{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WJWPJX5PQTGQ2RQC72B45P7PH","short_pith_number":"pith:5WJWPJX5","schema_version":"1.0","canonical_sha256":"ed9367a6fd7c26686a3017f41e75ff79c56c6ee61b75377476a46b0e3551b301","source":{"kind":"arxiv","id":"2404.01294","version":1},"attestation_state":"computed","paper":{"title":"CosmicMan: A Text-to-Image Foundation Model for Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianglin Fu, Kaiyuan Liu, Kwan-Yee Lin, Shikai Li, Wayne Wu, Wentao Wang","submitted_at":"2024-04-01T17:59:05Z","abstract_excerpt":"We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions. At the heart of CosmicMan's success are the new reflections and perspectives on data and models: (1) We found that data quality and a scalable data production flow are essentia"},"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":"2404.01294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"9f849c9493fdf77f2b492ea2109d6a1d39123df3704d16cd3eac44fb51d23221","abstract_canon_sha256":"87cc31f440709fcb354405410179217c4be40552c2102f9ddd8d09c3bae4954a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:04.109955Z","signature_b64":"3aoArwJqpS35YWY8CwM3NVPLl5sRrE4H/O2/cLOeEuiB31+o242Jry7zCOpk7IAtrnRB40cIQiptkgSqjjZqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed9367a6fd7c26686a3017f41e75ff79c56c6ee61b75377476a46b0e3551b301","last_reissued_at":"2026-07-05T08:03:04.109468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:04.109468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CosmicMan: A Text-to-Image Foundation Model for Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianglin Fu, Kaiyuan Liu, Kwan-Yee Lin, Shikai Li, Wayne Wu, Wentao Wang","submitted_at":"2024-04-01T17:59:05Z","abstract_excerpt":"We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions. At the heart of CosmicMan's success are the new reflections and perspectives on data and models: (1) We found that data quality and a scalable data production flow are essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01294","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/2404.01294/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":"2404.01294","created_at":"2026-07-05T08:03:04.109530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01294v1","created_at":"2026-07-05T08:03:04.109530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01294","created_at":"2026-07-05T08:03:04.109530+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WJWPJX5PQTG","created_at":"2026-07-05T08:03:04.109530+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WJWPJX5PQTGQ2RQ","created_at":"2026-07-05T08:03:04.109530+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WJWPJX5","created_at":"2026-07-05T08:03:04.109530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02713","citing_title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH","json":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH.json","graph_json":"https://pith.science/api/pith-number/5WJWPJX5PQTGQ2RQC72B45P7PH/graph.json","events_json":"https://pith.science/api/pith-number/5WJWPJX5PQTGQ2RQC72B45P7PH/events.json","paper":"https://pith.science/paper/5WJWPJX5"},"agent_actions":{"view_html":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH","download_json":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH.json","view_paper":"https://pith.science/paper/5WJWPJX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01294&json=true","fetch_graph":"https://pith.science/api/pith-number/5WJWPJX5PQTGQ2RQC72B45P7PH/graph.json","fetch_events":"https://pith.science/api/pith-number/5WJWPJX5PQTGQ2RQC72B45P7PH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH/action/storage_attestation","attest_author":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH/action/author_attestation","sign_citation":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH/action/citation_signature","submit_replication":"https://pith.science/pith/5WJWPJX5PQTGQ2RQC72B45P7PH/action/replication_record"}},"created_at":"2026-07-05T08:03:04.109530+00:00","updated_at":"2026-07-05T08:03:04.109530+00:00"}