{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JFT5LUVLKGZ2EFN3QF7I4CDTDX","short_pith_number":"pith:JFT5LUVL","schema_version":"1.0","canonical_sha256":"4967d5d2ab51b3a215bb817e8e08731df20406e22f99dfe17b45cc32c325875d","source":{"kind":"arxiv","id":"2509.05513","version":1},"attestation_state":"computed","paper":{"title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ahad Jawaid, Yu Xiang","submitted_at":"2025-09-05T21:47:55Z","abstract_excerpt":"Egocentric human videos provide scalable demonstrations for imitation learning, but existing corpora often lack either fine-grained, temporally localized action descriptions or dexterous hand annotations. We introduce OpenEgo, a multimodal egocentric manipulation dataset with standardized hand-pose annotations and intention-aligned action primitives. OpenEgo totals 1107 hours across six public datasets, covering 290 manipulation tasks in 600+ environments. We unify hand-pose layouts and provide descriptive, timestamped action primitives. To validate its utility, we train language-conditioned 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":"2509.05513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T21:47:55Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5ed5cc27ed2a21d141155df4c10b815ee7bd96c4d2fb36a010a7441934ced80a","abstract_canon_sha256":"32b308195614c880898e2c3d0cc842cb6bd9a3398eccfa745a7752531824a810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:48.853251Z","signature_b64":"CiinBFNkOQz1K0CQT/czQMevS5gzIDxuFW3C5twm6TvsZZJhBix3BEUdVhgJJxrXwBKL0XRo2Lb6gFbrsXQCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4967d5d2ab51b3a215bb817e8e08731df20406e22f99dfe17b45cc32c325875d","last_reissued_at":"2026-07-05T12:05:48.852764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:48.852764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ahad Jawaid, Yu Xiang","submitted_at":"2025-09-05T21:47:55Z","abstract_excerpt":"Egocentric human videos provide scalable demonstrations for imitation learning, but existing corpora often lack either fine-grained, temporally localized action descriptions or dexterous hand annotations. We introduce OpenEgo, a multimodal egocentric manipulation dataset with standardized hand-pose annotations and intention-aligned action primitives. OpenEgo totals 1107 hours across six public datasets, covering 290 manipulation tasks in 600+ environments. We unify hand-pose layouts and provide descriptive, timestamped action primitives. To validate its utility, we train language-conditioned i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05513","kind":"arxiv","version":1},"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/2509.05513/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":"2509.05513","created_at":"2026-07-05T12:05:48.852821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05513v1","created_at":"2026-07-05T12:05:48.852821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05513","created_at":"2026-07-05T12:05:48.852821+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFT5LUVLKGZ2","created_at":"2026-07-05T12:05:48.852821+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFT5LUVLKGZ2EFN3","created_at":"2026-07-05T12:05:48.852821+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFT5LUVL","created_at":"2026-07-05T12:05:48.852821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27325","citing_title":"Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31234","citing_title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13925","citing_title":"Towards Robotic Dexterous Hand Intelligence: A Survey","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06747","citing_title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX","json":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX.json","graph_json":"https://pith.science/api/pith-number/JFT5LUVLKGZ2EFN3QF7I4CDTDX/graph.json","events_json":"https://pith.science/api/pith-number/JFT5LUVLKGZ2EFN3QF7I4CDTDX/events.json","paper":"https://pith.science/paper/JFT5LUVL"},"agent_actions":{"view_html":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX","download_json":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX.json","view_paper":"https://pith.science/paper/JFT5LUVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05513&json=true","fetch_graph":"https://pith.science/api/pith-number/JFT5LUVLKGZ2EFN3QF7I4CDTDX/graph.json","fetch_events":"https://pith.science/api/pith-number/JFT5LUVLKGZ2EFN3QF7I4CDTDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX/action/storage_attestation","attest_author":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX/action/author_attestation","sign_citation":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX/action/citation_signature","submit_replication":"https://pith.science/pith/JFT5LUVLKGZ2EFN3QF7I4CDTDX/action/replication_record"}},"created_at":"2026-07-05T12:05:48.852821+00:00","updated_at":"2026-07-05T12:05:48.852821+00:00"}