{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JTWXCF4UVTUX5S3TMYYTAK2344","short_pith_number":"pith:JTWXCF4U","canonical_record":{"source":{"id":"2411.17835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T12:09:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"06e7aa005d262b56c14cec9d5db003c417a2ed7372fe4f8fbbc2b4aa3912ed18","abstract_canon_sha256":"f7411403ff3b2b194f96329db58fec34f1c78f073b50377931cefb12ccb288cf"},"schema_version":"1.0"},"canonical_sha256":"4ced711794ace97ecb736631302b5be70df944ce49242a4fe801d6ea8182a72d","source":{"kind":"arxiv","id":"2411.17835","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17835","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17835v1","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17835","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"JTWXCF4UVTUX","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"JTWXCF4UVTUX5S3T","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"JTWXCF4U","created_at":"2026-07-05T09:41:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JTWXCF4UVTUX5S3TMYYTAK2344","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T12:09:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"06e7aa005d262b56c14cec9d5db003c417a2ed7372fe4f8fbbc2b4aa3912ed18","abstract_canon_sha256":"f7411403ff3b2b194f96329db58fec34f1c78f073b50377931cefb12ccb288cf"},"schema_version":"1.0"},"canonical_sha256":"4ced711794ace97ecb736631302b5be70df944ce49242a4fe801d6ea8182a72d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:07.549901Z","signature_b64":"Yp23pT4HP5yZdMCy/kA0bqSmlWXvmXFduG4Bj5IpuXlYzIY88wXeVMdkxmP2yWqHBKZ6xxyPml/182k62aF9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ced711794ace97ecb736631302b5be70df944ce49242a4fe801d6ea8182a72d","last_reissued_at":"2026-07-05T09:41:07.549410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:07.549410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17835","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KcOfElJ3yNJueiKKc1hyXDOAA+lozwbKvXU62gTLRM9hbVBkQRIA9lS6rHQzmnCyY6cw3N6/OsJgw9mHjnO8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:55:10.589943Z"},"content_sha256":"73d2e86eed262fd414f97088bd4cfd03a9ef07372c1a1d22b8958be15cab3078","schema_version":"1.0","event_id":"sha256:73d2e86eed262fd414f97088bd4cfd03a9ef07372c1a1d22b8958be15cab3078"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JTWXCF4UVTUX5S3TMYYTAK2344","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Mohamed Rashad","submitted_at":"2024-11-19T12:09:12Z","abstract_excerpt":"We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat, and arabic-large-nougat. These models are fine-tuned on a synthetic dataset, arabic-img2md, comprising 13.7k pairs of Arabic book pages and their Markdown representations. Key contributions include the Aranizer-PBE-86k tokenizer, designed for efficient tokenization, and the use of torch.bfloat16 precision with Flash Attention 2 for optimized training and infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17835","kind":"arxiv","version":1},"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/2411.17835/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":"2026-07-05T09:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6s9kk/orTv2t2IwQVWBEW7YleNLjZ34ziMnHqsMjporwVkLVddUiA5rQTNtA94mW2Lu56TnfO43wOKzKeUX7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:55:10.590571Z"},"content_sha256":"320773881d754a2d8eb7fdbbf349a2b325186195851d4452d4fafb2f7fa08e44","schema_version":"1.0","event_id":"sha256:320773881d754a2d8eb7fdbbf349a2b325186195851d4452d4fafb2f7fa08e44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTWXCF4UVTUX5S3TMYYTAK2344/bundle.json","state_url":"https://pith.science/pith/JTWXCF4UVTUX5S3TMYYTAK2344/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTWXCF4UVTUX5S3TMYYTAK2344/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":"2026-08-05T22:55:10Z","links":{"resolver":"https://pith.science/pith/JTWXCF4UVTUX5S3TMYYTAK2344","bundle":"https://pith.science/pith/JTWXCF4UVTUX5S3TMYYTAK2344/bundle.json","state":"https://pith.science/pith/JTWXCF4UVTUX5S3TMYYTAK2344/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTWXCF4UVTUX5S3TMYYTAK2344/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JTWXCF4UVTUX5S3TMYYTAK2344","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":"f7411403ff3b2b194f96329db58fec34f1c78f073b50377931cefb12ccb288cf","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T12:09:12Z","title_canon_sha256":"06e7aa005d262b56c14cec9d5db003c417a2ed7372fe4f8fbbc2b4aa3912ed18"},"schema_version":"1.0","source":{"id":"2411.17835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17835","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17835v1","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17835","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"JTWXCF4UVTUX","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"JTWXCF4UVTUX5S3T","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"JTWXCF4U","created_at":"2026-07-05T09:41:07Z"}],"graph_snapshots":[{"event_id":"sha256:320773881d754a2d8eb7fdbbf349a2b325186195851d4452d4fafb2f7fa08e44","target":"graph","created_at":"2026-07-05T09:41:07Z","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/2411.17835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat, and arabic-large-nougat. These models are fine-tuned on a synthetic dataset, arabic-img2md, comprising 13.7k pairs of Arabic book pages and their Markdown representations. Key contributions include the Aranizer-PBE-86k tokenizer, designed for efficient tokenization, and the use of torch.bfloat16 precision with Flash Attention 2 for optimized training and infe","authors_text":"Mohamed Rashad","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T12:09:12Z","title":"Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17835","kind":"arxiv","version":1},"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":"sha256:73d2e86eed262fd414f97088bd4cfd03a9ef07372c1a1d22b8958be15cab3078","target":"record","created_at":"2026-07-05T09:41:07Z","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":"f7411403ff3b2b194f96329db58fec34f1c78f073b50377931cefb12ccb288cf","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T12:09:12Z","title_canon_sha256":"06e7aa005d262b56c14cec9d5db003c417a2ed7372fe4f8fbbc2b4aa3912ed18"},"schema_version":"1.0","source":{"id":"2411.17835","kind":"arxiv","version":1}},"canonical_sha256":"4ced711794ace97ecb736631302b5be70df944ce49242a4fe801d6ea8182a72d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ced711794ace97ecb736631302b5be70df944ce49242a4fe801d6ea8182a72d","first_computed_at":"2026-07-05T09:41:07.549410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:07.549410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yp23pT4HP5yZdMCy/kA0bqSmlWXvmXFduG4Bj5IpuXlYzIY88wXeVMdkxmP2yWqHBKZ6xxyPml/182k62aF9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:07.549901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d2e86eed262fd414f97088bd4cfd03a9ef07372c1a1d22b8958be15cab3078","sha256:320773881d754a2d8eb7fdbbf349a2b325186195851d4452d4fafb2f7fa08e44"],"state_sha256":"95a3c326e316ea3ed21727e6a364b8557007b2ae532f34120ad19783cee1d012"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+gdLsw2lZZyo80vcCV9R692PYVTy+3S/BHDsgZx8ofNYjeW2ypGT99ikuGiuwJiAlumkqNfUTcFyoyEqWhOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:55:10.595429Z","bundle_sha256":"fba49d6a24af23a22607ba04646ba0d10f6665615bbd340f6137ad322098ed00"}}