{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4RSDEJCIKPBDO5EMXSVFSZYVF","short_pith_number":"pith:B4RSDEJC","schema_version":"1.0","canonical_sha256":"0f23219122429e11bba465e552cb38a962f0825bde6d9b01658ed4e4d5f567e2","source":{"kind":"arxiv","id":"2404.07439","version":1},"attestation_state":"computed","paper":{"title":"Behavior Trees Enable Structured Programming of Language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Richard Kelley","submitted_at":"2024-04-11T02:44:13Z","abstract_excerpt":"Language models trained on internet-scale data sets have shown an impressive ability to solve problems in Natural Language Processing and Computer Vision. However, experience is showing that these models are frequently brittle in unexpected ways, and require significant scaffolding to ensure that they operate correctly in the larger systems that comprise \"language-model agents.\" In this paper, we argue that behavior trees provide a unifying framework for combining language models with classical AI and traditional programming. We introduce Dendron, a Python library for programming language mode"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.07439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-11T02:44:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"06730933bc53cf225955bcc7dcfdd6e901180addf44c1a46e880761e46282e78","abstract_canon_sha256":"211dea519d344067b9c5672a691d9ea63d1f5fa926ffb07bd75e1b0f2951fa42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:52.837796Z","signature_b64":"xRoXcwaBEtlqCm8kPTxKByHvUba/96zN4F+4LD5SV3y8IlLU/0dNqq1MviZi6OdxIOUemnbUXHAlfM3pU1HPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f23219122429e11bba465e552cb38a962f0825bde6d9b01658ed4e4d5f567e2","last_reissued_at":"2026-07-05T08:06:52.837382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:52.837382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior Trees Enable Structured Programming of Language Model Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Richard Kelley","submitted_at":"2024-04-11T02:44:13Z","abstract_excerpt":"Language models trained on internet-scale data sets have shown an impressive ability to solve problems in Natural Language Processing and Computer Vision. However, experience is showing that these models are frequently brittle in unexpected ways, and require significant scaffolding to ensure that they operate correctly in the larger systems that comprise \"language-model agents.\" In this paper, we argue that behavior trees provide a unifying framework for combining language models with classical AI and traditional programming. We introduce Dendron, a Python library for programming language mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07439","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.07439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.07439","created_at":"2026-07-05T08:06:52.837441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07439v1","created_at":"2026-07-05T08:06:52.837441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07439","created_at":"2026-07-05T08:06:52.837441+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4RSDEJCIKPB","created_at":"2026-07-05T08:06:52.837441+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4RSDEJCIKPBDO5E","created_at":"2026-07-05T08:06:52.837441+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4RSDEJC","created_at":"2026-07-05T08:06:52.837441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15242","citing_title":"Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an \"AI Therapist\"","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF","json":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF.json","graph_json":"https://pith.science/api/pith-number/B4RSDEJCIKPBDO5EMXSVFSZYVF/graph.json","events_json":"https://pith.science/api/pith-number/B4RSDEJCIKPBDO5EMXSVFSZYVF/events.json","paper":"https://pith.science/paper/B4RSDEJC"},"agent_actions":{"view_html":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF","download_json":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF.json","view_paper":"https://pith.science/paper/B4RSDEJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07439&json=true","fetch_graph":"https://pith.science/api/pith-number/B4RSDEJCIKPBDO5EMXSVFSZYVF/graph.json","fetch_events":"https://pith.science/api/pith-number/B4RSDEJCIKPBDO5EMXSVFSZYVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF/action/storage_attestation","attest_author":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF/action/author_attestation","sign_citation":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF/action/citation_signature","submit_replication":"https://pith.science/pith/B4RSDEJCIKPBDO5EMXSVFSZYVF/action/replication_record"}},"created_at":"2026-07-05T08:06:52.837441+00:00","updated_at":"2026-07-05T08:06:52.837441+00:00"}