{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4EKMKNVRKK3H2SZBHOREISFT6R","short_pith_number":"pith:4EKMKNVR","schema_version":"1.0","canonical_sha256":"e114c536b152b67d4b213ba24448b3f45e68095baac7e456b1389102aa0612c5","source":{"kind":"arxiv","id":"2309.09181","version":1},"attestation_state":"computed","paper":{"title":"From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Md Sadman Sakib, Yu Sun","submitted_at":"2023-09-17T07:09:16Z","abstract_excerpt":"Task planning for robotic cooking involves generating a sequence of actions for a robot to prepare a meal successfully. This paper introduces a novel task tree generation pipeline producing correct planning and efficient execution for cooking tasks. Our method first uses a large language model (LLM) to retrieve recipe instructions and then utilizes a fine-tuned GPT-3 to convert them into a task tree, capturing sequential and parallel dependencies among subtasks. The pipeline then mitigates the uncertainty and unreliable features of LLM outputs using task tree retrieval. We combine multiple LLM"},"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":"2309.09181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-17T07:09:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dce8bcee64f53139a8d49b9f013f8e6f592495daabb39980e2831b73962765a0","abstract_canon_sha256":"b0db221b06c53ea22cf9ed668d7a77638cd8bae74d93eba37bf4e3c8b2b05b6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:35.639048Z","signature_b64":"0hB2vNXIv8eL18WMCkD8P0tk7bCF+cuQh9Apiq+uDe9LPEy8XbPM+c/j6yjDR/gtJYtWI+jFcngLowAIwk1DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e114c536b152b67d4b213ba24448b3f45e68095baac7e456b1389102aa0612c5","last_reissued_at":"2026-07-05T06:51:35.638673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:35.638673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Md Sadman Sakib, Yu Sun","submitted_at":"2023-09-17T07:09:16Z","abstract_excerpt":"Task planning for robotic cooking involves generating a sequence of actions for a robot to prepare a meal successfully. This paper introduces a novel task tree generation pipeline producing correct planning and efficient execution for cooking tasks. Our method first uses a large language model (LLM) to retrieve recipe instructions and then utilizes a fine-tuned GPT-3 to convert them into a task tree, capturing sequential and parallel dependencies among subtasks. The pipeline then mitigates the uncertainty and unreliable features of LLM outputs using task tree retrieval. We combine multiple LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09181","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/2309.09181/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":"2309.09181","created_at":"2026-07-05T06:51:35.638724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09181v1","created_at":"2026-07-05T06:51:35.638724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09181","created_at":"2026-07-05T06:51:35.638724+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EKMKNVRKK3H","created_at":"2026-07-05T06:51:35.638724+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EKMKNVRKK3H2SZB","created_at":"2026-07-05T06:51:35.638724+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EKMKNVR","created_at":"2026-07-05T06:51:35.638724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12312","citing_title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","ref_index":98,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R","json":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R.json","graph_json":"https://pith.science/api/pith-number/4EKMKNVRKK3H2SZBHOREISFT6R/graph.json","events_json":"https://pith.science/api/pith-number/4EKMKNVRKK3H2SZBHOREISFT6R/events.json","paper":"https://pith.science/paper/4EKMKNVR"},"agent_actions":{"view_html":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R","download_json":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R.json","view_paper":"https://pith.science/paper/4EKMKNVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09181&json=true","fetch_graph":"https://pith.science/api/pith-number/4EKMKNVRKK3H2SZBHOREISFT6R/graph.json","fetch_events":"https://pith.science/api/pith-number/4EKMKNVRKK3H2SZBHOREISFT6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R/action/storage_attestation","attest_author":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R/action/author_attestation","sign_citation":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R/action/citation_signature","submit_replication":"https://pith.science/pith/4EKMKNVRKK3H2SZBHOREISFT6R/action/replication_record"}},"created_at":"2026-07-05T06:51:35.638724+00:00","updated_at":"2026-07-05T06:51:35.638724+00:00"}