{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DRQF42MAJXS6B42HFGFFVVNMRM","short_pith_number":"pith:DRQF42MA","schema_version":"1.0","canonical_sha256":"1c605e69804de5e0f347298a5ad5ac8b22e3ec622ede095e7d47448dbcf46b32","source":{"kind":"arxiv","id":"2502.08556","version":1},"attestation_state":"computed","paper":{"title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Lu Chen, Shixiang Tang, Sida Peng, Wanli Ouyang, Yizhou Wang, Yuan Wang","submitted_at":"2025-02-12T16:38:40Z","abstract_excerpt":"Human understanding and generation are critical for modeling digital humans and humanoid embodiments. Recently, Human-centric Foundation Models (HcFMs) inspired by the success of generalist models, such as large language and vision models, have emerged to unify diverse human-centric tasks into a single framework, surpassing traditional task-specific approaches. In this survey, we present a comprehensive overview of HcFMs by proposing a taxonomy that categorizes current approaches into four groups: (1) Human-centric Perception Foundation Models that capture fine-grained features for multi-modal"},"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":"2502.08556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T16:38:40Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"af0e20b25530cac3ef159b613ad9fea87b354f3b87735c54fa1f2be615ef21ca","abstract_canon_sha256":"83da948f9528deff13ed61d5610256cf0f77caadc7d5ce3c8329483643bcd080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:24.679753Z","signature_b64":"+znc0atAyhkQ3xTS/3m7/Gcwh36mFuE8PezRhuIkF9yz00y+KaBAOes7Jq3EyQ7Um+3Bv0gIeM55URVUsIXvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c605e69804de5e0f347298a5ad5ac8b22e3ec622ede095e7d47448dbcf46b32","last_reissued_at":"2026-07-05T10:13:24.679238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:24.679238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Lu Chen, Shixiang Tang, Sida Peng, Wanli Ouyang, Yizhou Wang, Yuan Wang","submitted_at":"2025-02-12T16:38:40Z","abstract_excerpt":"Human understanding and generation are critical for modeling digital humans and humanoid embodiments. Recently, Human-centric Foundation Models (HcFMs) inspired by the success of generalist models, such as large language and vision models, have emerged to unify diverse human-centric tasks into a single framework, surpassing traditional task-specific approaches. In this survey, we present a comprehensive overview of HcFMs by proposing a taxonomy that categorizes current approaches into four groups: (1) Human-centric Perception Foundation Models that capture fine-grained features for multi-modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08556","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/2502.08556/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":"2502.08556","created_at":"2026-07-05T10:13:24.679310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08556v1","created_at":"2026-07-05T10:13:24.679310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08556","created_at":"2026-07-05T10:13:24.679310+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRQF42MAJXS6","created_at":"2026-07-05T10:13:24.679310+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRQF42MAJXS6B42H","created_at":"2026-07-05T10:13:24.679310+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRQF42MA","created_at":"2026-07-05T10:13:24.679310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10127","citing_title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM","json":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM.json","graph_json":"https://pith.science/api/pith-number/DRQF42MAJXS6B42HFGFFVVNMRM/graph.json","events_json":"https://pith.science/api/pith-number/DRQF42MAJXS6B42HFGFFVVNMRM/events.json","paper":"https://pith.science/paper/DRQF42MA"},"agent_actions":{"view_html":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM","download_json":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM.json","view_paper":"https://pith.science/paper/DRQF42MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08556&json=true","fetch_graph":"https://pith.science/api/pith-number/DRQF42MAJXS6B42HFGFFVVNMRM/graph.json","fetch_events":"https://pith.science/api/pith-number/DRQF42MAJXS6B42HFGFFVVNMRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM/action/storage_attestation","attest_author":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM/action/author_attestation","sign_citation":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM/action/citation_signature","submit_replication":"https://pith.science/pith/DRQF42MAJXS6B42HFGFFVVNMRM/action/replication_record"}},"created_at":"2026-07-05T10:13:24.679310+00:00","updated_at":"2026-07-05T10:13:24.679310+00:00"}