{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4DXSS6CZDKYAKZXVHQQOJQ3AQL","short_pith_number":"pith:4DXSS6CZ","schema_version":"1.0","canonical_sha256":"e0ef2978591ab00566f53c20e4c36082e8f7ec530df5541c53002f9351d824fc","source":{"kind":"arxiv","id":"2307.01848","version":1},"attestation_state":"computed","paper":{"title":"Embodied Task Planning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Haibin Yan, Jiwen Lu, Xiuwei Xu, Zhenyu Wu, Ziwei Wang","submitted_at":"2023-07-04T17:58:25Z","abstract_excerpt":"Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) can embed rich semantic knowledge for agents in plan generation of complex tasks, while they lack the information about the realistic world and usually yield infeasible action sequences. In this paper, we propose a TAsk Planing Agent (TaPA) in embodied tasks for grounded planning with physical scene constraint, where the agent generates executable plans according to the existed objects in the scene by aligning LLMs wi"},"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":"2307.01848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-04T17:58:25Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"554846c9d1449656270f2915b9cdb8f382f5720a474199dd08ca146504e34d5a","abstract_canon_sha256":"8933e7240e07bcc18c101ff65955a8cbe8f235e42c50c2486b6ea19b95749593"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:20.287468Z","signature_b64":"CyTtydTA605Y1dE33tjG0Lrt6OufvDbJIKCfrgj31UvTsrDBlt35qaeZhMuxXIl7SxfHsU0xuyPELIkNCruwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ef2978591ab00566f53c20e4c36082e8f7ec530df5541c53002f9351d824fc","last_reissued_at":"2026-07-05T06:28:20.287039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:20.287039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Task Planning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Haibin Yan, Jiwen Lu, Xiuwei Xu, Zhenyu Wu, Ziwei Wang","submitted_at":"2023-07-04T17:58:25Z","abstract_excerpt":"Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) can embed rich semantic knowledge for agents in plan generation of complex tasks, while they lack the information about the realistic world and usually yield infeasible action sequences. In this paper, we propose a TAsk Planing Agent (TaPA) in embodied tasks for grounded planning with physical scene constraint, where the agent generates executable plans according to the existed objects in the scene by aligning LLMs wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01848","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/2307.01848/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":"2307.01848","created_at":"2026-07-05T06:28:20.287095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01848v1","created_at":"2026-07-05T06:28:20.287095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01848","created_at":"2026-07-05T06:28:20.287095+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DXSS6CZDKYA","created_at":"2026-07-05T06:28:20.287095+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DXSS6CZDKYAKZXV","created_at":"2026-07-05T06:28:20.287095+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DXSS6CZ","created_at":"2026-07-05T06:28:20.287095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08024","citing_title":"APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25851","citing_title":"RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2409.13107","citing_title":"Towards Robust Surgical Automation via Digital Twin Representations from Foundation Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21841","citing_title":"Embodied Task Planning via Graph-Informed Action Generation with Large Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":200,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01989","citing_title":"Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL","json":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL.json","graph_json":"https://pith.science/api/pith-number/4DXSS6CZDKYAKZXVHQQOJQ3AQL/graph.json","events_json":"https://pith.science/api/pith-number/4DXSS6CZDKYAKZXVHQQOJQ3AQL/events.json","paper":"https://pith.science/paper/4DXSS6CZ"},"agent_actions":{"view_html":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL","download_json":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL.json","view_paper":"https://pith.science/paper/4DXSS6CZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01848&json=true","fetch_graph":"https://pith.science/api/pith-number/4DXSS6CZDKYAKZXVHQQOJQ3AQL/graph.json","fetch_events":"https://pith.science/api/pith-number/4DXSS6CZDKYAKZXVHQQOJQ3AQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL/action/storage_attestation","attest_author":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL/action/author_attestation","sign_citation":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL/action/citation_signature","submit_replication":"https://pith.science/pith/4DXSS6CZDKYAKZXVHQQOJQ3AQL/action/replication_record"}},"created_at":"2026-07-05T06:28:20.287095+00:00","updated_at":"2026-07-05T06:28:20.287095+00:00"}