{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IUHBZTYJV3H7ZJPIYIHSOPVJYS","short_pith_number":"pith:IUHBZTYJ","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"},"canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","source":{"kind":"arxiv","id":"2510.17269","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.17269","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.17269v2","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17269","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"IUHBZTYJV3H7","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"IUHBZTYJV3H7ZJPI","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"IUHBZTYJ","created_at":"2026-05-21T01:04:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IUHBZTYJV3H7ZJPIYIHSOPVJYS","target":"record","payload":{"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"},"canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","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"},"source_kind":"arxiv","source_id":"2510.17269","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Gh02XF1ZWRQ0kw/+UrUxM/Qp41NuhZWdAXn+M8glnsV611njAnir0ewsqpUqb8XULUHGcLZJ0rnwLa32GE+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T22:32:35.792814Z"},"content_sha256":"01e59f4f99bb1e6da4a7913dafa4bcf861f79aeebe76df71ec34160240f2f5e6","schema_version":"1.0","event_id":"sha256:01e59f4f99bb1e6da4a7913dafa4bcf861f79aeebe76df71ec34160240f2f5e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IUHBZTYJV3H7ZJPIYIHSOPVJYS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63DY55jUaikRbq4bWyNPany6l3c0E06e8wb9P6qAfnUatkHYbg6OpY60R4ZEvS1jpwtSkvlskGuA0oI2LhPMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T22:32:35.793528Z"},"content_sha256":"83b9ea745e10d9a0fdd2233e80513bad9d9ff89ab5f51c4ed7c8e08d3a2a4d2a","schema_version":"1.0","event_id":"sha256:83b9ea745e10d9a0fdd2233e80513bad9d9ff89ab5f51c4ed7c8e08d3a2a4d2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/bundle.json","state_url":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/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":"2026-05-23T22:32:35Z","links":{"resolver":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS","bundle":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/bundle.json","state":"https://pith.science/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUHBZTYJV3H7ZJPIYIHSOPVJYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IUHBZTYJV3H7ZJPIYIHSOPVJYS","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":"d4b3f0dd2f4317f9aab112e0ae65c2b3267ce1046cf1076f844d9e28a9d24845","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T07:54:46Z","title_canon_sha256":"c84309328e87d7ab5f3a0ba6f7d794e9ed436159a7772f01488738bd17313222"},"schema_version":"1.0","source":{"id":"2510.17269","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.17269","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.17269v2","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17269","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"IUHBZTYJV3H7","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"IUHBZTYJV3H7ZJPI","created_at":"2026-05-21T01:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"IUHBZTYJ","created_at":"2026-05-21T01:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:83b9ea745e10d9a0fdd2233e80513bad9d9ff89ab5f51c4ed7c8e08d3a2a4d2a","target":"graph","created_at":"2026-05-21T01:04:17Z","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/2510.17269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amir Mahla, Andr\\'es Marafioti, Aritra Roy Gosthipaty, Leandro Von Werra, Luis Wiedmann, Orr Zohar, Rui Li, Thibaud Frere, Xiaohan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T07:54:46Z","title":"FineVision: Open Data Is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17269","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":"sha256:01e59f4f99bb1e6da4a7913dafa4bcf861f79aeebe76df71ec34160240f2f5e6","target":"record","created_at":"2026-05-21T01:04:17Z","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":"d4b3f0dd2f4317f9aab112e0ae65c2b3267ce1046cf1076f844d9e28a9d24845","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T07:54:46Z","title_canon_sha256":"c84309328e87d7ab5f3a0ba6f7d794e9ed436159a7772f01488738bd17313222"},"schema_version":"1.0","source":{"id":"2510.17269","kind":"arxiv","version":2}},"canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"450e1ccf09aecffca5e8c20f273ea9c4939ae99f9d803c2c322f3d9f658f92e6","first_computed_at":"2026-05-21T01:04:17.882920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:17.882920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdaaEFhw/UAqkYf2v/mxCNmJ1qsDt2Nik6tblD67YIZbg9JSerjv7HalMvw4AIWR2sEMuDGCZ03B0G0yA8TYAQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:17.883806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.17269","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01e59f4f99bb1e6da4a7913dafa4bcf861f79aeebe76df71ec34160240f2f5e6","sha256:83b9ea745e10d9a0fdd2233e80513bad9d9ff89ab5f51c4ed7c8e08d3a2a4d2a"],"state_sha256":"cffd7f57c47ddb64cae8f20616954084487705271281ba7641dc0637c68ff383"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+UBjJe8JvBfMKfNaF1jtB5alCPHVw3UmdEmw1QRqiZdIDryeDn2p5rGhL3net2MK1ka79+jnzxkrCdnbUfcBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T22:32:35.797522Z","bundle_sha256":"bf54e64e768ba20dea35eacc45add6f266975d11f47b871a551cac8283327742"}}