{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GRRJEQVM25UMTGQBLBF6EWZSEP","short_pith_number":"pith:GRRJEQVM","canonical_record":{"source":{"id":"2403.12943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:47:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"665e9a37da3b266d7c0ea06c4e2286a59d401b5c3a4235956f9cd310aebc3bf9","abstract_canon_sha256":"430c30914844e790ad303f7691e6e5178020b1b1224fef137fd5073658c57337"},"schema_version":"1.0"},"canonical_sha256":"34629242acd768c99a01584be25b3223c3a7dcfe82dfece9963c27902f036b7a","source":{"kind":"arxiv","id":"2403.12943","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12943","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12943v2","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12943","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"GRRJEQVM25UM","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"GRRJEQVM25UMTGQB","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"GRRJEQVM","created_at":"2026-07-05T09:00:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GRRJEQVM25UMTGQBLBF6EWZSEP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:47:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"665e9a37da3b266d7c0ea06c4e2286a59d401b5c3a4235956f9cd310aebc3bf9","abstract_canon_sha256":"430c30914844e790ad303f7691e6e5178020b1b1224fef137fd5073658c57337"},"schema_version":"1.0"},"canonical_sha256":"34629242acd768c99a01584be25b3223c3a7dcfe82dfece9963c27902f036b7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:02.835344Z","signature_b64":"4BB4UrIL8/24hZ4wiDgVoHrw5tRK6W8NZYNQYvIgEnGZ/rnz450rN40KdIseQH3tToUIzeQc87UiOLXGuDksDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34629242acd768c99a01584be25b3223c3a7dcfe82dfece9963c27902f036b7a","last_reissued_at":"2026-07-05T09:00:02.834838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:02.834838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12943","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rcz8qpyqQWBu4t95NX/3rUc4IGRl37DkfrFH370QQalTRQ5keMa/3p2Cbt0J2eWvVkyvK9u1eOpOGwwvZsfvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:31:37.879903Z"},"content_sha256":"cfdfd5aaca399b12238045c7d00e42aa08aa88751d4014bbbcb1792e63c986d4","schema_version":"1.0","event_id":"sha256:cfdfd5aaca399b12238045c7d00e42aa08aa88751d4014bbbcb1792e63c986d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GRRJEQVM25UMTGQBLBF6EWZSEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ayzaan Wahid, Christine Chan, Danny Driess, Debidatta Dwibedi, Igor Gilitschenski, Maria Attarian, Nikhil J Joshi, Pannag R Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Vidhi Jain, Yonatan Bisk","submitted_at":"2024-03-19T17:47:37Z","abstract_excerpt":"Large-scale multi-task robotic manipulation systems often rely on text to specify the task. In this work, we explore whether a robot can learn by observing humans. To do so, the robot must understand a person's intent and perform the inferred task despite differences in the embodiments and environments. We introduce Vid2Robot, an end-to-end video-conditioned policy that takes human videos demonstrating manipulation tasks as input and produces robot actions. Our model is trained with a large dataset of prompt video-robot trajectory pairs to learn unified representations of human and robot actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12943","kind":"arxiv","version":2},"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/2403.12943/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":"2026-07-05T09:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FKmT3U5iDym6RHSvWHZ7yeyWWP2tCPwsp7kJVt5Co/ihemAmKmFi5w7kHEygOJu+JKsfO9u1sPWbc1qCsymAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:31:37.880588Z"},"content_sha256":"73c50ba4478f3ad60facdfe9206b0bec917d40648e6cdfd09d214e9f3e14c453","schema_version":"1.0","event_id":"sha256:73c50ba4478f3ad60facdfe9206b0bec917d40648e6cdfd09d214e9f3e14c453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/bundle.json","state_url":"https://pith.science/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/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":"2026-08-19T21:31:37Z","links":{"resolver":"https://pith.science/pith/GRRJEQVM25UMTGQBLBF6EWZSEP","bundle":"https://pith.science/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/bundle.json","state":"https://pith.science/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRRJEQVM25UMTGQBLBF6EWZSEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GRRJEQVM25UMTGQBLBF6EWZSEP","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":"430c30914844e790ad303f7691e6e5178020b1b1224fef137fd5073658c57337","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:47:37Z","title_canon_sha256":"665e9a37da3b266d7c0ea06c4e2286a59d401b5c3a4235956f9cd310aebc3bf9"},"schema_version":"1.0","source":{"id":"2403.12943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12943","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12943v2","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12943","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"GRRJEQVM25UM","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"GRRJEQVM25UMTGQB","created_at":"2026-07-05T09:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"GRRJEQVM","created_at":"2026-07-05T09:00:02Z"}],"graph_snapshots":[{"event_id":"sha256:73c50ba4478f3ad60facdfe9206b0bec917d40648e6cdfd09d214e9f3e14c453","target":"graph","created_at":"2026-07-05T09:00:02Z","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/2403.12943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale multi-task robotic manipulation systems often rely on text to specify the task. In this work, we explore whether a robot can learn by observing humans. To do so, the robot must understand a person's intent and perform the inferred task despite differences in the embodiments and environments. We introduce Vid2Robot, an end-to-end video-conditioned policy that takes human videos demonstrating manipulation tasks as input and produces robot actions. Our model is trained with a large dataset of prompt video-robot trajectory pairs to learn unified representations of human and robot actio","authors_text":"Ayzaan Wahid, Christine Chan, Danny Driess, Debidatta Dwibedi, Igor Gilitschenski, Maria Attarian, Nikhil J Joshi, Pannag R Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Vidhi Jain, Yonatan Bisk","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:47:37Z","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12943","kind":"arxiv","version":2},"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:cfdfd5aaca399b12238045c7d00e42aa08aa88751d4014bbbcb1792e63c986d4","target":"record","created_at":"2026-07-05T09:00:02Z","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":"430c30914844e790ad303f7691e6e5178020b1b1224fef137fd5073658c57337","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-19T17:47:37Z","title_canon_sha256":"665e9a37da3b266d7c0ea06c4e2286a59d401b5c3a4235956f9cd310aebc3bf9"},"schema_version":"1.0","source":{"id":"2403.12943","kind":"arxiv","version":2}},"canonical_sha256":"34629242acd768c99a01584be25b3223c3a7dcfe82dfece9963c27902f036b7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34629242acd768c99a01584be25b3223c3a7dcfe82dfece9963c27902f036b7a","first_computed_at":"2026-07-05T09:00:02.834838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:02.834838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4BB4UrIL8/24hZ4wiDgVoHrw5tRK6W8NZYNQYvIgEnGZ/rnz450rN40KdIseQH3tToUIzeQc87UiOLXGuDksDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:02.835344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfdfd5aaca399b12238045c7d00e42aa08aa88751d4014bbbcb1792e63c986d4","sha256:73c50ba4478f3ad60facdfe9206b0bec917d40648e6cdfd09d214e9f3e14c453"],"state_sha256":"610cc032f5b657e3d9007ea2a4efdea034d50520687f0832d1be407ab533e5fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F32KXCHa73tMrjjbhJrAfvAfnE13uT3MupYMoNHj5DIp/GuxT9LDGYbEo72NYELeW3ZwQH4HwW08Ejj2BM0yBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:31:37.887276Z","bundle_sha256":"4950e4fe3db1388c8773d468aea33b1d22795330a473ec11db319c277042e295"}}