{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FHURX5KGAJVOJ5HZFJYOO2TDGM","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":"34c48cf2a97eb553ca0ea159b4ae326e8b9fc440edeca8cc4be1f2447dc556ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-20T18:58:32Z","title_canon_sha256":"f7187e8d02b0c7f7865ff8176292b3a3467ba53aebeac99765434e0de06ac4b3"},"schema_version":"1.0","source":{"id":"2601.14251","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.14251","created_at":"2026-07-01T01:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2601.14251v2","created_at":"2026-07-01T01:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14251","created_at":"2026-07-01T01:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"FHURX5KGAJVO","created_at":"2026-07-01T01:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"FHURX5KGAJVOJ5HZ","created_at":"2026-07-01T01:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"FHURX5KG","created_at":"2026-07-01T01:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:cd19cf0293b93d589863a0dfe337ca63f3a8a80a20e25182e35bc801628b2862","target":"graph","created_at":"2026-07-01T01:17:45Z","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/2601.14251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present LightOnOCR-2-1B, a 1B-parameter end-to-end multilingual vision--language model that converts document images (e.g., PDFs) into clean, naturally ordered text without brittle OCR pipelines. Trained on a large-scale, high-quality distillation mix with strong coverage of scans, French documents, and scientific PDFs, LightOnOCR-2 achieves state-of-the-art results on OlmOCR-Bench while being 9$\\times$ smaller and substantially faster than prior best-performing models. We further extend the output format to predict normalized bounding boxes for embedded images, introducing localization dur","authors_text":"Adrien Cavaill\\`es, Baptiste Aubertin, Said Taghadouini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-20T18:58:32Z","title":"LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14251","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":"sha256:7a1122cdce3ee44581b58fc07dc23b86ae4bf30f557cc9dab0858eaef9e85da7","target":"record","created_at":"2026-07-01T01:17:45Z","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":"34c48cf2a97eb553ca0ea159b4ae326e8b9fc440edeca8cc4be1f2447dc556ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-20T18:58:32Z","title_canon_sha256":"f7187e8d02b0c7f7865ff8176292b3a3467ba53aebeac99765434e0de06ac4b3"},"schema_version":"1.0","source":{"id":"2601.14251","kind":"arxiv","version":2}},"canonical_sha256":"29e91bf546026ae4f4f92a70e76a63330e289874cc5313304895717979bd1a88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29e91bf546026ae4f4f92a70e76a63330e289874cc5313304895717979bd1a88","first_computed_at":"2026-07-01T01:17:45.951944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:45.951944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LzjqPsi6fQS/yMcFeLoF5fcP6g05Rxb7O+N7/3zlValfQHMHehE+RTKvUynVo/B5ZmuRXQDoNRdquTd/WS7TDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:45.952420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.14251","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a1122cdce3ee44581b58fc07dc23b86ae4bf30f557cc9dab0858eaef9e85da7","sha256:cd19cf0293b93d589863a0dfe337ca63f3a8a80a20e25182e35bc801628b2862"],"state_sha256":"6cbc4490caf39cb8a1cd2d6bb5b79d2614e8c3ef59d2fe16c8cb8dad56ab1454"}