{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGYXKL6EGNYVV57IDR3OQHGUX6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c90a7c4a7a4347c1a64e54c91f618771be680b385c9cfb79765a125d6e86b217","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:19:32Z","title_canon_sha256":"ee9896a6eb632211c6e6dc196d0481b562ad0951094526e2ce478f826481fd09"},"schema_version":"1.0","source":{"id":"2410.20717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20717","created_at":"2026-07-05T09:27:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20717v1","created_at":"2026-07-05T09:27:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20717","created_at":"2026-07-05T09:27:09Z"},{"alias_kind":"pith_short_12","alias_value":"JGYXKL6EGNYV","created_at":"2026-07-05T09:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"JGYXKL6EGNYVV57I","created_at":"2026-07-05T09:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"JGYXKL6E","created_at":"2026-07-05T09:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:918ff27b3c8d400ac802226f8d352fc276dd176f85e8c0cba64afdc2fc240421","target":"graph","created_at":"2026-07-05T09:27:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.20717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although multimodal large language models (MLLMs) have achieved promising results on a wide range of vision-language tasks, their ability to perceive and understand human faces is rarely explored. In this work, we comprehensively evaluate existing MLLMs on face perception tasks. The quantitative results reveal that existing MLLMs struggle to handle these tasks. The primary reason is the lack of image-text datasets that contain fine-grained descriptions of human faces. To tackle this problem, we design a practical pipeline for constructing datasets, upon which we further build a novel multimoda","authors_text":"Haomiao Sun, Hu Han, Mingjie He, Shiguang Shan, Tianheng Lian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:19:32Z","title":"Face-MLLM: A Large Face Perception Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20717","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fdba10f520ec7fbede7e85640ab9161272b4a586fdebb924d9fc02012ed17c52","target":"record","created_at":"2026-07-05T09:27:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c90a7c4a7a4347c1a64e54c91f618771be680b385c9cfb79765a125d6e86b217","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:19:32Z","title_canon_sha256":"ee9896a6eb632211c6e6dc196d0481b562ad0951094526e2ce478f826481fd09"},"schema_version":"1.0","source":{"id":"2410.20717","kind":"arxiv","version":1}},"canonical_sha256":"49b1752fc433715af7e81c76e81cd4bf84f9c8adfb91a8b4d9055d53004aead0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b1752fc433715af7e81c76e81cd4bf84f9c8adfb91a8b4d9055d53004aead0","first_computed_at":"2026-07-05T09:27:09.897565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:09.897565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DhvfuRFvbn3QPFQNe6RnUc/lcMwrKJtbXHzIxndrCyN5oU0CaJDYZALgnX4WIEwV6eIFY4jDQ3E6Gwp6jAtaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:09.898023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdba10f520ec7fbede7e85640ab9161272b4a586fdebb924d9fc02012ed17c52","sha256:918ff27b3c8d400ac802226f8d352fc276dd176f85e8c0cba64afdc2fc240421"],"state_sha256":"f7bd1b227333406004b6c7e872492730e0fe8566f2c8fbee399385b95ed2ac71"}