{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IDFY5QEPPTHZBRNIIAOYUAPU3F","short_pith_number":"pith:IDFY5QEP","schema_version":"1.0","canonical_sha256":"40cb8ec08f7ccf90c5a8401d8a01f4d9736be1e00d6c72b61483e429230ec83c","source":{"kind":"arxiv","id":"2406.17659","version":1},"attestation_state":"computed","paper":{"title":"DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Andy Kaminski, Chad Esselink, Hao Yang, Saeid Amiri, Shiqi Zhang, Xiaohan Zhang, Yan Ding, Yohei Hayamizu, Zainab Altaweel","submitted_at":"2024-06-25T15:49:47Z","abstract_excerpt":"Vision-language models (VLMs) have been applied to robot task planning problems, where the robot receives a task in natural language and generates plans based on visual inputs. While current VLMs have demonstrated strong vision-language understanding capabilities, their performance is still far from being satisfactory in planning tasks. At the same time, although classical task planners, such as PDDL-based, are strong in planning for long-horizon tasks, they do not work well in open worlds where unforeseen situations are common. In this paper, we propose a novel task planning and execution fra"},"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":"2406.17659","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-25T15:49:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3a1a66b0ed4c872809c2d1b4e4ce5f6f01ea8c8ee1c33cc895fb4efac94ec515","abstract_canon_sha256":"1266e5b8ed38fad3840e9b3df9c971fa495c42dc2cdf2e72628f39eac58665c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:38.329625Z","signature_b64":"AXV1p9qFx3/JGpSHafTwsL2CTWmFFJ9udFaQfRtQB+MZVliLYc4BZ3l0NVkKN8+9SNlQ/sJSALmQQ+MYvtmkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40cb8ec08f7ccf90c5a8401d8a01f4d9736be1e00d6c72b61483e429230ec83c","last_reissued_at":"2026-07-05T08:36:38.328974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:38.328974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Andy Kaminski, Chad Esselink, Hao Yang, Saeid Amiri, Shiqi Zhang, Xiaohan Zhang, Yan Ding, Yohei Hayamizu, Zainab Altaweel","submitted_at":"2024-06-25T15:49:47Z","abstract_excerpt":"Vision-language models (VLMs) have been applied to robot task planning problems, where the robot receives a task in natural language and generates plans based on visual inputs. While current VLMs have demonstrated strong vision-language understanding capabilities, their performance is still far from being satisfactory in planning tasks. At the same time, although classical task planners, such as PDDL-based, are strong in planning for long-horizon tasks, they do not work well in open worlds where unforeseen situations are common. In this paper, we propose a novel task planning and execution fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17659","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/2406.17659/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":"2406.17659","created_at":"2026-07-05T08:36:38.329046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17659v1","created_at":"2026-07-05T08:36:38.329046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17659","created_at":"2026-07-05T08:36:38.329046+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDFY5QEPPTHZ","created_at":"2026-07-05T08:36:38.329046+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDFY5QEPPTHZBRNI","created_at":"2026-07-05T08:36:38.329046+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDFY5QEP","created_at":"2026-07-05T08:36:38.329046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.10446","citing_title":"VeriGraph: Scene Graphs for Execution Verifiable Robot Planning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17830","citing_title":"SYMBOLIZER: Symbolic Model-free Task Planning with VLMs","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F","json":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F.json","graph_json":"https://pith.science/api/pith-number/IDFY5QEPPTHZBRNIIAOYUAPU3F/graph.json","events_json":"https://pith.science/api/pith-number/IDFY5QEPPTHZBRNIIAOYUAPU3F/events.json","paper":"https://pith.science/paper/IDFY5QEP"},"agent_actions":{"view_html":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F","download_json":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F.json","view_paper":"https://pith.science/paper/IDFY5QEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17659&json=true","fetch_graph":"https://pith.science/api/pith-number/IDFY5QEPPTHZBRNIIAOYUAPU3F/graph.json","fetch_events":"https://pith.science/api/pith-number/IDFY5QEPPTHZBRNIIAOYUAPU3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F/action/storage_attestation","attest_author":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F/action/author_attestation","sign_citation":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F/action/citation_signature","submit_replication":"https://pith.science/pith/IDFY5QEPPTHZBRNIIAOYUAPU3F/action/replication_record"}},"created_at":"2026-07-05T08:36:38.329046+00:00","updated_at":"2026-07-05T08:36:38.329046+00:00"}