{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D33LOATHL7KQL3LRWLGMA75VXJ","short_pith_number":"pith:D33LOATH","schema_version":"1.0","canonical_sha256":"1ef6b702675fd505ed71b2ccc07fb5ba6ba6828b9f4a0af2e827e689bd0234ca","source":{"kind":"arxiv","id":"2401.08089","version":1},"attestation_state":"computed","paper":{"title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CL","authors_text":"Bin Li, Fu Li, Xiaodong Yi, Xueying Wang, Yanzhen Wang, Yunlong Wu","submitted_at":"2024-01-16T03:28:29Z","abstract_excerpt":"This paper presents an innovative exploration of the application potential of large language models (LLM) in addressing the challenging task of automatically generating behavior trees (BTs) for complex tasks. The conventional manual BT generation method is inefficient and heavily reliant on domain expertise. On the other hand, existing automatic BT generation technologies encounter bottlenecks related to task complexity, model adaptability, and reliability. In order to overcome these challenges, we propose a novel methodology that leverages the robust representation and reasoning abilities of "},"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":"2401.08089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T03:28:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"834c770573f16635361c730d12ce63c889f8a3096739cc59d34839a1477ed211","abstract_canon_sha256":"b4b8b9d3b6c63ee0d8c7c73b092fb12eb4a47fb98b758eb5e80f4171f0e6366f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:07.184108Z","signature_b64":"MazMHkLhovOe0fgctjWjhcYIAhYzNeWDH1tupxcwmM8Nr50yV+hKffNY6zYT16Gqv8u1P4OPRW1NWhB9U6olBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ef6b702675fd505ed71b2ccc07fb5ba6ba6828b9f4a0af2e827e689bd0234ca","last_reissued_at":"2026-07-05T07:34:07.183631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:07.183631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CL","authors_text":"Bin Li, Fu Li, Xiaodong Yi, Xueying Wang, Yanzhen Wang, Yunlong Wu","submitted_at":"2024-01-16T03:28:29Z","abstract_excerpt":"This paper presents an innovative exploration of the application potential of large language models (LLM) in addressing the challenging task of automatically generating behavior trees (BTs) for complex tasks. The conventional manual BT generation method is inefficient and heavily reliant on domain expertise. On the other hand, existing automatic BT generation technologies encounter bottlenecks related to task complexity, model adaptability, and reliability. In order to overcome these challenges, we propose a novel methodology that leverages the robust representation and reasoning abilities of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08089","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/2401.08089/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":"2401.08089","created_at":"2026-07-05T07:34:07.183689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08089v1","created_at":"2026-07-05T07:34:07.183689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08089","created_at":"2026-07-05T07:34:07.183689+00:00"},{"alias_kind":"pith_short_12","alias_value":"D33LOATHL7KQ","created_at":"2026-07-05T07:34:07.183689+00:00"},{"alias_kind":"pith_short_16","alias_value":"D33LOATHL7KQL3LR","created_at":"2026-07-05T07:34:07.183689+00:00"},{"alias_kind":"pith_short_8","alias_value":"D33LOATH","created_at":"2026-07-05T07:34:07.183689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ","json":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ.json","graph_json":"https://pith.science/api/pith-number/D33LOATHL7KQL3LRWLGMA75VXJ/graph.json","events_json":"https://pith.science/api/pith-number/D33LOATHL7KQL3LRWLGMA75VXJ/events.json","paper":"https://pith.science/paper/D33LOATH"},"agent_actions":{"view_html":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ","download_json":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ.json","view_paper":"https://pith.science/paper/D33LOATH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08089&json=true","fetch_graph":"https://pith.science/api/pith-number/D33LOATHL7KQL3LRWLGMA75VXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/D33LOATHL7KQL3LRWLGMA75VXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ/action/storage_attestation","attest_author":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ/action/author_attestation","sign_citation":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ/action/citation_signature","submit_replication":"https://pith.science/pith/D33LOATHL7KQL3LRWLGMA75VXJ/action/replication_record"}},"created_at":"2026-07-05T07:34:07.183689+00:00","updated_at":"2026-07-05T07:34:07.183689+00:00"}