{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SX2VDE4LB4SD4MBBTLSM5PGB6I","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":"4f4ebcf561d19b89de502b7c2966939f5d347c74f2f9b027237655872a56d3e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T08:45:48Z","title_canon_sha256":"87ad7d438dc0e3b28915f029ec7768d93210c4b35cd5e9a3fe6ddc72993792da"},"schema_version":"1.0","source":{"id":"2310.18343","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18343","created_at":"2026-07-05T07:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18343v2","created_at":"2026-07-05T07:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18343","created_at":"2026-07-05T07:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"SX2VDE4LB4SD","created_at":"2026-07-05T07:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"SX2VDE4LB4SD4MBB","created_at":"2026-07-05T07:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"SX2VDE4L","created_at":"2026-07-05T07:09:03Z"}],"graph_snapshots":[{"event_id":"sha256:766fd8db5ff30ebc9aa4030e87dd62333c2aa399c2363db8e7f24a03541e673c","target":"graph","created_at":"2026-07-05T07:09:03Z","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/2310.18343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for ","authors_text":"Desmond Elliott, Isabelle Augenstein, Nadav Borenstein, Phillip Rust","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T08:45:48Z","title":"PHD: Pixel-Based Language Modeling of Historical Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18343","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:f7704632939adb5b170dbd9948ca553ac03b753b0d5ca67b5b5b7d7997f9226e","target":"record","created_at":"2026-07-05T07:09:03Z","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":"4f4ebcf561d19b89de502b7c2966939f5d347c74f2f9b027237655872a56d3e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T08:45:48Z","title_canon_sha256":"87ad7d438dc0e3b28915f029ec7768d93210c4b35cd5e9a3fe6ddc72993792da"},"schema_version":"1.0","source":{"id":"2310.18343","kind":"arxiv","version":2}},"canonical_sha256":"95f551938b0f243e30219ae4cebcc1f22e8f454d4f933cd23bee78937eb78180","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f551938b0f243e30219ae4cebcc1f22e8f454d4f933cd23bee78937eb78180","first_computed_at":"2026-07-05T07:09:03.831864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:03.831864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+LbjGHYkOhe+Dog1F4JT/sjYcZ/yaljPviC/PadTN4Bmh1T/dKkGN2brXq61/O7kV7ChmeSTFmVH5BQJ0WzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:03.832326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18343","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7704632939adb5b170dbd9948ca553ac03b753b0d5ca67b5b5b7d7997f9226e","sha256:766fd8db5ff30ebc9aa4030e87dd62333c2aa399c2363db8e7f24a03541e673c"],"state_sha256":"a3cf5329be24b7b284bdec3a9777d62afe4e4867d92f6a7c85d5263132e56034"}