{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M77K7C6EGWN5VIAIIBDCXYVKSS","short_pith_number":"pith:M77K7C6E","schema_version":"1.0","canonical_sha256":"67feaf8bc4359bdaa00840462be2aa948b29f1606b2a31f28560502fbfff9ae2","source":{"kind":"arxiv","id":"2508.13013","version":1},"attestation_state":"computed","paper":{"title":"EgoTwin: Dreaming Body and View in First Person","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Jingqiao Xiu, Liang Pan, Mengze Li, Sirui Han, Wentao Wang, Yicong Li, Ziwei Liu","submitted_at":"2025-08-18T15:33:09Z","abstract_excerpt":"While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with"},"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":"2508.13013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T15:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"4a8f4d2cd464be7e9e8bb2c8df7d64b10656e1f03bd7fd38e31762257f38026f","abstract_canon_sha256":"8b5497ee57022bc9716ffb68dc3744043819b10e4c92c046a6b303624324bd90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:30.883829Z","signature_b64":"iv1+Sz1CGfKvnLhw4nWgau8rZKJRhBWCC2fZ31FQKl7lCzcl/BR8iO1RHdRKlXNLzPb2sWhVtXYlo7opF239AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67feaf8bc4359bdaa00840462be2aa948b29f1606b2a31f28560502fbfff9ae2","last_reissued_at":"2026-07-05T11:55:30.883349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:30.883349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoTwin: Dreaming Body and View in First Person","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Jingqiao Xiu, Liang Pan, Mengze Li, Sirui Han, Wentao Wang, Yicong Li, Ziwei Liu","submitted_at":"2025-08-18T15:33:09Z","abstract_excerpt":"While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13013","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/2508.13013/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":"2508.13013","created_at":"2026-07-05T11:55:30.883408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13013v1","created_at":"2026-07-05T11:55:30.883408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13013","created_at":"2026-07-05T11:55:30.883408+00:00"},{"alias_kind":"pith_short_12","alias_value":"M77K7C6EGWN5","created_at":"2026-07-05T11:55:30.883408+00:00"},{"alias_kind":"pith_short_16","alias_value":"M77K7C6EGWN5VIAI","created_at":"2026-07-05T11:55:30.883408+00:00"},{"alias_kind":"pith_short_8","alias_value":"M77K7C6E","created_at":"2026-07-05T11:55:30.883408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26316","citing_title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21714","citing_title":"AstraNav-World: World Model for Foresight Control and Consistency","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19105","citing_title":"EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS","json":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS.json","graph_json":"https://pith.science/api/pith-number/M77K7C6EGWN5VIAIIBDCXYVKSS/graph.json","events_json":"https://pith.science/api/pith-number/M77K7C6EGWN5VIAIIBDCXYVKSS/events.json","paper":"https://pith.science/paper/M77K7C6E"},"agent_actions":{"view_html":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS","download_json":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS.json","view_paper":"https://pith.science/paper/M77K7C6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13013&json=true","fetch_graph":"https://pith.science/api/pith-number/M77K7C6EGWN5VIAIIBDCXYVKSS/graph.json","fetch_events":"https://pith.science/api/pith-number/M77K7C6EGWN5VIAIIBDCXYVKSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS/action/storage_attestation","attest_author":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS/action/author_attestation","sign_citation":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS/action/citation_signature","submit_replication":"https://pith.science/pith/M77K7C6EGWN5VIAIIBDCXYVKSS/action/replication_record"}},"created_at":"2026-07-05T11:55:30.883408+00:00","updated_at":"2026-07-05T11:55:30.883408+00:00"}