{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T6C3J4VRVT67RJ6TWG2LSYU5PE","short_pith_number":"pith:T6C3J4VR","schema_version":"1.0","canonical_sha256":"9f85b4f2b1acfdf8a7d3b1b4b9629d791642d2cd461db74a921324f91a3112eb","source":{"kind":"arxiv","id":"2407.08428","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fengji Ma, Guanjie Huang, Jinting Wang, Li Liu, Wentao Lei","submitted_at":"2024-07-11T12:09:05Z","abstract_excerpt":"Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. With the potential for wide-ranging applications in film, gaming, and virtual communication, the ability to generate natural and realistic human video is critical. Recent advancements in generative models have laid a solid foundation for the growing interest in this area. Despite the significant progress, the task of human video generation remains challenging due to the consistency of characters, the c"},"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":"2407.08428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T12:09:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a593e155daf2abc4b6466aff36d9ca2eb758f3e4f7d40918724f79af560aee48","abstract_canon_sha256":"2787fb2e3976e93663517f134e187c756bc266cb87e93d872d7979eca8eba7e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:48.332925Z","signature_b64":"68kK8PIP52fw3Jp/McGvuotqk2EHQtndu4gkFXWeyRBiHt7tQfsFAYUOAY/D6Gk5pQaZ1iShJfg9knFCEjeMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f85b4f2b1acfdf8a7d3b1b4b9629d791642d2cd461db74a921324f91a3112eb","last_reissued_at":"2026-07-05T08:42:48.332403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:48.332403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fengji Ma, Guanjie Huang, Jinting Wang, Li Liu, Wentao Lei","submitted_at":"2024-07-11T12:09:05Z","abstract_excerpt":"Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. With the potential for wide-ranging applications in film, gaming, and virtual communication, the ability to generate natural and realistic human video is critical. Recent advancements in generative models have laid a solid foundation for the growing interest in this area. Despite the significant progress, the task of human video generation remains challenging due to the consistency of characters, the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08428","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/2407.08428/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":"2407.08428","created_at":"2026-07-05T08:42:48.332469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08428v1","created_at":"2026-07-05T08:42:48.332469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08428","created_at":"2026-07-05T08:42:48.332469+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6C3J4VRVT67","created_at":"2026-07-05T08:42:48.332469+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6C3J4VRVT67RJ6T","created_at":"2026-07-05T08:42:48.332469+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6C3J4VR","created_at":"2026-07-05T08:42:48.332469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05994","citing_title":"SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05961","citing_title":"HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE","json":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE.json","graph_json":"https://pith.science/api/pith-number/T6C3J4VRVT67RJ6TWG2LSYU5PE/graph.json","events_json":"https://pith.science/api/pith-number/T6C3J4VRVT67RJ6TWG2LSYU5PE/events.json","paper":"https://pith.science/paper/T6C3J4VR"},"agent_actions":{"view_html":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE","download_json":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE.json","view_paper":"https://pith.science/paper/T6C3J4VR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08428&json=true","fetch_graph":"https://pith.science/api/pith-number/T6C3J4VRVT67RJ6TWG2LSYU5PE/graph.json","fetch_events":"https://pith.science/api/pith-number/T6C3J4VRVT67RJ6TWG2LSYU5PE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE/action/storage_attestation","attest_author":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE/action/author_attestation","sign_citation":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE/action/citation_signature","submit_replication":"https://pith.science/pith/T6C3J4VRVT67RJ6TWG2LSYU5PE/action/replication_record"}},"created_at":"2026-07-05T08:42:48.332469+00:00","updated_at":"2026-07-05T08:42:48.332469+00:00"}