{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GTLMDQNFSJNYXTIAOGF33E7JKX","short_pith_number":"pith:GTLMDQNF","schema_version":"1.0","canonical_sha256":"34d6c1c1a5925b8bcd00718bbd93e955e1ab1ecb6a1e8ca24efe3757f4ae988c","source":{"kind":"arxiv","id":"2508.09858","version":1},"attestation_state":"computed","paper":{"title":"HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangrun Wang, Liang Lin, Weiqi Li, Zehao Zhang","submitted_at":"2025-08-13T14:50:19Z","abstract_excerpt":"\\textbf{Synthetic human dynamics} aims to generate photorealistic videos of human subjects performing expressive, intention-driven motions. However, current approaches face two core challenges: (1) \\emph{geometric inconsistency} and \\emph{coarse reconstruction}, due to limited 3D modeling and detail preservation; and (2) \\emph{motion generalization limitations} and \\emph{scene inharmonization}, stemming from weak generative capabilities. To address these, we present \\textbf{HumanGenesis}, a framework that integrates geometric and generative modeling through four collaborative agents: (1) \\text"},"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":"2508.09858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-13T14:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"517cef7a8d3839546a5f33bee975f89960b91b44854742cff271703a34ca070d","abstract_canon_sha256":"9c6df494659f15ae039c904967b86d7231906c472875a2ce20996c7558effc31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:23.276098Z","signature_b64":"CYyLt+WVgf/q/35AWXfflUgRKHl6BL/eLx8XxuICcYWsbmVpWyPT7fNxmAdovUW0xBw+YO965zHvZ4fd+kmhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d6c1c1a5925b8bcd00718bbd93e955e1ab1ecb6a1e8ca24efe3757f4ae988c","last_reissued_at":"2026-07-05T11:53:23.275563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:23.275563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangrun Wang, Liang Lin, Weiqi Li, Zehao Zhang","submitted_at":"2025-08-13T14:50:19Z","abstract_excerpt":"\\textbf{Synthetic human dynamics} aims to generate photorealistic videos of human subjects performing expressive, intention-driven motions. However, current approaches face two core challenges: (1) \\emph{geometric inconsistency} and \\emph{coarse reconstruction}, due to limited 3D modeling and detail preservation; and (2) \\emph{motion generalization limitations} and \\emph{scene inharmonization}, stemming from weak generative capabilities. To address these, we present \\textbf{HumanGenesis}, a framework that integrates geometric and generative modeling through four collaborative agents: (1) \\text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09858","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/2508.09858/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":"2508.09858","created_at":"2026-07-05T11:53:23.275625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09858v1","created_at":"2026-07-05T11:53:23.275625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09858","created_at":"2026-07-05T11:53:23.275625+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTLMDQNFSJNY","created_at":"2026-07-05T11:53:23.275625+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTLMDQNFSJNYXTIA","created_at":"2026-07-05T11:53:23.275625+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTLMDQNF","created_at":"2026-07-05T11:53:23.275625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX","json":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX.json","graph_json":"https://pith.science/api/pith-number/GTLMDQNFSJNYXTIAOGF33E7JKX/graph.json","events_json":"https://pith.science/api/pith-number/GTLMDQNFSJNYXTIAOGF33E7JKX/events.json","paper":"https://pith.science/paper/GTLMDQNF"},"agent_actions":{"view_html":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX","download_json":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX.json","view_paper":"https://pith.science/paper/GTLMDQNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09858&json=true","fetch_graph":"https://pith.science/api/pith-number/GTLMDQNFSJNYXTIAOGF33E7JKX/graph.json","fetch_events":"https://pith.science/api/pith-number/GTLMDQNFSJNYXTIAOGF33E7JKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX/action/storage_attestation","attest_author":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX/action/author_attestation","sign_citation":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX/action/citation_signature","submit_replication":"https://pith.science/pith/GTLMDQNFSJNYXTIAOGF33E7JKX/action/replication_record"}},"created_at":"2026-07-05T11:53:23.275625+00:00","updated_at":"2026-07-05T11:53:23.275625+00:00"}