centralized (undistributed) behavioral model into a distributed one: it generates multiple component models — subsets of the original, centralized behavioral model — each designed to be run on a separate machine. When run simultaneously, however, these component models mimic the behavior of the original system, but require much less synchronization. Below we elaborate on the abstract concepts and formal definitions of the proposed process. An example showing how these concepts apply in the setting of a particular distributed application appears in Section 5. 2. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 4 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach #B87VZR 3 DISTRIBUTION VIA REPLICATE-AND-PROJECT Matching excerpt #6EBGV6: The classical problem of multicasting or broadcasting a message efficiently in a distributed network is well studied (e.g. (Miller and Poellabauer, 2009) presents an approach for minimum-energy-broadcasts in distributed networks with limited resources and unknown topology), however it is beyond the scope of this paper. For simplicity we assume that the cost of those broadcasts and bookkeeping is small. Note that even in systems with a large number of components and scenarios, a component often needs to keep track of only a small subset of the other components; for example, an autonomous car considers other cars only when they are in its immediate vicinity, and does not keep track of all vehicles in the world. Still, this dynamic registering and unregistering of components is also beyond the scope of this paper and is left for future work. 3. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 1 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach #EQ58MY 1 INTRODUCTION Matching excerpt #MSQ2R2: The rest of the paper is organized as follows. In Section 2 we provide a brief introduction to the scenario-based approach. In Section 3 we introduce the notion of a distributed scenario-based model, and show how it can be automatically generated from a non-distributed model by our replicate-and-project technique. The correctness of this transformation is proved in Appendix A. Section 4 describes how the approach can be applied when different components in the model operate on different time scales. An example implementation and its evaluation appear in Section 5, followed by a discussion in Section 6 of our ongoing and planned future work. In section 7, we discuss related work that has been carried out on automatic distribution, both in the general setting and in the context of scenario-based modeling. We conclude in Section 8. Approximate matches 1. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 0 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach Score: 0.028 Related excerpt #S3CX43: Abstract: In recent years, scenario-based modeling has been proposed to help mitigate some of the underlying difficulties in modeling complex reactive systems, by allowing modelers to specify system behavior in a way that is intuitive and directly executable. This modeling approach simplifies the specification of systems that include events occurring in distinct system components. However, when these system components are physically distributed, executing the scenario-based model requires inter-component coordination that may negatively affect system performance or robustness. We describe a technique that aims to reduce the amount of joint eventselection decisions that require coordination and synchronization among distributed system components. The technique calls for replicating the entire scenario-based executable specification in each of the components, and then transforming it in a component-specific manner that induces the required differences in execution while reducing synchronization requirements. In addition to advantages in streamlining design and improving performance, our approach captures the fact that in certain “smart” distributed systems it is often required that components know what rules govern the behavior of other components. Our evaluation of the technique shows promising results. 2. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 1 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach #EQ58MY 1 INTRODUCTION Score: 0.028 Related excerpt #NYDQ5E: We seek to address this problem by proposing an automated technique for the transformation of classical, highly synchronous scenario-based models into equivalent models with a greatly reduced level of synchronization. The basis of our approach is a rather straightforward replicate-and-project technique but with some subtle facets: we replicate the full set of scenarios in all the distributed components but project them in a component-specific fashion, so that each component is made responsible only for the actions that fall within its the local scope. Other, external actions are assumed to be performed by projections running on other components. 3. Source: Distributing Scenario-Based Models: A Replicate-and-Project Approach (#D4VB7S), Assaf Marron, Daniel Gritzner, David Harel, Guy Katz, Joel Greenyer, Shlomi Steinberg, p. 1 Context: #D8TLPF Distributing Scenario-Based Models: A Replicate-and-Project Approach #EQ58MY 1 INTRODUCTION Score: 0.016 Related excerpt #MSQ2R2: The rest of the paper is organized as follows. In Section 2 we provide a brief introduction to the scenario-based approach. In Section 3 we introduce the notion of a distributed scenario-based model, and show how it can be automatically generated from a non-distributed model by our replicate-and-project technique. The correctness of this transformation is proved in Appendix A. Section 4 describes how the approach can be applied when different components in the model operate on different time scales. An example implementation and its evaluation appear in Section 5, followed by a discussion in Section 6 of our ongoing and planned future work. In section 7, we discuss related work that has been carried out on automatic distribution, both in the general setting and in the context of scenario-based modeling. We conclude in Section 8. ### 36. Tool result: search_text Exact matches 1. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 0 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI Matching excerpt #5QRGC9: Abstract: The manual modeling of complex systems is a daunting task; and although a plethora of methods exist that mitigate this issue, the problem remains very difficult. Recent advances in generative AI have allowed the creation of general-purpose chatbots, capable of assisting software engineers in various modeling tasks. However, these chatbots are often inaccurate, and an unstructured use thereof could result in erroneous system models. In this paper, we outline a method for the safer and more structured use of chatbots as part of the modeling process. To streamline this integration, we propose leveraging scenario-based modeling techniques, which are known to facilitate the automated analysis of models. We argue that through iterative invocations of the chatbot and the manual and automatic inspection of the resulting models, a more accurate system model can eventually be obtained. We describe favorable preliminary results, which highlight the potential of this approach. 2. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 5 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI #9WLWJE 4 USING THE METHOD IN THE DEVELOPMENT CYCLE #GFGWAX 4.1 Code Generation Matching excerpt #W637V9: Code generation is probably the most straightforward chatbot capability that we propose be integrated into the development cycle. In Section 3 we showed that ChatGPT can generate an (executable) SB model — a capability that has also been demonstrated with other languages (Surameery and Shakor, 2023; Burak et al., 2023; Liu et al., 2023). A unique advantage in the context of SB systems is the ability to generate stand-alone scenarios, which can be reviewed and tested separately, and then be incrementally added to the system under development. In our preliminary testing for this paper, we experimented with code generation for requirements in the realms of autonomous vehicles, algorithms on data structures, simulating natural phenomena, and control systems. In all of these, the ChatGPT/SBM integration proved useful. 3. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 1 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI #YCTU28 1 INTRODUCTION Matching excerpt #HCYBCG: In order to design such a modeling scheme, we propose to leverage the extensive work carried out in the modeling community over the years. Specifically, we propose to focus on modeling frameworks that afford two benefits that complement the capabilities of ChatGPT: (i) the models produced by the framework are naturally well-aligned with how humans perceive systems; this, we believe, will make it easier for the human engineer to inspect ChatGPT’s output; and (ii) the resulting models are amenable to automated analysis tasks, such as model checking, which will support the automated detection of bugs and inconsistencies in the automatically generated models. Approximate matches 1. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 1 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI #YCTU28 1 INTRODUCTION Score: 0.016 Related excerpt #3GMY9J: In the remainder of the paper, we present the key concepts of our approach, and discuss a high-level plan for the next steps. We begin by introducing the concepts of SBM and language model-based chatbots in Section 2. Next, we present the proposed integration of SBM and ChatGPT in Section 3, followed by a discussion of some of the more advanced aspects of 2. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 0 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI #YCTU28 1 INTRODUCTION Score: 0.016 Related excerpt #NSNJDZ: Here, we advocate the creation of an encompassing modeling scheme that will combine ChatGPT with more traditional techniques for manual modeling of systems (Biolchini et al., 2005; Pettersson and Andersson, 2016), in a way that will achieve this goal. Our core idea is to use ChatGPT in a controlled way; i.e., to repeatedly invoke it for various tasks, but to 3. Source: On Augmenting Scenario-Based Modeling with Generative AI (#3JCRAD), Assaf Marron, David Harel, Guy Katz, Smadar Szekely, p. 0 Context: #9DMNFE On Augmenting Scenario-Based Modeling with Generative AI Score: 0.016 Related excerpt #5QRGC9: Abstract: The manual modeling of complex systems is a daunting task; and although a plethora of methods exist that mitigate this issue, the problem remains very difficult. Recent advances in generative AI have allowed the creation of general-purpose chatbots, capable of assisting software engineers in various modeling tasks. However, these chatbots are often inaccurate, and an unstructured use thereof could result in erroneous system models. In this paper, we outline a method for the safer and more structured use of chatbots as part of the modeling process. To streamline this integration, we propose leveraging scenario-based modeling techniques, which are known to facilitate the automated analysis of models. We argue that through iterative invocations of the chatbot and the manual and automatic inspection of the resulting models, a more accurate system model can eventually be obtained. We describe favorable preliminary results, which highlight the potential of this approach. ### 37. Tool result: search_text Exact matches 1. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 0 Context: #8BNNNW Adaptive Behavioral Programming #26K3LE I. INTRODUCTION Matching excerpt #GGLEEY: In this paper we propose to give the user the possibility to not only set these multi-modal rules and boundaries, but also to specify a desired behavior in an easy and intuitive way, by setting the goals the program should achieve, and the scenarios it should avoid. The program is then given the freedom to learn and adapt according to its experience from the environment. Such adaptivity is highly desirable, as the programmer cannot always anticipate how the reactive system's environment will react. In addition, it allows the 2. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 1 Context: #8BNNNW Adaptive Behavioral Programming #RTGR3V II. INTEGRATING REINFORCEMENTS INTO BEHAVIORAL PROGRAMS #XNTHBG A. Implementing scenario-based programming Matching excerpt #T8AV9R: In this paper, we suggest ways to modify these choice and execution mechanisms, which, coupled with appropriate extensions to the LSC language and BPJ, render both languages suitable for dealing with adaptive behavior. 3. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 0 Context: #8BNNNW Adaptive Behavioral Programming Matching excerpt #ZMBNDB: Abstract —We introduce a way to program adaptive reactive systems, using behavioral, scenario-based programming. Extending the semantics of live sequence charts with reinforcements allows the programmer not only to specify what the system should do or must not do, but also what it should try to do, in an intuitive and incremental way. By integrating scenario-based programs with reinforcement learning methods, the program can adapt to the environment, and try to achieve the desired goals. Visualization methods and modular learning decompositions, based on the unique structure of the program, are suggested, and result in an efficient development process and a fast learning rate. Approximate matches 1. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 1 Context: #8BNNNW Adaptive Behavioral Programming #RTGR3V II. INTEGRATING REINFORCEMENTS INTO BEHAVIORAL PROGRAMS #XNTHBG A. Implementing scenario-based programming Score: 0.03 Related excerpt #T8AV9R: In this paper, we suggest ways to modify these choice and execution mechanisms, which, coupled with appropriate extensions to the LSC language and BPJ, render both languages suitable for dealing with adaptive behavior. 2. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 0 Context: #8BNNNW Adaptive Behavioral Programming Score: 0.029 Related excerpt #ZMBNDB: Abstract —We introduce a way to program adaptive reactive systems, using behavioral, scenario-based programming. Extending the semantics of live sequence charts with reinforcements allows the programmer not only to specify what the system should do or must not do, but also what it should try to do, in an intuitive and incremental way. By integrating scenario-based programs with reinforcement learning methods, the program can adapt to the environment, and try to achieve the desired goals. Visualization methods and modular learning decompositions, based on the unique structure of the program, are suggested, and result in an efficient development process and a fast learning rate. 3. Source: Adaptive Behavioral Programming (#P2W4J5), David Harel, Nir Eitan, p. 0 Context: #8BNNNW Adaptive Behavioral Programming #26K3LE I. INTRODUCTION Score: 0.016 Related excerpt #GGLEEY: In this paper we propose to give the user the possibility to not only set these multi-modal rules and boundaries, but also to specify a desired behavior in an easy and intuitive way, by setting the goals the program should achieve, and the scenarios it should avoid. The program is then given the freedom to learn and adapt according to its experience from the environment. Such adaptivity is highly desirable, as the programmer cannot always anticipate how the reactive system's environment will react. In addition, it allows the ### 38. Tool result: search_text Exact matches 1. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 0 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems Matching excerpt #GYZTYN: Abstract: Models of complex systems, both human-made and natural, assist in making critical decisions with regard to function, safety, economy, the environment and more. In this position paper, we explore the difficulty in modeling several innate properties of such systems, including: (i) the frequent emergence of new entities (like group effects and temporal patterns) and the system's reaction to such emergence; (ii) the essence of the system's reactive behavior as a rich composition of stand-alone rules; and (iii) the vast number of internal and external interactions that the system engages in. For each of these challenges we propose some implications to modeling—methodological approaches that can help address it and potential support in modeling languages and tools. We introduce the concept of unmodeling —formally defining model entities and behaviors that are excluded from model execution—and discuss how unmodeling enhances model quality, supports incremental enhancement, and facilitates evaluation. This report emanates from our research and development in modeling languages and methods and our present research in biological evolution. We believe that analysis and implementation of these principles have general applicability in model development and assessment. 2. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 0 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems #HJ6WJT 1 INTRODUCTION Matching excerpt #RVGSAD: Solving modeling difficulties requires recognition and analysis of specific issues. In this paper, we document three properties that are common to many complex reactive systems and argue that even though these properties are hard to model, they must be captured in models that are used in critical decisions. For each of these properties of the modeled system we propose some techniques that modelers can apply to deal with the challenge, and we outline possible features in modeling languages (Including UML, SysML, Statecharts, Live Sequence Charts, MATLAB/Simulink, NeLogo, etc.) and associated modeling platforms that can help modelers in these tasks. 3. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 2 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems #82URE7 2 MOTIVATION #YAH2PF 2.1 Modeling Biological Evolution Matching excerpt #ZRNGZD: Modeling natural autoencoding, with its emphasis on the emergence of patterns subject to numerous laws of nature and the unbounded web of natural interactions, internal and external to each organism and species, presents intriguing technical challenges. In this paper we outline domain-independent methodologies for tackling three of these difficulties. Approximate matches 1. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 0 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems Score: 0.029 Related excerpt #GYZTYN: Abstract: Models of complex systems, both human-made and natural, assist in making critical decisions with regard to function, safety, economy, the environment and more. In this position paper, we explore the difficulty in modeling several innate properties of such systems, including: (i) the frequent emergence of new entities (like group effects and temporal patterns) and the system's reaction to such emergence; (ii) the essence of the system's reactive behavior as a rich composition of stand-alone rules; and (iii) the vast number of internal and external interactions that the system engages in. For each of these challenges we propose some implications to modeling—methodological approaches that can help address it and potential support in modeling languages and tools. We introduce the concept of unmodeling —formally defining model entities and behaviors that are excluded from model execution—and discuss how unmodeling enhances model quality, supports incremental enhancement, and facilitates evaluation. This report emanates from our research and development in modeling languages and methods and our present research in biological evolution. We believe that analysis and implementation of these principles have general applicability in model development and assessment. 2. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 1 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems #HJ6WJT 1 INTRODUCTION Score: 0.016 Related excerpt #K2BU9K: by our engagement with the use of modeling in science education. Yet, we believe that the ideas presented here transcend our specific contexts and can be applied in systems ranging from the global economy through transportation and autonomous vehicles to biological contexts like the immune or nervous systems of organisms; indeed, the examples throughout the paper come from diverse domains. Furthermore, while some of the points we raise may be familiar, we believe that these challenges deserve additional attention and a more central role in methodologies for system modeling and in system engineering at large. 3. Source: Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems (#XQ5NKX), Assaf Marron, David Harel, Guy Frankel, Irun Cohen, Smadar Szekely, p. 2 Context: #PGA2GE Challenges in Modeling and Unmodeling Emergence, Rule Composition, and Networked Interactions in Complex Reactive Systems #82URE7 2 MOTIVATION #YAH2PF 2.1 Modeling Biological Evolution Score: 0.016 Related excerpt #ZRNGZD: Modeling natural autoencoding, with its emphasis on the emergence of patterns subject to numerous laws of nature and the unbounded web of natural interactions, internal and external to each organism and species, presents intriguing technical challenges. In this paper we outline domain-independent methodologies for tackling three of these difficulties. ### 39. Assistant I have enough to work with. Generating eight covers now: #### Tool call: `generate_image` ```json { "prompt": "Abstract technical cover art: a constellation of glowing parallel threads weaving between distant nodes of a distributed network, each thread a ribbon of amber light converging at bright synchronization junctions, set against deep indigo. Subtle Erlang-like hexagonal motifs and a faint quadrotor silhouette in the background. Flat modernist poster style, high contrast, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Cover art for a paper on visually tracing reactive systems: a stylized Pac-Man-like maze rendered as translucent layers, with a luminous timeline of colored event bars flowing horizontally through the maze like a musical score, magnifying-glass lens hovering over one segment revealing fine sequence-chart details. Cool blue-grey palette with cyan and orange accents, clean diagrammatic poster style, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Minimal geometric cover: several horizontal racing lanes of light moving at different speeds — some racing ahead in bright teal, one lagging in dim violet — with dotted ghost-projections showing where the fast lanes predicted the outcome and ran ahead of a synchronization barrier drawn as a thin broken vertical line. Dark charcoal background, precise vector aesthetic, sense of eager forward motion, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Cover art blending formal modeling and AI: a large speech-bubble made of flowing neural filaments handing a glowing blueprint of interlocking scenario blocks to a human hand holding calipers; around them a circular loop of arrows suggesting iterative generation, inspection, and correction. Warm paper-white background, ink-blue and emerald palette, editorial illustration style, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Cover concept for replicate-and-project distribution: one intricate crystalline model at center is mirrored into four identical translucent copies drifting toward the corners, each copy with a different facet illuminated in a distinct color (red, teal, gold, violet) while the rest fades to glass. Thin light-lines connect the lit facets, implying loose coordination. Deep navy void, elegant sci-fi minimalism, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Editorial cover: a chatbot rendered as a softly glowing orb of language fragments dictating into an assembly of modular scenario tiles that snap together like dominoes on a drafting table; a magnifier and checkmark stamps hover over recently placed tiles, some tiles being pushed back for rework. Muted graphite background, coral and mint accents, isometric illustration, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Cover for adaptive behavioral programming with reinforcement learning: a small stylized robot navigating a branching path of glowing stepping stones, some stones warm gold (rewards) and some ember red (penalties), with faint sequence-chart panels floating above like guiding constellations; the path behind the robot brightens as it learns. Twilight gradient background, playful yet technical vector style, no text." } ``` #### Tool call: `generate_image` ```json { "prompt": "Conceptual cover on emergence and unmodeling: a dense murmuration of tiny geometric birds forming a larger emergent figure, part of the flock enclosed in a precise wireframe box while another region is deliberately erased into blank negative space outlined by a dashed boundary. Interwoven fine rule-lines connect individual birds. Soft dawn palette of rose, slate and cream, contemplative scientific-poster aesthetic, no text." } ``` ### 40. Tool result: generate_image GENERATED IMAGE #T4JPQM URL: /images/T4JPQM Model: gpt-image-2 Prompt: Abstract technical cover art: a constellation of glowing parallel threads weaving between distant nodes of a distributed network, each thread a ribbon of amber light converging at bright synchronization junctions, set against deep indigo. Subtle Erlang-like hexagonal motifs and a faint quadrotor silhouette in the background. Flat modernist poster style, high contrast, no text. ### 41. Tool result: generate_image GENERATED IMAGE #CEPYHV URL: /images/CEPYHV Model: gpt-image-2 Prompt: Cover art for a paper on visually tracing reactive systems: a stylized Pac-Man-like maze rendered as translucent layers, with a luminous timeline of colored event bars flowing horizontally through the maze like a musical score, magnifying-glass lens hovering over one segment revealing fine sequence-chart details. Cool blue-grey palette with cyan and orange accents, clean diagrammatic poster style, no text. ### 42. Tool result: generate_image GENERATED IMAGE #DUAWWV URL: /images/DUAWWV Model: gpt-image-2 Prompt: Minimal geometric cover: several horizontal racing lanes of light moving at different speeds — some racing ahead in bright teal, one lagging in dim violet — with dotted ghost-projections showing where the fast lanes predicted the outcome and ran ahead of a synchronization barrier drawn as a thin broken vertical line. Dark charcoal background, precise vector aesthetic, sense of eager forward motion, no text. ### 43. Tool result: generate_image GENERATED IMAGE #PLFTDR URL: /images/PLFTDR Model: gpt-image-2 Prompt: Cover art blending formal modeling and AI: a large speech-bubble made of flowing neural filaments handing a glowing blueprint of interlocking scenario blocks to a human hand holding calipers; around them a circular loop of arrows suggesting iterative generation, inspection, and correction. Warm paper-white background, ink-blue and emerald palette, editorial illustration style, no text. ### 44. Tool result: generate_image GENERATED IMAGE #W7SZVY URL: /images/W7SZVY Model: gpt-image-2 Prompt: Cover concept for replicate-and-project distribution: one intricate crystalline model at center is mirrored into four identical translucent copies drifting toward the corners, each copy with a different facet illuminated in a distinct color (red, teal, gold, violet) while the rest fades to glass. Thin light-lines connect the lit facets, implying loose coordination. Deep navy void, elegant sci-fi minimalism, no text. ### 45. Tool result: generate_image GENERATED IMAGE #USVTHK URL: /images/USVTHK Model: gpt-image-2 Prompt: Editorial cover: a chatbot rendered as a softly glowing orb of language fragments dictating into an assembly of modular scenario tiles that snap together like dominoes on a drafting table; a magnifier and checkmark stamps hover over recently placed tiles, some tiles being pushed back for rework. Muted graphite background, coral and mint accents, isometric illustration, no text. ### 46. Tool result: generate_image GENERATED IMAGE #HFKEH3 URL: /images/HFKEH3 Model: gpt-image-2 Prompt: Cover for adaptive behavioral programming with reinforcement learning: a small stylized robot navigating a branching path of glowing stepping stones, some stones warm gold (rewards) and some ember red (penalties), with faint sequence-chart panels floating above like guiding constellations; the path behind the robot brightens as it learns. Twilight gradient background, playful yet technical vector style, no text. ### 47. Tool result: generate_image GENERATED IMAGE #KBQPE3 URL: /images/KBQPE3 Model: gpt-image-2 Prompt: Conceptual cover on emergence and unmodeling: a dense murmuration of tiny geometric birds forming a larger emergent figure, part of the flock enclosed in a precise wireframe box while another region is deliberately erased into blank negative space outlined by a dashed boundary. Interwoven fine rule-lines connect individual birds. Soft dawn palette of rose, slate and cream, contemplative scientific-poster aesthetic, no text. ### 48. Assistant tool calls #### Tool call: `update_document_metadata` ```json { "cover_image_id": "T4JPQM", "document_id": "M5788P", "micro_abstract": "Extends behavioral programming to distributed architectures: b-threads as Erlang processes, eager execution to relax synchronization, and modular distributed execution, demonstrated on simulations and a quadrotor." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "CEPYHV", "document_id": "QV3BWZ", "micro_abstract": "Introduces model-based trace visualization and exploration for reactive systems, using scenario-based (LSC) abstractions and the Tracer prototype, demonstrated on a PacMan game." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "DUAWWV", "document_id": "TDS4H2", "micro_abstract": "Proposes eager execution for behavioral programs: fast b-threads run ahead when synchronization outcomes are predictable, improving performance, modularity, and distributability, shown in a C++ BP framework." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "USVTHK", "document_id": "CSJARA", "micro_abstract": "Extended methodology for combining LLM chatbots with scenario-based modeling: iterative generation of stand-alone scenarios checked by analysis and human review, framed as a step toward Wise Computing." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "W7SZVY", "document_id": "D4VB7S", "micro_abstract": "Distributes scenario-based models by replicating the full specification on every component and projecting it per component, mimicking centralized behavior while sharply reducing synchronization." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "PLFTDR", "document_id": "3JCRAD", "micro_abstract": "Outlines a structured method for using generative-AI chatbots in modeling: iteratively generate scenario-based model fragments, then analyze and inspect them to converge on an accurate system model." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "HFKEH3", "document_id": "P2W4J5", "micro_abstract": "Adds reinforcements to live sequence charts and BPJ so scenario-based programs can learn from their environment, specifying goals to pursue and scenarios to avoid, with modular learning decompositions." } ``` #### Tool call: `update_document_metadata` ```json { "cover_image_id": "KBQPE3", "document_id": "XQ5NKX", "micro_abstract": "Position paper on modeling emergence, rule composition, and networked interactions in complex reactive systems, introducing \"unmodeling\"—explicitly excluding entities and behaviors from model execution." } ``` ### 49. Tool result: update_document_metadata Updated metadata for #M5788P: cover_image_id, micro_abstract ### 50. Tool result: update_document_metadata Updated metadata for #QV3BWZ: cover_image_id, micro_abstract ### 51. Tool result: update_document_metadata Updated metadata for #TDS4H2: cover_image_id, micro_abstract ### 52. Tool result: update_document_metadata Updated metadata for #CSJARA: cover_image_id, micro_abstract ### 53. Tool result: update_document_metadata Updated metadata for #D4VB7S: cover_image_id, micro_abstract ### 54. Tool result: update_document_metadata Updated metadata for #3JCRAD: cover_image_id, micro_abstract ### 55. Tool result: update_document_metadata Updated metadata for #P2W4J5: cover_image_id, micro_abstract ### 56. Tool result: update_document_metadata Updated metadata for #XQ5NKX: cover_image_id, micro_abstract ### 57. Assistant All eight now have grounded micro-abstracts and covers: - #M5788P — BP in distributed architectures (Erlang b-threads, eager execution, quadrotor) · cover #T4JPQM - #QV3BWZ — Model-based trace visualization with the Tracer / PacMan · cover #CEPYHV - #TDS4H2 — Eager execution relaxing BP synchronization · cover #DUAWWV - #CSJARA — LLM + scenario-based modeling methodology (extended, Wise Computing) · cover #USVTHK - #D4VB7S — Replicate-and-project distribution of SB models · cover #W7SZVY - #3JCRAD — Structured generative-AI augmentation of SBM (the shorter MODELSWARD paper) · cover #PLFTDR - #P2W4J5 — Reinforcement-extended LSCs for adaptive BP · cover #HFKEH3 - #XQ5NKX — Emergence, rule composition, and "unmodeling" · cover #KBQPE3 Abstracts were pulled directly from each paper's own abstract/intro (e.g. #9H9YU2, #S3CX43, #5QRGC9, #ZMBNDB, #GYZTYN). Note the eight docs are still in "Unfiled" — say the word and a folder name, e.g. "Scenario-Based & Behavioral Programming", and I'll file them. ### 58. User yeah let's do a folder ### 59. Assistant tool calls #### Tool call: `update_document_metadata` ```json { "document_id": "M5788P", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "QV3BWZ", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "TDS4H2", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "CSJARA", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "D4VB7S", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "3JCRAD", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "P2W4J5", "folder": "Scenario-Based & Behavioral Programming" } ``` #### Tool call: `update_document_metadata` ```json { "document_id": "XQ5NKX", "folder": "Scenario-Based & Behavioral Programming" } ``` ### 60. Tool result: update_document_metadata Updated metadata for #M5788P: folder ### 61. Tool result: update_document_metadata Updated metadata for #QV3BWZ: folder ### 62. Tool result: update_document_metadata Updated metadata for #TDS4H2: folder ### 63. Tool result: update_document_metadata Updated metadata for #CSJARA: folder ### 64. Tool result: update_document_metadata Updated metadata for #D4VB7S: folder ### 65. Tool result: update_document_metadata Updated metadata for #3JCRAD: folder ### 66. Tool result: update_document_metadata Updated metadata for #P2W4J5: folder ### 67. Tool result: update_document_metadata Updated metadata for #XQ5NKX: folder ### 68. Assistant All eight papers (#M5788P, #QV3BWZ, #TDS4H2, #CSJARA, #D4VB7S, #3JCRAD, #P2W4J5, #XQ5NKX) are now filed under **Scenario-Based & Behavioral Programming**.