{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CTXBW7A6IGSKNLROV4YAN6QJZJ","short_pith_number":"pith:CTXBW7A6","schema_version":"1.0","canonical_sha256":"14ee1b7c1e41a4a6ae2eaf3006fa09ca4ec0297ffc14b3b8efd36827c9bec3be","source":{"kind":"arxiv","id":"2503.23907","version":2},"attestation_state":"computed","paper":{"title":"HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Long Zeng, Pengfei Wan, Pingfa Feng, Qingyu Li, Qiulin Wang, Wenyu Qin, Xiaokun Liu, Zhichao Liao","submitted_at":"2025-03-31T09:58:11Z","abstract_excerpt":"Image Aesthetic Assessment (IAA) is a long-standing and challenging research task. However, its subset, Human Image Aesthetic Assessment (HIAA), has been scarcely explored. To bridge this research gap, our work pioneers a holistic implementation framework tailored for HIAA. Specifically, we introduce HumanBeauty, the first dataset purpose-built for HIAA, which comprises 108k high-quality human images with manual annotations. To achieve comprehensive and fine-grained HIAA, 50K human images are manually collected through a rigorous curation process and annotated leveraging our trailblazing 12-di"},"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":"2503.23907","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:58:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7aa0d59c36b4eaae302bde083b748873104c15b2a921fbc29004cc6d5877c65a","abstract_canon_sha256":"60f9e3ce5a78b6e1dea24b5bbf48658c1cf5e162cfaa0a7eb04b9939178de09a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:55.186178Z","signature_b64":"bQZuf/ZTwYdEtUfqkF1jwDhR6OK7nD6SXx8jG7F9eGX1GECVuN6gGz26kJ2R9wk5oLxBvbiimeE2szQJHpI2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14ee1b7c1e41a4a6ae2eaf3006fa09ca4ec0297ffc14b3b8efd36827c9bec3be","last_reissued_at":"2026-07-05T11:10:55.185657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:55.185657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Long Zeng, Pengfei Wan, Pingfa Feng, Qingyu Li, Qiulin Wang, Wenyu Qin, Xiaokun Liu, Zhichao Liao","submitted_at":"2025-03-31T09:58:11Z","abstract_excerpt":"Image Aesthetic Assessment (IAA) is a long-standing and challenging research task. However, its subset, Human Image Aesthetic Assessment (HIAA), has been scarcely explored. To bridge this research gap, our work pioneers a holistic implementation framework tailored for HIAA. Specifically, we introduce HumanBeauty, the first dataset purpose-built for HIAA, which comprises 108k high-quality human images with manual annotations. To achieve comprehensive and fine-grained HIAA, 50K human images are manually collected through a rigorous curation process and annotated leveraging our trailblazing 12-di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23907","kind":"arxiv","version":2},"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/2503.23907/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":"2503.23907","created_at":"2026-07-05T11:10:55.185732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23907v2","created_at":"2026-07-05T11:10:55.185732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23907","created_at":"2026-07-05T11:10:55.185732+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTXBW7A6IGSK","created_at":"2026-07-05T11:10:55.185732+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTXBW7A6IGSKNLRO","created_at":"2026-07-05T11:10:55.185732+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTXBW7A6","created_at":"2026-07-05T11:10:55.185732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26930","citing_title":"PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07561","citing_title":"PureCC: Pure Learning for Text-to-Image Concept Customization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14635","citing_title":"MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19636","citing_title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ","json":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ.json","graph_json":"https://pith.science/api/pith-number/CTXBW7A6IGSKNLROV4YAN6QJZJ/graph.json","events_json":"https://pith.science/api/pith-number/CTXBW7A6IGSKNLROV4YAN6QJZJ/events.json","paper":"https://pith.science/paper/CTXBW7A6"},"agent_actions":{"view_html":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ","download_json":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ.json","view_paper":"https://pith.science/paper/CTXBW7A6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23907&json=true","fetch_graph":"https://pith.science/api/pith-number/CTXBW7A6IGSKNLROV4YAN6QJZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CTXBW7A6IGSKNLROV4YAN6QJZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ/action/storage_attestation","attest_author":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ/action/author_attestation","sign_citation":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ/action/citation_signature","submit_replication":"https://pith.science/pith/CTXBW7A6IGSKNLROV4YAN6QJZJ/action/replication_record"}},"created_at":"2026-07-05T11:10:55.185732+00:00","updated_at":"2026-07-05T11:10:55.185732+00:00"}