{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GRQAVAUJLHOLHOYGN5NYY5B7K6","short_pith_number":"pith:GRQAVAUJ","canonical_record":{"source":{"id":"2604.24681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-27T16:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"63f2c3e9f6d365c198ae85a9197536e4ade200b0bfd8ad0a6d5a8cea836f2db4","abstract_canon_sha256":"9a7bfcc568bc41266cd16956e666af7770068d98376afd8fd735c12302fd09d8"},"schema_version":"1.0"},"canonical_sha256":"34600a828959dcb3bb066f5b8c743f57be7943b8efc14c3b1da63586ce3bd91e","source":{"kind":"arxiv","id":"2604.24681","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24681","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24681v2","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24681","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"GRQAVAUJLHOL","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"GRQAVAUJLHOLHOYG","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"GRQAVAUJ","created_at":"2026-05-22T01:04:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GRQAVAUJLHOLHOYGN5NYY5B7K6","target":"record","payload":{"canonical_record":{"source":{"id":"2604.24681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-27T16:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"63f2c3e9f6d365c198ae85a9197536e4ade200b0bfd8ad0a6d5a8cea836f2db4","abstract_canon_sha256":"9a7bfcc568bc41266cd16956e666af7770068d98376afd8fd735c12302fd09d8"},"schema_version":"1.0"},"canonical_sha256":"34600a828959dcb3bb066f5b8c743f57be7943b8efc14c3b1da63586ce3bd91e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:03.267001Z","signature_b64":"lB1KmVeb9YQhr/5OU+COY9bL1stg8KTeNacGYi97uPvbMzXQ6FOH4+PlpVVhkOiwR61sfzjqeJhU2w+od/wnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34600a828959dcb3bb066f5b8c743f57be7943b8efc14c3b1da63586ce3bd91e","last_reissued_at":"2026-05-22T01:04:03.266172Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:03.266172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.24681","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":"2026-05-22T01:04:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jq0PwQLUKX159lHBxkEKv7ta/Yhtx/KnSXTZ5GEktMIrOcCaYD8FP94elJBnpoUIWAIYjudwqs7RSL9DtsSVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:53:10.719709Z"},"content_sha256":"78e61b7aa11358bf707b1a76a46b8f7a8def38e1bbdd7723d78b0e34d28a0954","schema_version":"1.0","event_id":"sha256:78e61b7aa11358bf707b1a76a46b8f7a8def38e1bbdd7723d78b0e34d28a0954"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GRQAVAUJLHOLHOYGN5NYY5B7K6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guangyu Chen, Jinkun Liu, Wenbo Ding, Yifan Xie, Yuan Wang, Yu Sun","submitted_at":"2026-04-27T16:42:18Z","abstract_excerpt":"Human videos contain rich manipulation priors, but using them for robot learning remains difficult because raw observations entangle scene understanding, human motion, and embodiment-specific action. We introduce MoT-HRA, a hierarchical vision-language-action framework that learns human-intention priors from large-scale human demonstrations. We first curate HA-2.2M, a 2.2M-episode action-language dataset reconstructed from heterogeneous human videos through hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment. On top of this dataset, MoT-HRA factorizes "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on hand motion generation, simulated manipulation, and real-world robot tasks show that MoT-HRA improves motion plausibility and robust control under distribution shift.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment steps used to curate HA-2.2M from heterogeneous human videos successfully extract embodiment-agnostic human-intention priors without introducing substantial artifacts, biases, or loss of critical information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoT-HRA learns embodiment-agnostic human-intention priors from the HA-2.2M dataset of 2.2M human video episodes through a three-expert hierarchy to improve robotic motion plausibility and robustness under distribution shift.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"66c603715eb6d7cdf74b6843da26f8261679f25ef47635e1e19d0f3a673bd240"},"source":{"id":"2604.24681","kind":"arxiv","version":2},"verdict":{"id":"5ab851d7-5b8c-47f4-90b0-e0462b72c8ef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T02:45:55.774426Z","strongest_claim":"Experiments on hand motion generation, simulated manipulation, and real-world robot tasks show that MoT-HRA improves motion plausibility and robust control under distribution shift.","one_line_summary":"MoT-HRA learns embodiment-agnostic human-intention priors from the HA-2.2M dataset of 2.2M human video episodes through a three-expert hierarchy to improve robotic motion plausibility and robustness under distribution shift.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment steps used to curate HA-2.2M from heterogeneous human videos successfully extract embodiment-agnostic human-intention priors without introducing substantial artifacts, biases, or loss of critical information.","pith_extraction_headline":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24681/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T06:35:50.393016Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:52:19.836490Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"272f2bb85cf96cb87582202480ecbbd3958db1baffd10a154ca3ea0257545eec"},"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":"5ab851d7-5b8c-47f4-90b0-e0462b72c8ef"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89nYM3YYPBgLYkigCUjoI6+dJMy72mIClW0Ji0CJ4xg5lDSx+EfLYt+K0PIKA1Gsfr4UGaPGp7idmNMXMncJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:53:10.720216Z"},"content_sha256":"49128938bf9ac4f98c5da724255eae0ec4de45120d33e31fdfc681daf305ff9f","schema_version":"1.0","event_id":"sha256:49128938bf9ac4f98c5da724255eae0ec4de45120d33e31fdfc681daf305ff9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/bundle.json","state_url":"https://pith.science/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/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":"2026-06-05T20:53:10Z","links":{"resolver":"https://pith.science/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6","bundle":"https://pith.science/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/bundle.json","state":"https://pith.science/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRQAVAUJLHOLHOYGN5NYY5B7K6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GRQAVAUJLHOLHOYGN5NYY5B7K6","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":"9a7bfcc568bc41266cd16956e666af7770068d98376afd8fd735c12302fd09d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-27T16:42:18Z","title_canon_sha256":"63f2c3e9f6d365c198ae85a9197536e4ade200b0bfd8ad0a6d5a8cea836f2db4"},"schema_version":"1.0","source":{"id":"2604.24681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24681","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24681v2","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24681","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"GRQAVAUJLHOL","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"GRQAVAUJLHOLHOYG","created_at":"2026-05-22T01:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"GRQAVAUJ","created_at":"2026-05-22T01:04:03Z"}],"graph_snapshots":[{"event_id":"sha256:49128938bf9ac4f98c5da724255eae0ec4de45120d33e31fdfc681daf305ff9f","target":"graph","created_at":"2026-05-22T01:04:03Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on hand motion generation, simulated manipulation, and real-world robot tasks show that MoT-HRA improves motion plausibility and robust control under distribution shift."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment steps used to curate HA-2.2M from heterogeneous human videos successfully extract embodiment-agnostic human-intention priors without introducing substantial artifacts, biases, or loss of critical information."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MoT-HRA learns embodiment-agnostic human-intention priors from the HA-2.2M dataset of 2.2M human video episodes through a three-expert hierarchy to improve robotic motion plausibility and robustness under distribution shift."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation."}],"snapshot_sha256":"66c603715eb6d7cdf74b6843da26f8261679f25ef47635e1e19d0f3a673bd240"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T06:35:50.393016Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:52:19.836490Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.24681/integrity.json","findings":[],"snapshot_sha256":"272f2bb85cf96cb87582202480ecbbd3958db1baffd10a154ca3ea0257545eec","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human videos contain rich manipulation priors, but using them for robot learning remains difficult because raw observations entangle scene understanding, human motion, and embodiment-specific action. We introduce MoT-HRA, a hierarchical vision-language-action framework that learns human-intention priors from large-scale human demonstrations. We first curate HA-2.2M, a 2.2M-episode action-language dataset reconstructed from heterogeneous human videos through hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment. On top of this dataset, MoT-HRA factorizes ","authors_text":"Guangyu Chen, Jinkun Liu, Wenbo Ding, Yifan Xie, Yuan Wang, Yu Sun","cross_cats":[],"headline":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-27T16:42:18Z","title":"Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.24681","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T02:45:55.774426Z","id":"5ab851d7-5b8c-47f4-90b0-e0462b72c8ef","model_set":{"reader":"grok-4.3"},"one_line_summary":"MoT-HRA learns embodiment-agnostic human-intention priors from the HA-2.2M dataset of 2.2M human video episodes through a three-expert hierarchy to improve robotic motion plausibility and robustness under distribution shift.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MoT-HRA learns human-intention priors from 2.2 million video episodes to guide more reliable robot manipulation.","strongest_claim":"Experiments on hand motion generation, simulated manipulation, and real-world robot tasks show that MoT-HRA improves motion plausibility and robust control under distribution shift.","weakest_assumption":"The hand-centric filtering, spatial reconstruction, temporal segmentation, and language alignment steps used to curate HA-2.2M from heterogeneous human videos successfully extract embodiment-agnostic human-intention priors without introducing substantial artifacts, biases, or loss of critical information."}},"verdict_id":"5ab851d7-5b8c-47f4-90b0-e0462b72c8ef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78e61b7aa11358bf707b1a76a46b8f7a8def38e1bbdd7723d78b0e34d28a0954","target":"record","created_at":"2026-05-22T01:04:03Z","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":"9a7bfcc568bc41266cd16956e666af7770068d98376afd8fd735c12302fd09d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-27T16:42:18Z","title_canon_sha256":"63f2c3e9f6d365c198ae85a9197536e4ade200b0bfd8ad0a6d5a8cea836f2db4"},"schema_version":"1.0","source":{"id":"2604.24681","kind":"arxiv","version":2}},"canonical_sha256":"34600a828959dcb3bb066f5b8c743f57be7943b8efc14c3b1da63586ce3bd91e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34600a828959dcb3bb066f5b8c743f57be7943b8efc14c3b1da63586ce3bd91e","first_computed_at":"2026-05-22T01:04:03.266172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:03.266172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lB1KmVeb9YQhr/5OU+COY9bL1stg8KTeNacGYi97uPvbMzXQ6FOH4+PlpVVhkOiwR61sfzjqeJhU2w+od/wnAQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:03.267001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.24681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78e61b7aa11358bf707b1a76a46b8f7a8def38e1bbdd7723d78b0e34d28a0954","sha256:49128938bf9ac4f98c5da724255eae0ec4de45120d33e31fdfc681daf305ff9f"],"state_sha256":"a858e3fd0db8f0b08e0f9108391d71daae5ebc13719313e97d0ce18d3d0f7b38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UrvkYU6Kse+nOKjjPE71jApA1xPxSp6mdMKQFt0PqiMTdM+lsi9LN0+pellF6aArLUCCOzzbYuCZlA7V5joMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:53:10.722845Z","bundle_sha256":"8fb3f35e52d974d138251a62899933e6576e62ffda6f0012658a96b9430bb031"}}