{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VEBY7NGB7T5L6RL534NV3LX7GS","short_pith_number":"pith:VEBY7NGB","schema_version":"1.0","canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","source":{"kind":"arxiv","id":"2311.12015","version":4},"attestation_state":"computed","paper":{"title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Atsushi Kanehira, Jun Takamatsu, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Naoki Wake","submitted_at":"2023-11-20T18:54:39Z","abstract_excerpt":"We introduce a pipeline that enhances a general-purpose Vision Language Model, GPT-4V(ision), to facilitate one-shot visual teaching for robotic manipulation. This system analyzes videos of humans performing tasks and outputs executable robot programs that incorporate insights into affordances. The process begins with GPT-4V analyzing the videos to obtain textual explanations of environmental and action details. A GPT-4-based task planner then encodes these details into a symbolic task plan. Subsequently, vision systems spatially and temporally ground the task plan in the videos. Objects are i"},"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":"2311.12015","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-20T18:54:39Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c09903ed8a50b48c626167ad9250c0dc93fa7599e0eed109b3cecb9eb1086ec1","abstract_canon_sha256":"250bf8b910b0b1595fbd1ac129edcdd97e2321e7eb12b3c9c76cde05e34a95ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:21.471258Z","signature_b64":"ieSEr5BYR5xU+4aoR+whMwQBvNUgmAFbnWzV6uIjeTBUOhFmV03Rk2OFmrPMtbgnqrNUBzu2yBeYwiC5MtJrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","last_reissued_at":"2026-07-05T09:18:21.470800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:21.470800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Atsushi Kanehira, Jun Takamatsu, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Naoki Wake","submitted_at":"2023-11-20T18:54:39Z","abstract_excerpt":"We introduce a pipeline that enhances a general-purpose Vision Language Model, GPT-4V(ision), to facilitate one-shot visual teaching for robotic manipulation. This system analyzes videos of humans performing tasks and outputs executable robot programs that incorporate insights into affordances. The process begins with GPT-4V analyzing the videos to obtain textual explanations of environmental and action details. A GPT-4-based task planner then encodes these details into a symbolic task plan. Subsequently, vision systems spatially and temporally ground the task plan in the videos. Objects are i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12015","kind":"arxiv","version":4},"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/2311.12015/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":"2311.12015","created_at":"2026-07-05T09:18:21.470852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12015v4","created_at":"2026-07-05T09:18:21.470852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12015","created_at":"2026-07-05T09:18:21.470852+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEBY7NGB7T5L","created_at":"2026-07-05T09:18:21.470852+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEBY7NGB7T5L6RL5","created_at":"2026-07-05T09:18:21.470852+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEBY7NGB","created_at":"2026-07-05T09:18:21.470852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS","json":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS.json","graph_json":"https://pith.science/api/pith-number/VEBY7NGB7T5L6RL534NV3LX7GS/graph.json","events_json":"https://pith.science/api/pith-number/VEBY7NGB7T5L6RL534NV3LX7GS/events.json","paper":"https://pith.science/paper/VEBY7NGB"},"agent_actions":{"view_html":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS","download_json":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS.json","view_paper":"https://pith.science/paper/VEBY7NGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12015&json=true","fetch_graph":"https://pith.science/api/pith-number/VEBY7NGB7T5L6RL534NV3LX7GS/graph.json","fetch_events":"https://pith.science/api/pith-number/VEBY7NGB7T5L6RL534NV3LX7GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/action/storage_attestation","attest_author":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/action/author_attestation","sign_citation":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/action/citation_signature","submit_replication":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/action/replication_record"}},"created_at":"2026-07-05T09:18:21.470852+00:00","updated_at":"2026-07-05T09:18:21.470852+00:00"}