{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LWONAZWJGCE5LAOOV6OHNBWZ2J","short_pith_number":"pith:LWONAZWJ","canonical_record":{"source":{"id":"2607.00250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"829a7ed4de5fc8abb2b12469546f545f6bb1af1b09aef2a63ba5b09d392bd04d","abstract_canon_sha256":"345d56a4eb4b3913a2cfe30a195523991b33f27ad3277ace3a8e787b6b00d99e"},"schema_version":"1.0"},"canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","source":{"kind":"arxiv","id":"2607.00250","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00250","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00250v1","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00250","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"LWONAZWJGCE5","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"LWONAZWJGCE5LAOO","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"LWONAZWJ","created_at":"2026-07-02T00:18:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LWONAZWJGCE5LAOOV6OHNBWZ2J","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"829a7ed4de5fc8abb2b12469546f545f6bb1af1b09aef2a63ba5b09d392bd04d","abstract_canon_sha256":"345d56a4eb4b3913a2cfe30a195523991b33f27ad3277ace3a8e787b6b00d99e"},"schema_version":"1.0"},"canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:41.094078Z","signature_b64":"60cpYmrZWv39jC56WCSfE42C38z1NJaszUAzs17i79z4qflqkCsCE0OKSGlEwe3l/TAOu6MbTSPjduloiyYiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","last_reissued_at":"2026-07-02T00:18:41.093234Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:41.093234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00250","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":"2026-07-02T00:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dzHCLtevOdZIeFot1on1NHWvqXNV3QO6DLRvzq8z8Qvd42nGYbQjtp6uGYvE4av+dlGT6bauUJ9ooPldO85uBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:16:11.120632Z"},"content_sha256":"7e71c2da283d7e65739d2e43e26fba39b5a81a7f7a8fe7038d5b7608ddd95558","schema_version":"1.0","event_id":"sha256:7e71c2da283d7e65739d2e43e26fba39b5a81a7f7a8fe7038d5b7608ddd95558"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LWONAZWJGCE5LAOOV6OHNBWZ2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LV-ROVER: Multi-Stream Tesseract Voting for Maltese Paragraph OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam Darmanin","submitted_at":"2026-06-30T22:58:41Z","abstract_excerpt":"Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single known real labelled PDF corpus for OCR training, 57 page, far below what paragraph-level training needs: low-resource for OCR specifically. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract LV-ROVER ensemble, and report results on a 422-paragraph benchmark against a fine-tuned-Tesseract baseline of character error rate (CER) 0.0234. Ensemble recognition alone improves CER by 44 percent, to 0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00250","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/2607.00250/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":"2026-07-02T00:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6y7eQiI9cbDr8hgOTv353OWbgWeFygmvyZYuXebOSoFqiq8GOITB//TGgmjfRwUXqRvKSgYgHPcX2h3SMSplDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:16:11.121005Z"},"content_sha256":"64a2e5eb1e6e5fc0243cb7988762a9359c50fe293d05292abd8bd92cbabf98a3","schema_version":"1.0","event_id":"sha256:64a2e5eb1e6e5fc0243cb7988762a9359c50fe293d05292abd8bd92cbabf98a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/bundle.json","state_url":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/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":"2026-07-03T08:16:11Z","links":{"resolver":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J","bundle":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/bundle.json","state":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LWONAZWJGCE5LAOOV6OHNBWZ2J","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":"345d56a4eb4b3913a2cfe30a195523991b33f27ad3277ace3a8e787b6b00d99e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","title_canon_sha256":"829a7ed4de5fc8abb2b12469546f545f6bb1af1b09aef2a63ba5b09d392bd04d"},"schema_version":"1.0","source":{"id":"2607.00250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00250","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00250v1","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00250","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"LWONAZWJGCE5","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"LWONAZWJGCE5LAOO","created_at":"2026-07-02T00:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"LWONAZWJ","created_at":"2026-07-02T00:18:41Z"}],"graph_snapshots":[{"event_id":"sha256:64a2e5eb1e6e5fc0243cb7988762a9359c50fe293d05292abd8bd92cbabf98a3","target":"graph","created_at":"2026-07-02T00:18:41Z","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/2607.00250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single known real labelled PDF corpus for OCR training, 57 page, far below what paragraph-level training needs: low-resource for OCR specifically. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract LV-ROVER ensemble, and report results on a 422-paragraph benchmark against a fine-tuned-Tesseract baseline of character error rate (CER) 0.0234. Ensemble recognition alone improves CER by 44 percent, to 0","authors_text":"Adam Darmanin","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","title":"LV-ROVER: Multi-Stream Tesseract Voting for Maltese Paragraph OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00250","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":"sha256:7e71c2da283d7e65739d2e43e26fba39b5a81a7f7a8fe7038d5b7608ddd95558","target":"record","created_at":"2026-07-02T00:18:41Z","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":"345d56a4eb4b3913a2cfe30a195523991b33f27ad3277ace3a8e787b6b00d99e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","title_canon_sha256":"829a7ed4de5fc8abb2b12469546f545f6bb1af1b09aef2a63ba5b09d392bd04d"},"schema_version":"1.0","source":{"id":"2607.00250","kind":"arxiv","version":1}},"canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","first_computed_at":"2026-07-02T00:18:41.093234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:41.093234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60cpYmrZWv39jC56WCSfE42C38z1NJaszUAzs17i79z4qflqkCsCE0OKSGlEwe3l/TAOu6MbTSPjduloiyYiAg==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:41.094078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e71c2da283d7e65739d2e43e26fba39b5a81a7f7a8fe7038d5b7608ddd95558","sha256:64a2e5eb1e6e5fc0243cb7988762a9359c50fe293d05292abd8bd92cbabf98a3"],"state_sha256":"727b09995f70a4549403c62ba116fc03215387bc46b8488e06cd11e28afaaa56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhJ3sVnvluikA+OvuvKSbnxt7YnTLMA6jCZ/Gdkbt/dULpHw97nehPI4z7A10YQHvGcraA48J7T1pX2i9srNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T08:16:11.123124Z","bundle_sha256":"8cd6e8ad5476cf3e3f148af5a6ed90472c7265282e79734c36139f9334bab0e9"}}