{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BO6JF7VLCSJY2AI265Z4RW5FUR","short_pith_number":"pith:BO6JF7VL","schema_version":"1.0","canonical_sha256":"0bbc92feab14938d011af773c8dba5a44a9dd05f7e97f75b9b86aa5153da3e44","source":{"kind":"arxiv","id":"2306.05171","version":1},"attestation_state":"computed","paper":{"title":"Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Zi-rui, Fang Yi-shu, Lu Xing-tong, Pan Wei-qin, Sheng Bi, Shi Hai-peng, Yue Zhen","submitted_at":"2023-06-08T13:10:00Z","abstract_excerpt":"Traditional robot task planning methods face challenges when dealing with highly unstructured environments and complex tasks. We propose a task planning method that combines human expertise with an LLM and have designed an LLM prompt template, Think_Net_Prompt, with stronger expressive power to represent structured professional knowledge. We further propose a method to progressively decompose tasks and generate a task tree to reduce the planning volume for each task, and we have designed a strategy to decouple robot task planning. By dividing different planning entities and separating the task"},"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":"2306.05171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-08T13:10:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82c2f96a03081080cafddc2a0344e082429ca12d125c4ee5625d64a5c3380ce7","abstract_canon_sha256":"1d7d673d6522d8871f0d95b864407040af633a4dfc31a3878f9d75a2baf14c1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:53.250584Z","signature_b64":"9wb0wLj7k2yLaad/iCwfqwRIH4l5jip23DSw0I5qmVw2i1AnAvZy9nha289yGDttvINW2ggeqjp0+ETSrgVIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bbc92feab14938d011af773c8dba5a44a9dd05f7e97f75b9b86aa5153da3e44","last_reissued_at":"2026-07-05T06:18:53.250146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:53.250146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Zi-rui, Fang Yi-shu, Lu Xing-tong, Pan Wei-qin, Sheng Bi, Shi Hai-peng, Yue Zhen","submitted_at":"2023-06-08T13:10:00Z","abstract_excerpt":"Traditional robot task planning methods face challenges when dealing with highly unstructured environments and complex tasks. We propose a task planning method that combines human expertise with an LLM and have designed an LLM prompt template, Think_Net_Prompt, with stronger expressive power to represent structured professional knowledge. We further propose a method to progressively decompose tasks and generate a task tree to reduce the planning volume for each task, and we have designed a strategy to decouple robot task planning. By dividing different planning entities and separating the task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05171","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/2306.05171/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":"2306.05171","created_at":"2026-07-05T06:18:53.250203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05171v1","created_at":"2026-07-05T06:18:53.250203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05171","created_at":"2026-07-05T06:18:53.250203+00:00"},{"alias_kind":"pith_short_12","alias_value":"BO6JF7VLCSJY","created_at":"2026-07-05T06:18:53.250203+00:00"},{"alias_kind":"pith_short_16","alias_value":"BO6JF7VLCSJY2AI2","created_at":"2026-07-05T06:18:53.250203+00:00"},{"alias_kind":"pith_short_8","alias_value":"BO6JF7VL","created_at":"2026-07-05T06:18:53.250203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29627","citing_title":"A Two-Stage Reflection and Reprompting Framework for LLM-Based Solution of Petri Net Reachability Problems in Industrial Applications","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR","json":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR.json","graph_json":"https://pith.science/api/pith-number/BO6JF7VLCSJY2AI265Z4RW5FUR/graph.json","events_json":"https://pith.science/api/pith-number/BO6JF7VLCSJY2AI265Z4RW5FUR/events.json","paper":"https://pith.science/paper/BO6JF7VL"},"agent_actions":{"view_html":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR","download_json":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR.json","view_paper":"https://pith.science/paper/BO6JF7VL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05171&json=true","fetch_graph":"https://pith.science/api/pith-number/BO6JF7VLCSJY2AI265Z4RW5FUR/graph.json","fetch_events":"https://pith.science/api/pith-number/BO6JF7VLCSJY2AI265Z4RW5FUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR/action/storage_attestation","attest_author":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR/action/author_attestation","sign_citation":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR/action/citation_signature","submit_replication":"https://pith.science/pith/BO6JF7VLCSJY2AI265Z4RW5FUR/action/replication_record"}},"created_at":"2026-07-05T06:18:53.250203+00:00","updated_at":"2026-07-05T06:18:53.250203+00:00"}