{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AJ7GNQSQ5AFWZOYM54TDXWCINT","short_pith_number":"pith:AJ7GNQSQ","schema_version":"1.0","canonical_sha256":"027e66c250e80b6cbb0cef263bd8486cca905c58e553e0343c7edb5b9f59abc2","source":{"kind":"arxiv","id":"2503.21457","version":1},"attestation_state":"computed","paper":{"title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junliang Chen, Linlin Shen, Meidan Ding, Wenting Chen, Xianxu Hou, Xiaoqin Wang, Xiaoyang Peng, Xusen Ma, Yudong Li","submitted_at":"2025-03-27T12:45:44Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the str"},"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":"2503.21457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T12:45:44Z","cross_cats_sorted":[],"title_canon_sha256":"60b6208c013596a90a359104399e1fc0c5aa28f347a201b3509b814328ccfd8c","abstract_canon_sha256":"34fd9de2b5127998f207372e0c75fe7cc5a441b24c59a15ea60e8cecf64e9d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:25.599307Z","signature_b64":"T5Dhem1Ftgc+1cQSVjUB6WumZlCEEyzSu7o9qwjK4dmT5xXlKPyPTfb3JWx8MvYd5VUSGPzdah9ReLHupIUUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027e66c250e80b6cbb0cef263bd8486cca905c58e553e0343c7edb5b9f59abc2","last_reissued_at":"2026-07-05T10:40:25.598764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:25.598764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junliang Chen, Linlin Shen, Meidan Ding, Wenting Chen, Xianxu Hou, Xiaoqin Wang, Xiaoyang Peng, Xusen Ma, Yudong Li","submitted_at":"2025-03-27T12:45:44Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21457","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/2503.21457/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":"2503.21457","created_at":"2026-07-05T10:40:25.598843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21457v1","created_at":"2026-07-05T10:40:25.598843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21457","created_at":"2026-07-05T10:40:25.598843+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ7GNQSQ5AFW","created_at":"2026-07-05T10:40:25.598843+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ7GNQSQ5AFWZOYM","created_at":"2026-07-05T10:40:25.598843+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ7GNQSQ","created_at":"2026-07-05T10:40:25.598843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03470","citing_title":"Mixed-Modality Dual Face-Hair Retrieval","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT","json":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT.json","graph_json":"https://pith.science/api/pith-number/AJ7GNQSQ5AFWZOYM54TDXWCINT/graph.json","events_json":"https://pith.science/api/pith-number/AJ7GNQSQ5AFWZOYM54TDXWCINT/events.json","paper":"https://pith.science/paper/AJ7GNQSQ"},"agent_actions":{"view_html":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT","download_json":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT.json","view_paper":"https://pith.science/paper/AJ7GNQSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21457&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ7GNQSQ5AFWZOYM54TDXWCINT/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ7GNQSQ5AFWZOYM54TDXWCINT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT/action/storage_attestation","attest_author":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT/action/author_attestation","sign_citation":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT/action/citation_signature","submit_replication":"https://pith.science/pith/AJ7GNQSQ5AFWZOYM54TDXWCINT/action/replication_record"}},"created_at":"2026-07-05T10:40:25.598843+00:00","updated_at":"2026-07-05T10:40:25.598843+00:00"}