{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYBQHHR76HNB5XYVLYO2Q3CWVG","short_pith_number":"pith:MYBQHHR7","schema_version":"1.0","canonical_sha256":"6603039e3ff1da1edf155e1da86c56a9b67555443de3646401477c1cd26d7b5a","source":{"kind":"arxiv","id":"2411.08380","version":1},"attestation_state":"computed","paper":{"title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Liu, Guosheng Zhao, Jiayu Wang, Kang Zhao, Xiaofeng Wang, Xiaoyi Bao, Xingang Wang, Yingya Zhang, Zheng Zhu","submitted_at":"2024-11-13T07:05:40Z","abstract_excerpt":"Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments. Within this context, egocentric video generation, which centers on the human perspective, holds significant potential for enhancing applications in virtual reality, augmented reality, and gaming. However, the generation of egocentric videos presents substantial challenges due to the dynamic nature of egocentric viewpoints, the intricate diversity of actions, and the complex variety of scenes encountered. Existing datasets are inadequate for addressing these challe"},"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":"2411.08380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T07:05:40Z","cross_cats_sorted":[],"title_canon_sha256":"5237e57cabb9dad6cfab4491e8f07e56fee2ce86f300395ec354c4437899fe5a","abstract_canon_sha256":"98df4e5e7010ac5358b86b7fe1b591db17321d7ff631f6f78ef11ac528d87338"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:46.503035Z","signature_b64":"JNaHVmRmbmUiHi7RPVGSwOUIYmWOo4oK9hFHltjTqObfdetvoaN+krrQBjsi0/18vlAKvNW7+cv93NKUf6tiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6603039e3ff1da1edf155e1da86c56a9b67555443de3646401477c1cd26d7b5a","last_reissued_at":"2026-07-05T09:34:46.502616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:46.502616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Liu, Guosheng Zhao, Jiayu Wang, Kang Zhao, Xiaofeng Wang, Xiaoyi Bao, Xingang Wang, Yingya Zhang, Zheng Zhu","submitted_at":"2024-11-13T07:05:40Z","abstract_excerpt":"Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments. Within this context, egocentric video generation, which centers on the human perspective, holds significant potential for enhancing applications in virtual reality, augmented reality, and gaming. However, the generation of egocentric videos presents substantial challenges due to the dynamic nature of egocentric viewpoints, the intricate diversity of actions, and the complex variety of scenes encountered. Existing datasets are inadequate for addressing these challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08380","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/2411.08380/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":"2411.08380","created_at":"2026-07-05T09:34:46.502674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08380v1","created_at":"2026-07-05T09:34:46.502674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08380","created_at":"2026-07-05T09:34:46.502674+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYBQHHR76HNB","created_at":"2026-07-05T09:34:46.502674+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYBQHHR76HNB5XYV","created_at":"2026-07-05T09:34:46.502674+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYBQHHR7","created_at":"2026-07-05T09:34:46.502674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26316","citing_title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18127","citing_title":"SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27621","citing_title":"Robot Learning from Human Videos: A Survey","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09535","citing_title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG","json":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG.json","graph_json":"https://pith.science/api/pith-number/MYBQHHR76HNB5XYVLYO2Q3CWVG/graph.json","events_json":"https://pith.science/api/pith-number/MYBQHHR76HNB5XYVLYO2Q3CWVG/events.json","paper":"https://pith.science/paper/MYBQHHR7"},"agent_actions":{"view_html":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG","download_json":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG.json","view_paper":"https://pith.science/paper/MYBQHHR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08380&json=true","fetch_graph":"https://pith.science/api/pith-number/MYBQHHR76HNB5XYVLYO2Q3CWVG/graph.json","fetch_events":"https://pith.science/api/pith-number/MYBQHHR76HNB5XYVLYO2Q3CWVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG/action/storage_attestation","attest_author":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG/action/author_attestation","sign_citation":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG/action/citation_signature","submit_replication":"https://pith.science/pith/MYBQHHR76HNB5XYVLYO2Q3CWVG/action/replication_record"}},"created_at":"2026-07-05T09:34:46.502674+00:00","updated_at":"2026-07-05T09:34:46.502674+00:00"}