{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CBBNEEB4WS6NZPLDS7MRXTEFVD","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":"c999d16b1556d063e91ce74ec2e256a51501f483c551d188b4ffa3789afd3acc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T14:00:14Z","title_canon_sha256":"f3b72d857dcf1d91e4710d79e6e3b8f4970e9225c7ae2ae44aa27e8c9f775a25"},"schema_version":"1.0","source":{"id":"2407.08515","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08515","created_at":"2026-07-05T08:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08515v2","created_at":"2026-07-05T08:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08515","created_at":"2026-07-05T08:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"CBBNEEB4WS6N","created_at":"2026-07-05T08:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"CBBNEEB4WS6NZPLD","created_at":"2026-07-05T08:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"CBBNEEB4","created_at":"2026-07-05T08:42:55Z"}],"graph_snapshots":[{"event_id":"sha256:8b73d7070d6f73e4f8bf43b381847b9ca4b7834813da84c13dfc206751f0099e","target":"graph","created_at":"2026-07-05T08:42:55Z","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/2407.08515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, image-text-driven multi-modal deep learning models have demonstrated their outstanding potential in many fields. In practice, tasks centered around facial images have broad application prospects. This paper presents \\textbf{FaceCaption-15M}, a large-scale, diverse, and high-quality dataset of facial images accompanied by their natural language descriptions (facial image-to-text). This dataset aims to facilitate a study on face-centered tasks. FaceCaption-15M comprises over 15 million pairs of facial images and their corresponding natural language descriptions of facial features, mak","authors_text":"Dawei Dai, Guoyin Wang, Mingming Jia, Yingge Liu, Yutang Li, Zhang YuanHui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T14:00:14Z","title":"15M Multimodal Facial Image-Text Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08515","kind":"arxiv","version":2},"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":"sha256:9360a1333ed99b427648ec196845d0b5e6348627d26d9a12b0a728885b82620a","target":"record","created_at":"2026-07-05T08:42:55Z","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":"c999d16b1556d063e91ce74ec2e256a51501f483c551d188b4ffa3789afd3acc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T14:00:14Z","title_canon_sha256":"f3b72d857dcf1d91e4710d79e6e3b8f4970e9225c7ae2ae44aa27e8c9f775a25"},"schema_version":"1.0","source":{"id":"2407.08515","kind":"arxiv","version":2}},"canonical_sha256":"1042d2103cb4bcdcbd6397d91bcc85a8fd346d2def306ee25c6055c1e6ba3a86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1042d2103cb4bcdcbd6397d91bcc85a8fd346d2def306ee25c6055c1e6ba3a86","first_computed_at":"2026-07-05T08:42:55.471212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:55.471212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3fnOSdaAFfETcM1pyjy1asfKOkQ7Wp1Aqoaj9ci7k+jj8297PPZt0plrKO4wzi3YMFiJLMUuKmEyRvi07bgAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:55.471668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08515","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9360a1333ed99b427648ec196845d0b5e6348627d26d9a12b0a728885b82620a","sha256:8b73d7070d6f73e4f8bf43b381847b9ca4b7834813da84c13dfc206751f0099e"],"state_sha256":"f83291b7c67baa787589c3424c393d2c5fd3b356e2ef2dd9ac7e3d6c705a642c"}