{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IILFVPSSGADV6O7DLPAXL3XGXQ","short_pith_number":"pith:IILFVPSS","schema_version":"1.0","canonical_sha256":"42165abe5230075f3be35bc175eee6bc1eba2fd129ac4c6834078474b335509c","source":{"kind":"arxiv","id":"2504.15624","version":2},"attestation_state":"computed","paper":{"title":"FaceInsight: A Multimodal Large Language Model for Face Perception","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjiang Luo, Hua Zhang, Jianhou Gan, Jingzhi Li, Ruoyu Chen, Wenqi Ren, Xiaochun Cao","submitted_at":"2025-04-22T06:31:57Z","abstract_excerpt":"Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing inaccurate or misleading responses to face-specific queries. To address this gap, we propose FaceInsight, the versatile face perception MLLM that provides fine-grained facial information. Our approach introduces visual-textual alignment of facial knowledge to model both uncertain dependencies and deterministic relationships among facial information, mitigating the l"},"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":"2504.15624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T06:31:57Z","cross_cats_sorted":[],"title_canon_sha256":"25513f16ed379e7d96a98ea863eda3d5e8ee2288b31d4ccdc09406560333e69e","abstract_canon_sha256":"661020e4af464b798c29bed15ff100da68fc647e4dd4471b92ec4b0d2df90c4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:16.566470Z","signature_b64":"i200Kl8XE7jLkLbSb75CvuTGXQTbM2o3CTxmE+I+5KcqDIoC85CsNtPAVUKjEkbePYIypU3aoqVRS5ONqrQKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42165abe5230075f3be35bc175eee6bc1eba2fd129ac4c6834078474b335509c","last_reissued_at":"2026-07-05T10:54:16.565925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:16.565925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceInsight: A Multimodal Large Language Model for Face Perception","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjiang Luo, Hua Zhang, Jianhou Gan, Jingzhi Li, Ruoyu Chen, Wenqi Ren, Xiaochun Cao","submitted_at":"2025-04-22T06:31:57Z","abstract_excerpt":"Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing inaccurate or misleading responses to face-specific queries. To address this gap, we propose FaceInsight, the versatile face perception MLLM that provides fine-grained facial information. Our approach introduces visual-textual alignment of facial knowledge to model both uncertain dependencies and deterministic relationships among facial information, mitigating the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15624","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/2504.15624/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":"2504.15624","created_at":"2026-07-05T10:54:16.565996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15624v2","created_at":"2026-07-05T10:54:16.565996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15624","created_at":"2026-07-05T10:54:16.565996+00:00"},{"alias_kind":"pith_short_12","alias_value":"IILFVPSSGADV","created_at":"2026-07-05T10:54:16.565996+00:00"},{"alias_kind":"pith_short_16","alias_value":"IILFVPSSGADV6O7D","created_at":"2026-07-05T10:54:16.565996+00:00"},{"alias_kind":"pith_short_8","alias_value":"IILFVPSS","created_at":"2026-07-05T10:54:16.565996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ","json":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ.json","graph_json":"https://pith.science/api/pith-number/IILFVPSSGADV6O7DLPAXL3XGXQ/graph.json","events_json":"https://pith.science/api/pith-number/IILFVPSSGADV6O7DLPAXL3XGXQ/events.json","paper":"https://pith.science/paper/IILFVPSS"},"agent_actions":{"view_html":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ","download_json":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ.json","view_paper":"https://pith.science/paper/IILFVPSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15624&json=true","fetch_graph":"https://pith.science/api/pith-number/IILFVPSSGADV6O7DLPAXL3XGXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IILFVPSSGADV6O7DLPAXL3XGXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ/action/storage_attestation","attest_author":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ/action/author_attestation","sign_citation":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ/action/citation_signature","submit_replication":"https://pith.science/pith/IILFVPSSGADV6O7DLPAXL3XGXQ/action/replication_record"}},"created_at":"2026-07-05T10:54:16.565996+00:00","updated_at":"2026-07-05T10:54:16.565996+00:00"}