{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z62RGGWLBPRXGQO5A3SUC6ZD4M","short_pith_number":"pith:Z62RGGWL","schema_version":"1.0","canonical_sha256":"cfb5131acb0be37341dd06e5417b23e31b905724d40cea585a72f37b78bc32ea","source":{"kind":"arxiv","id":"2602.16872","version":2},"attestation_state":"computed","paper":{"title":"DODO: Discrete OCR Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gilad Deutch, Niv Nayman, Roi Ronen, Roy Ganz, Sean Man, Shahar Tsiper, Shai Mazor","submitted_at":"2026-02-18T20:59:22Z","abstract_excerpt":"Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR is a highly deterministic task where the visual input strictly dictates"},"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":"2602.16872","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-18T20:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"4dfe0e658532c3af736f6e70d047deb0544508db73980826bd407c40212aaec0","abstract_canon_sha256":"a6678b01909e1593cfa90ca5332df478ecb2de8775aba49d4e19317a005f86e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:46.362348Z","signature_b64":"cE894g9TNBrkl9UYH7VzwdSeySkLv2w++ueLrb1zj0FL2YwZeHLlz77vIbn64L+zFIAaUBTPOddbAcoLk0k3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb5131acb0be37341dd06e5417b23e31b905724d40cea585a72f37b78bc32ea","last_reissued_at":"2026-05-28T02:04:46.361897Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:46.361897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DODO: Discrete OCR Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gilad Deutch, Niv Nayman, Roi Ronen, Roy Ganz, Sean Man, Shahar Tsiper, Shai Mazor","submitted_at":"2026-02-18T20:59:22Z","abstract_excerpt":"Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR is a highly deterministic task where the visual input strictly dictates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16872","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/2602.16872/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":"2602.16872","created_at":"2026-05-28T02:04:46.361945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16872v2","created_at":"2026-05-28T02:04:46.361945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16872","created_at":"2026-05-28T02:04:46.361945+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z62RGGWLBPRX","created_at":"2026-05-28T02:04:46.361945+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z62RGGWLBPRXGQO5","created_at":"2026-05-28T02:04:46.361945+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z62RGGWL","created_at":"2026-05-28T02:04:46.361945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M","json":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M.json","graph_json":"https://pith.science/api/pith-number/Z62RGGWLBPRXGQO5A3SUC6ZD4M/graph.json","events_json":"https://pith.science/api/pith-number/Z62RGGWLBPRXGQO5A3SUC6ZD4M/events.json","paper":"https://pith.science/paper/Z62RGGWL"},"agent_actions":{"view_html":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M","download_json":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M.json","view_paper":"https://pith.science/paper/Z62RGGWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16872&json=true","fetch_graph":"https://pith.science/api/pith-number/Z62RGGWLBPRXGQO5A3SUC6ZD4M/graph.json","fetch_events":"https://pith.science/api/pith-number/Z62RGGWLBPRXGQO5A3SUC6ZD4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M/action/storage_attestation","attest_author":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M/action/author_attestation","sign_citation":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M/action/citation_signature","submit_replication":"https://pith.science/pith/Z62RGGWLBPRXGQO5A3SUC6ZD4M/action/replication_record"}},"created_at":"2026-05-28T02:04:46.361945+00:00","updated_at":"2026-05-28T02:04:46.361945+00:00"}