{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XDSAW7BIXYJ57LGQFKKTW3A4CB","short_pith_number":"pith:XDSAW7BI","schema_version":"1.0","canonical_sha256":"b8e40b7c28be13dfacd02a953b6c1c1052c8c690d7d318115348010004f6acb8","source":{"kind":"arxiv","id":"2302.12927","version":1},"attestation_state":"computed","paper":{"title":"Robot Behavior-Tree-Based Task Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"C.S. George Lee, Yue Cao","submitted_at":"2023-02-24T22:53:10Z","abstract_excerpt":"Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for investigating automatic behavior-tree-based task generation. Prior behavior-tree-based task generation approaches focus on fixed primitive tasks and lack generalizability to new task domains. To cope with this issue, we propose a novel behavior-tree-based task generation approach that utilizes state-of-the-art large language models. We propose a Phase-Step prompt design"},"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":"2302.12927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-24T22:53:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b721aef519010e7d567add87c4e4dc9d6783cdee754b0dba609686f33dc28413","abstract_canon_sha256":"06df297a2700d612ed94368f514eae7af15b50b67f21e2e8e673352fad30f8d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:40.895909Z","signature_b64":"qw3JY/gDSFvN2/U2ZmTW0ynO9bZ4+rdm0LUh0qcHCPU8b04gjih3TdtxkGRt/LBYfjQV+DvIDMF/Kzi9i4ZSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8e40b7c28be13dfacd02a953b6c1c1052c8c690d7d318115348010004f6acb8","last_reissued_at":"2026-07-05T05:45:40.895451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:40.895451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Behavior-Tree-Based Task Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"C.S. George Lee, Yue Cao","submitted_at":"2023-02-24T22:53:10Z","abstract_excerpt":"Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for investigating automatic behavior-tree-based task generation. Prior behavior-tree-based task generation approaches focus on fixed primitive tasks and lack generalizability to new task domains. To cope with this issue, we propose a novel behavior-tree-based task generation approach that utilizes state-of-the-art large language models. We propose a Phase-Step prompt design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12927","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/2302.12927/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":"2302.12927","created_at":"2026-07-05T05:45:40.895510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12927v1","created_at":"2026-07-05T05:45:40.895510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12927","created_at":"2026-07-05T05:45:40.895510+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDSAW7BIXYJ5","created_at":"2026-07-05T05:45:40.895510+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDSAW7BIXYJ57LGQ","created_at":"2026-07-05T05:45:40.895510+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDSAW7BI","created_at":"2026-07-05T05:45:40.895510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26256","citing_title":"Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12358","citing_title":"From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04129","citing_title":"KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17190","citing_title":"LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB","json":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB.json","graph_json":"https://pith.science/api/pith-number/XDSAW7BIXYJ57LGQFKKTW3A4CB/graph.json","events_json":"https://pith.science/api/pith-number/XDSAW7BIXYJ57LGQFKKTW3A4CB/events.json","paper":"https://pith.science/paper/XDSAW7BI"},"agent_actions":{"view_html":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB","download_json":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB.json","view_paper":"https://pith.science/paper/XDSAW7BI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12927&json=true","fetch_graph":"https://pith.science/api/pith-number/XDSAW7BIXYJ57LGQFKKTW3A4CB/graph.json","fetch_events":"https://pith.science/api/pith-number/XDSAW7BIXYJ57LGQFKKTW3A4CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB/action/storage_attestation","attest_author":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB/action/author_attestation","sign_citation":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB/action/citation_signature","submit_replication":"https://pith.science/pith/XDSAW7BIXYJ57LGQFKKTW3A4CB/action/replication_record"}},"created_at":"2026-07-05T05:45:40.895510+00:00","updated_at":"2026-07-05T05:45:40.895510+00:00"}