{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBBNEEB4WS6NZPLDS7MRXTEFVD","short_pith_number":"pith:CBBNEEB4","schema_version":"1.0","canonical_sha256":"1042d2103cb4bcdcbd6397d91bcc85a8fd346d2def306ee25c6055c1e6ba3a86","source":{"kind":"arxiv","id":"2407.08515","version":2},"attestation_state":"computed","paper":{"title":"15M Multimodal Facial Image-Text Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dawei Dai, Guoyin Wang, Mingming Jia, Yingge Liu, Yutang Li, Zhang YuanHui","submitted_at":"2024-07-11T14:00:14Z","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"},"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":"2407.08515","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T14:00:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3b72d857dcf1d91e4710d79e6e3b8f4970e9225c7ae2ae44aa27e8c9f775a25","abstract_canon_sha256":"c999d16b1556d063e91ce74ec2e256a51501f483c551d188b4ffa3789afd3acc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:55.471668Z","signature_b64":"3fnOSdaAFfETcM1pyjy1asfKOkQ7Wp1Aqoaj9ci7k+jj8297PPZt0plrKO4wzi3YMFiJLMUuKmEyRvi07bgAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1042d2103cb4bcdcbd6397d91bcc85a8fd346d2def306ee25c6055c1e6ba3a86","last_reissued_at":"2026-07-05T08:42:55.471212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:55.471212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"15M Multimodal Facial Image-Text Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dawei Dai, Guoyin Wang, Mingming Jia, Yingge Liu, Yutang Li, Zhang YuanHui","submitted_at":"2024-07-11T14:00:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08515","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/2407.08515/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":"2407.08515","created_at":"2026-07-05T08:42:55.471275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08515v2","created_at":"2026-07-05T08:42:55.471275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08515","created_at":"2026-07-05T08:42:55.471275+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBBNEEB4WS6N","created_at":"2026-07-05T08:42:55.471275+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBBNEEB4WS6NZPLD","created_at":"2026-07-05T08:42:55.471275+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBBNEEB4","created_at":"2026-07-05T08:42:55.471275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD","json":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD.json","graph_json":"https://pith.science/api/pith-number/CBBNEEB4WS6NZPLDS7MRXTEFVD/graph.json","events_json":"https://pith.science/api/pith-number/CBBNEEB4WS6NZPLDS7MRXTEFVD/events.json","paper":"https://pith.science/paper/CBBNEEB4"},"agent_actions":{"view_html":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD","download_json":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD.json","view_paper":"https://pith.science/paper/CBBNEEB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08515&json=true","fetch_graph":"https://pith.science/api/pith-number/CBBNEEB4WS6NZPLDS7MRXTEFVD/graph.json","fetch_events":"https://pith.science/api/pith-number/CBBNEEB4WS6NZPLDS7MRXTEFVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD/action/storage_attestation","attest_author":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD/action/author_attestation","sign_citation":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD/action/citation_signature","submit_replication":"https://pith.science/pith/CBBNEEB4WS6NZPLDS7MRXTEFVD/action/replication_record"}},"created_at":"2026-07-05T08:42:55.471275+00:00","updated_at":"2026-07-05T08:42:55.471275+00:00"}