{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z2JV37S2VO4SDOO7CRX7OC7UVY","short_pith_number":"pith:Z2JV37S2","schema_version":"1.0","canonical_sha256":"ce935dfe5aabb921b9df146ff70bf4ae39f213245dfc8527e7ac9b298b510983","source":{"kind":"arxiv","id":"2604.00725","version":2},"attestation_state":"computed","paper":{"title":"A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Chatelain, Merveilles Agbeti-Messan, Pierrick Tranouez, St\\'ephane Nicolas, Thierry Paquet","submitted_at":"2026-04-01T10:33:33Z","abstract_excerpt":"End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregress"},"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":"2604.00725","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T10:33:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1afe7f954897ef8b6b5868de7f4414132b76454b046840ed01cc74e41b9ec886","abstract_canon_sha256":"4f4880dd252c517b4731b292434c1c0a740b2475123573f2cf428a3f8f0cf5b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:02.570681Z","signature_b64":"z6JI9P84o+2LdiWoYfZCW1/owSvd4fGZaDxiODzTa509RTdx+4EeWsYYN3BeI87BIexMb+s/Q/X/OLRQUZNuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce935dfe5aabb921b9df146ff70bf4ae39f213245dfc8527e7ac9b298b510983","last_reissued_at":"2026-06-24T01:15:02.570225Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:02.570225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Chatelain, Merveilles Agbeti-Messan, Pierrick Tranouez, St\\'ephane Nicolas, Thierry Paquet","submitted_at":"2026-04-01T10:33:33Z","abstract_excerpt":"End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00725","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/2604.00725/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":"2604.00725","created_at":"2026-06-24T01:15:02.570291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.00725v2","created_at":"2026-06-24T01:15:02.570291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00725","created_at":"2026-06-24T01:15:02.570291+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2JV37S2VO4S","created_at":"2026-06-24T01:15:02.570291+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2JV37S2VO4SDOO7","created_at":"2026-06-24T01:15:02.570291+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2JV37S2","created_at":"2026-06-24T01:15:02.570291+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/Z2JV37S2VO4SDOO7CRX7OC7UVY","json":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY.json","graph_json":"https://pith.science/api/pith-number/Z2JV37S2VO4SDOO7CRX7OC7UVY/graph.json","events_json":"https://pith.science/api/pith-number/Z2JV37S2VO4SDOO7CRX7OC7UVY/events.json","paper":"https://pith.science/paper/Z2JV37S2"},"agent_actions":{"view_html":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY","download_json":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY.json","view_paper":"https://pith.science/paper/Z2JV37S2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.00725&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2JV37S2VO4SDOO7CRX7OC7UVY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2JV37S2VO4SDOO7CRX7OC7UVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY/action/storage_attestation","attest_author":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY/action/author_attestation","sign_citation":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY/action/citation_signature","submit_replication":"https://pith.science/pith/Z2JV37S2VO4SDOO7CRX7OC7UVY/action/replication_record"}},"created_at":"2026-06-24T01:15:02.570291+00:00","updated_at":"2026-06-24T01:15:02.570291+00:00"}