{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VEBY7NGB7T5L6RL534NV3LX7GS","short_pith_number":"pith:VEBY7NGB","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"},"canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","source":{"kind":"arxiv","id":"2311.12015","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12015","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12015v4","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12015","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"VEBY7NGB7T5L","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"VEBY7NGB7T5L6RL5","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"VEBY7NGB","created_at":"2026-07-05T09:18:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VEBY7NGB7T5L6RL534NV3LX7GS","target":"record","payload":{"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"},"canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","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"},"source_kind":"arxiv","source_id":"2311.12015","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwnjxlzhU2YKJcU8IcsLKC2EBqBti7E2d0HOeA0raCYI/f2XfqBiiStSPsxvaTHnCNGA/80L9AJHS7kMWiQLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:39:14.317507Z"},"content_sha256":"3832b9f3a92d84210f7f5653b633592e127db45e485229f57f95b2ffb5b06c95","schema_version":"1.0","event_id":"sha256:3832b9f3a92d84210f7f5653b633592e127db45e485229f57f95b2ffb5b06c95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VEBY7NGB7T5L6RL534NV3LX7GS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzA0mzLxSLfF8IPwQjAbeYDpBjr/kXZ/LGcPH7A7wQ18BeoIhALA5b+CwT5uRp9HGaRIOGlbTxcodpKLTlUyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:39:14.318296Z"},"content_sha256":"08cc1ab8457f850c811cafbb5b461aaeb2fc0b2320f3322eaaef68a07a651340","schema_version":"1.0","event_id":"sha256:08cc1ab8457f850c811cafbb5b461aaeb2fc0b2320f3322eaaef68a07a651340"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/bundle.json","state_url":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEBY7NGB7T5L6RL534NV3LX7GS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T02:39:14Z","links":{"resolver":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS","bundle":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/bundle.json","state":"https://pith.science/pith/VEBY7NGB7T5L6RL534NV3LX7GS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEBY7NGB7T5L6RL534NV3LX7GS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VEBY7NGB7T5L6RL534NV3LX7GS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"250bf8b910b0b1595fbd1ac129edcdd97e2321e7eb12b3c9c76cde05e34a95ed","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-20T18:54:39Z","title_canon_sha256":"c09903ed8a50b48c626167ad9250c0dc93fa7599e0eed109b3cecb9eb1086ec1"},"schema_version":"1.0","source":{"id":"2311.12015","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12015","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12015v4","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12015","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"VEBY7NGB7T5L","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"VEBY7NGB7T5L6RL5","created_at":"2026-07-05T09:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"VEBY7NGB","created_at":"2026-07-05T09:18:21Z"}],"graph_snapshots":[{"event_id":"sha256:08cc1ab8457f850c811cafbb5b461aaeb2fc0b2320f3322eaaef68a07a651340","target":"graph","created_at":"2026-07-05T09:18:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.12015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Atsushi Kanehira, Jun Takamatsu, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Naoki Wake","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-20T18:54:39Z","title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12015","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3832b9f3a92d84210f7f5653b633592e127db45e485229f57f95b2ffb5b06c95","target":"record","created_at":"2026-07-05T09:18:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"250bf8b910b0b1595fbd1ac129edcdd97e2321e7eb12b3c9c76cde05e34a95ed","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-20T18:54:39Z","title_canon_sha256":"c09903ed8a50b48c626167ad9250c0dc93fa7599e0eed109b3cecb9eb1086ec1"},"schema_version":"1.0","source":{"id":"2311.12015","kind":"arxiv","version":4}},"canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9038fb4c1fcfabf457ddf1b5daeff349255dc4a4cd7d8da7fbfe975e945a749","first_computed_at":"2026-07-05T09:18:21.470800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:21.470800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ieSEr5BYR5xU+4aoR+whMwQBvNUgmAFbnWzV6uIjeTBUOhFmV03Rk2OFmrPMtbgnqrNUBzu2yBeYwiC5MtJrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:21.471258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12015","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3832b9f3a92d84210f7f5653b633592e127db45e485229f57f95b2ffb5b06c95","sha256:08cc1ab8457f850c811cafbb5b461aaeb2fc0b2320f3322eaaef68a07a651340"],"state_sha256":"71620bc8ec2d53f46ba1be6e414c33379bf83cb0eac7ee5c76266bc3e17cfcc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/T+96TojXU55hXF8hOgg7ZzJxqY0DhoxM/Zp1iYy/tDpvQDDTBCHspAhYy26DWAF2+yogSMfL6vvDI3asDJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:39:14.325897Z","bundle_sha256":"cf8d2eec63e04f825cefc2b464c2433ed1ac2dc4f18df0ae37682554b128121f"}}