{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GPPIJ3QGXLOT2IBWLO6ISFU5L","short_pith_number":"pith:3GPPIJ3Q","schema_version":"1.0","canonical_sha256":"d99ef4277035d6e9e901b2dde448b4eadc4d89712983872b86f9518579c3f877","source":{"kind":"arxiv","id":"2406.10328","version":1},"attestation_state":"computed","paper":{"title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Bhatele, Alireza Ganjdanesh, Gowthami Somepalli, Heng Huang, Kaiyu Yue, Mayuka Jayawardhana, Reza Shirkavand, Sukriti Paul, Tom Goldstein, Vasu Singla","submitted_at":"2024-06-14T17:59:53Z","abstract_excerpt":"Training large vision-language models requires extensive, high-quality image-text pairs. Existing web-scraped datasets, however, are noisy and lack detailed image descriptions. To bridge this gap, we introduce PixelProse, a comprehensive dataset of over 16M (million) synthetically generated captions, leveraging cutting-edge vision-language models for detailed and accurate descriptions. To ensure data integrity, we rigorously analyze our dataset for problematic content, including child sexual abuse material (CSAM), personally identifiable information (PII), and toxicity. We also provide valuabl"},"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":"2406.10328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:53Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9101b6e363971b9f824244a4565251bababc329203b32fa6e784d4d28dd87f0c","abstract_canon_sha256":"48c0494e916317f94efa2065b094402929485ab003914df616ee47f0b1ab2378"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:15.093761Z","signature_b64":"YmrFY4mfEA+QtvEnCveZy9r+hj8v9O7GBbg+AGNu8cwOb2r/uGptueEt5i0vKU+h26QFlcNq5T9s7ObJyiSRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99ef4277035d6e9e901b2dde448b4eadc4d89712983872b86f9518579c3f877","last_reissued_at":"2026-07-05T08:32:15.093260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:15.093260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Bhatele, Alireza Ganjdanesh, Gowthami Somepalli, Heng Huang, Kaiyu Yue, Mayuka Jayawardhana, Reza Shirkavand, Sukriti Paul, Tom Goldstein, Vasu Singla","submitted_at":"2024-06-14T17:59:53Z","abstract_excerpt":"Training large vision-language models requires extensive, high-quality image-text pairs. Existing web-scraped datasets, however, are noisy and lack detailed image descriptions. To bridge this gap, we introduce PixelProse, a comprehensive dataset of over 16M (million) synthetically generated captions, leveraging cutting-edge vision-language models for detailed and accurate descriptions. To ensure data integrity, we rigorously analyze our dataset for problematic content, including child sexual abuse material (CSAM), personally identifiable information (PII), and toxicity. We also provide valuabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10328","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/2406.10328/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":"2406.10328","created_at":"2026-07-05T08:32:15.093311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10328v1","created_at":"2026-07-05T08:32:15.093311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10328","created_at":"2026-07-05T08:32:15.093311+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GPPIJ3QGXLO","created_at":"2026-07-05T08:32:15.093311+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GPPIJ3QGXLOT2IB","created_at":"2026-07-05T08:32:15.093311+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GPPIJ3Q","created_at":"2026-07-05T08:32:15.093311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28023","citing_title":"VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21728","citing_title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18115","citing_title":"WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L","json":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L.json","graph_json":"https://pith.science/api/pith-number/3GPPIJ3QGXLOT2IBWLO6ISFU5L/graph.json","events_json":"https://pith.science/api/pith-number/3GPPIJ3QGXLOT2IBWLO6ISFU5L/events.json","paper":"https://pith.science/paper/3GPPIJ3Q"},"agent_actions":{"view_html":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L","download_json":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L.json","view_paper":"https://pith.science/paper/3GPPIJ3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10328&json=true","fetch_graph":"https://pith.science/api/pith-number/3GPPIJ3QGXLOT2IBWLO6ISFU5L/graph.json","fetch_events":"https://pith.science/api/pith-number/3GPPIJ3QGXLOT2IBWLO6ISFU5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L/action/storage_attestation","attest_author":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L/action/author_attestation","sign_citation":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L/action/citation_signature","submit_replication":"https://pith.science/pith/3GPPIJ3QGXLOT2IBWLO6ISFU5L/action/replication_record"}},"created_at":"2026-07-05T08:32:15.093311+00:00","updated_at":"2026-07-05T08:32:15.093311+00:00"}