{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JGYXKL6EGNYVV57IDR3OQHGUX6","short_pith_number":"pith:JGYXKL6E","canonical_record":{"source":{"id":"2410.20717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:19:32Z","cross_cats_sorted":[],"title_canon_sha256":"ee9896a6eb632211c6e6dc196d0481b562ad0951094526e2ce478f826481fd09","abstract_canon_sha256":"c90a7c4a7a4347c1a64e54c91f618771be680b385c9cfb79765a125d6e86b217"},"schema_version":"1.0"},"canonical_sha256":"49b1752fc433715af7e81c76e81cd4bf84f9c8adfb91a8b4d9055d53004aead0","source":{"kind":"arxiv","id":"2410.20717","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JGYXKL6EGNYVV57IDR3OQHGUX6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:19:32Z","cross_cats_sorted":[],"title_canon_sha256":"ee9896a6eb632211c6e6dc196d0481b562ad0951094526e2ce478f826481fd09","abstract_canon_sha256":"c90a7c4a7a4347c1a64e54c91f618771be680b385c9cfb79765a125d6e86b217"},"schema_version":"1.0"},"canonical_sha256":"49b1752fc433715af7e81c76e81cd4bf84f9c8adfb91a8b4d9055d53004aead0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:09.898023Z","signature_b64":"DhvfuRFvbn3QPFQNe6RnUc/lcMwrKJtbXHzIxndrCyN5oU0CaJDYZALgnX4WIEwV6eIFY4jDQ3E6Gwp6jAtaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b1752fc433715af7e81c76e81cd4bf84f9c8adfb91a8b4d9055d53004aead0","last_reissued_at":"2026-07-05T09:27:09.897565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:09.897565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20717","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dsu+8WOEJu5vHUgG1UrPMXJG6YSC49MZ3RuyoBx1iootb4v9G46o/a08W0A562leSWPkrrptAgZ4Hb0lX2FqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:09:14.739498Z"},"content_sha256":"fdba10f520ec7fbede7e85640ab9161272b4a586fdebb924d9fc02012ed17c52","schema_version":"1.0","event_id":"sha256:fdba10f520ec7fbede7e85640ab9161272b4a586fdebb924d9fc02012ed17c52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JGYXKL6EGNYVV57IDR3OQHGUX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Face-MLLM: A Large Face Perception Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haomiao Sun, Hu Han, Mingjie He, Shiguang Shan, Tianheng Lian","submitted_at":"2024-10-28T04:19:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20717","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/2410.20717/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJLx8cs0g2eAuuwkotgBljq0P5xRN/5eOLS2HtU2F8NbP4EIRHYJ+fDTTpnS2fjAX3hdifBtiLSHj+BkT7CLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:09:14.740018Z"},"content_sha256":"918ff27b3c8d400ac802226f8d352fc276dd176f85e8c0cba64afdc2fc240421","schema_version":"1.0","event_id":"sha256:918ff27b3c8d400ac802226f8d352fc276dd176f85e8c0cba64afdc2fc240421"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/bundle.json","state_url":"https://pith.science/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T14:09:14Z","links":{"resolver":"https://pith.science/pith/JGYXKL6EGNYVV57IDR3OQHGUX6","bundle":"https://pith.science/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/bundle.json","state":"https://pith.science/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGYXKL6EGNYVV57IDR3OQHGUX6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ml62ibjgj6TSG/6nOiH+fvGjz0d0Vw5caFTvN2ESaN8n7H5VNaRc1cjFIRTOA/Q6jI5qqDqRgObpd5Kr3LsBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:09:14.745686Z","bundle_sha256":"d0e8d7f057a991b32e6082d546a0c74cdacc9175b013ce3f78a4bcb9c960d92e"}}