{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IUHBZTYJV3H7ZJPIYIHSOPVJYS","short_pith_number":"pith:IUHBZTYJ","schema_version":"1.0","canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","source":{"kind":"arxiv","id":"2510.17269","version":2},"attestation_state":"computed","paper":{"title":"FineVision: Open Data Is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amir Mahla, Andr\\'es Marafioti, Aritra Roy Gosthipaty, Leandro Von Werra, Luis Wiedmann, Orr Zohar, Rui Li, Thibaud Frere, Xiaohan Wang","submitted_at":"2025-10-20T07:54:46Z","abstract_excerpt":"The advancement of vision-language models (VLMs) is hampered by a fragmented landscape of inconsistent and contaminated public datasets. We introduce FineVision, a meticulously collected, curated, and unified corpus of 24 million samples - the largest open resource of its kind. We unify more than 200 sources into 185 subsets via a semi-automated, human-in-the-loop pipeline: automation performs bulk ingestion and schema mapping, while reviewers audit mappings and spot-check outputs to verify faithful consumption of annotations, appropriate formatting and diversity, and safety; issues trigger ta"},"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":"2510.17269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T07:54:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c84309328e87d7ab5f3a0ba6f7d794e9ed436159a7772f01488738bd17313222","abstract_canon_sha256":"d4b3f0dd2f4317f9aab112e0ae65c2b3267ce1046cf1076f844d9e28a9d24845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:17.883806Z","signature_b64":"tdaaEFhw/UAqkYf2v/mxCNmJ1qsDt2Nik6tblD67YIZbg9JSerjv7HalMvw4AIWR2sEMuDGCZ03B0G0yA8TYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","last_reissued_at":"2026-05-21T01:04:17.882920Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:17.882920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineVision: Open Data Is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amir Mahla, Andr\\'es Marafioti, Aritra Roy Gosthipaty, Leandro Von Werra, Luis Wiedmann, Orr Zohar, Rui Li, Thibaud Frere, Xiaohan Wang","submitted_at":"2025-10-20T07:54:46Z","abstract_excerpt":"The advancement of vision-language models (VLMs) is hampered by a fragmented landscape of inconsistent and contaminated public datasets. We introduce FineVision, a meticulously collected, curated, and unified corpus of 24 million samples - the largest open resource of its kind. We unify more than 200 sources into 185 subsets via a semi-automated, human-in-the-loop pipeline: automation performs bulk ingestion and schema mapping, while reviewers audit mappings and spot-check outputs to verify faithful consumption of annotations, appropriate formatting and diversity, and safety; issues trigger ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17269","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/2510.17269/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":"2510.17269","created_at":"2026-05-21T01:04:17.883028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.17269v2","created_at":"2026-05-21T01:04:17.883028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17269","created_at":"2026-05-21T01:04:17.883028+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUHBZTYJV3H7","created_at":"2026-05-21T01:04:17.883028+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUHBZTYJV3H7ZJPI","created_at":"2026-05-21T01:04:17.883028+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUHBZTYJ","created_at":"2026-05-21T01:04:17.883028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11629","citing_title":"OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08560","citing_title":"ZAYA1-VL-8B Technical Report","ref_index":152,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16514","citing_title":"BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS","json":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS.json","graph_json":"https://pith.science/api/pith-number/IUHBZTYJV3H7ZJPIYIHSOPVJYS/graph.json","events_json":"https://pith.science/api/pith-number/IUHBZTYJV3H7ZJPIYIHSOPVJYS/events.json","paper":"https://pith.science/paper/IUHBZTYJ"},"agent_actions":{"view_html":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS","download_json":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS.json","view_paper":"https://pith.science/paper/IUHBZTYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.17269&json=true","fetch_graph":"https://pith.science/api/pith-number/IUHBZTYJV3H7ZJPIYIHSOPVJYS/graph.json","fetch_events":"https://pith.science/api/pith-number/IUHBZTYJV3H7ZJPIYIHSOPVJYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/action/storage_attestation","attest_author":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/action/author_attestation","sign_citation":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/action/citation_signature","submit_replication":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/action/replication_record"}},"created_at":"2026-05-21T01:04:17.883028+00:00","updated_at":"2026-05-21T01:04:17.883028+00:00"}