{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:APTM2RGTNNX6WQYUQGHRDZFNZF","short_pith_number":"pith:APTM2RGT","canonical_record":{"source":{"id":"2507.12440","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T17:27:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"35d6c8a08ed7e862faa491421fdea9b3a680d66ca768d255f737e8d6fcc54559","abstract_canon_sha256":"f9e2b4dcdf8182edd04a77c1e3edb2b0a086f24bd68c6138699b57a11247243b"},"schema_version":"1.0"},"canonical_sha256":"03e6cd44d36b6feb4314818f11e4adc97aef8ffe8273958dd4f6eb7db107a00c","source":{"kind":"arxiv","id":"2507.12440","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12440","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12440v3","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12440","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"APTM2RGTNNX6","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"APTM2RGTNNX6WQYU","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"APTM2RGT","created_at":"2026-05-21T04:27:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:APTM2RGTNNX6WQYUQGHRDZFNZF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12440","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T17:27:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"35d6c8a08ed7e862faa491421fdea9b3a680d66ca768d255f737e8d6fcc54559","abstract_canon_sha256":"f9e2b4dcdf8182edd04a77c1e3edb2b0a086f24bd68c6138699b57a11247243b"},"schema_version":"1.0"},"canonical_sha256":"03e6cd44d36b6feb4314818f11e4adc97aef8ffe8273958dd4f6eb7db107a00c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T04:27:34.074456Z","signature_b64":"pUUc1EWri/w4sNpwV7MgbN+tvv7f8zKaqB/Ceo37Hi/RljOLVx1ZfUA9HOfSCGBS/hyUhlFUExJuuOs0ddKDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e6cd44d36b6feb4314818f11e4adc97aef8ffe8273958dd4f6eb7db107a00c","last_reissued_at":"2026-05-21T04:27:34.072705Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T04:27:34.072705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12440","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T04:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cadu0FO0J1MdRy7y6taxhq4MfvLIM3w+KGhEDvkfooO1mJsPCiN2yyAnounSjaoJY/3q75P8XMTR4UgKgJaAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:15:02.964693Z"},"content_sha256":"016a3a212c159e063a8626838591d5eec5ab068b05afbc23db31f8449878552c","schema_version":"1.0","event_id":"sha256:016a3a212c159e063a8626838591d5eec5ab068b05afbc23db31f8449878552c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:APTM2RGTNNX6WQYUQGHRDZFNZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"An-Chieh Cheng, BoRui Li, Hongxu Yin, Qinxi Yu, Ri-Zhao Qiu, Ruihan Yang, Rui Yan, Sifei Liu, Song Han, Xiaolong Wang, Xueyan Zou, Xuxin Cheng, Yao Lu, Yecheng Wu, Yunhao Fang","submitted_at":"2025-07-16T17:27:44Z","abstract_excerpt":"Real robot data collection for imitation learning has led to significant advancements in robotic manipulation. However, the requirement for robot hardware in the process fundamentally constrains the scale of the data. In this paper, we explore training Vision-Language-Action (VLA) models using egocentric human videos. The benefit of using human videos is not only for their scale but more importantly for the richness of scenes and tasks. With a VLA trained on human video that predicts human wrist and hand actions, we can perform Inverse Kinematics and retargeting to convert the human actions to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12440","kind":"arxiv","version":3},"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/2507.12440/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":"2026-05-21T04:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1IZRDphCT9JJeCgpU6Yyztf4GCW0svt4HU/FSkP0A6kKVB8O2rm86Q5+ZDmZ+606yEgSk+rMC0cBsEH9CoFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:15:02.965376Z"},"content_sha256":"9b52b1beba76688c464580cf3e341d5ae3f277ecca6e5ab1deb312bdc3eaad14","schema_version":"1.0","event_id":"sha256:9b52b1beba76688c464580cf3e341d5ae3f277ecca6e5ab1deb312bdc3eaad14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/bundle.json","state_url":"https://pith.science/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/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":"2026-05-22T03:15:02Z","links":{"resolver":"https://pith.science/pith/APTM2RGTNNX6WQYUQGHRDZFNZF","bundle":"https://pith.science/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/bundle.json","state":"https://pith.science/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APTM2RGTNNX6WQYUQGHRDZFNZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:APTM2RGTNNX6WQYUQGHRDZFNZF","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":"f9e2b4dcdf8182edd04a77c1e3edb2b0a086f24bd68c6138699b57a11247243b","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T17:27:44Z","title_canon_sha256":"35d6c8a08ed7e862faa491421fdea9b3a680d66ca768d255f737e8d6fcc54559"},"schema_version":"1.0","source":{"id":"2507.12440","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12440","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12440v3","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12440","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"APTM2RGTNNX6","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"APTM2RGTNNX6WQYU","created_at":"2026-05-21T04:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"APTM2RGT","created_at":"2026-05-21T04:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:9b52b1beba76688c464580cf3e341d5ae3f277ecca6e5ab1deb312bdc3eaad14","target":"graph","created_at":"2026-05-21T04:27:34Z","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/2507.12440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real robot data collection for imitation learning has led to significant advancements in robotic manipulation. However, the requirement for robot hardware in the process fundamentally constrains the scale of the data. In this paper, we explore training Vision-Language-Action (VLA) models using egocentric human videos. The benefit of using human videos is not only for their scale but more importantly for the richness of scenes and tasks. With a VLA trained on human video that predicts human wrist and hand actions, we can perform Inverse Kinematics and retargeting to convert the human actions to","authors_text":"An-Chieh Cheng, BoRui Li, Hongxu Yin, Qinxi Yu, Ri-Zhao Qiu, Ruihan Yang, Rui Yan, Sifei Liu, Song Han, Xiaolong Wang, Xueyan Zou, Xuxin Cheng, Yao Lu, Yecheng Wu, Yunhao Fang","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T17:27:44Z","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12440","kind":"arxiv","version":3},"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":"sha256:016a3a212c159e063a8626838591d5eec5ab068b05afbc23db31f8449878552c","target":"record","created_at":"2026-05-21T04:27:34Z","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":"f9e2b4dcdf8182edd04a77c1e3edb2b0a086f24bd68c6138699b57a11247243b","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T17:27:44Z","title_canon_sha256":"35d6c8a08ed7e862faa491421fdea9b3a680d66ca768d255f737e8d6fcc54559"},"schema_version":"1.0","source":{"id":"2507.12440","kind":"arxiv","version":3}},"canonical_sha256":"03e6cd44d36b6feb4314818f11e4adc97aef8ffe8273958dd4f6eb7db107a00c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e6cd44d36b6feb4314818f11e4adc97aef8ffe8273958dd4f6eb7db107a00c","first_computed_at":"2026-05-21T04:27:34.072705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T04:27:34.072705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pUUc1EWri/w4sNpwV7MgbN+tvv7f8zKaqB/Ceo37Hi/RljOLVx1ZfUA9HOfSCGBS/hyUhlFUExJuuOs0ddKDBA==","signature_status":"signed_v1","signed_at":"2026-05-21T04:27:34.074456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12440","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:016a3a212c159e063a8626838591d5eec5ab068b05afbc23db31f8449878552c","sha256:9b52b1beba76688c464580cf3e341d5ae3f277ecca6e5ab1deb312bdc3eaad14"],"state_sha256":"8eaf68c43474c537b60257dbdc2ff9c972100e4a3044e6029d22b684ac3b5d92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8xMztgs7JaxCtcFHOYiW/N0LVcpVoMuBqYvfVqLuHzfT1FSGYFcF7zPy1ctWBMb27PAAVAOshjJlFURlCZiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T03:15:02.968889Z","bundle_sha256":"3d2eb1b76738cbcb563cc87953965f8d43029cc6bc7196a8e57404a165a2a38b"}}