{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RWNVR5J2VS7JVERRK23I4MCFEU","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":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9"},"schema_version":"1.0","source":{"id":"2509.09722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09722v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"RWNVR5J2VS7J","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"RWNVR5J2VS7JVERR","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"RWNVR5J2","created_at":"2026-07-05T12:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b","target":"graph","created_at":"2026-07-05T12:09:47Z","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/2509.09722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel ensemble framework that stabilizes LLM based text extraction from noisy historical documents. We transcribe multiple augmented variants of each image with Gemini 2.0 Flash and fuse these outputs with a custom Needleman Wunsch style aligner that yields both a consensus transcription and a confidence score. We present a new dataset of 622 Pennsylvania death records, and demonstrate our method improves transcription accuracy by 4 percentage points relative to a single shot baseline. We find that padding and blurring are the most useful for improving accuracy, while grid warp pe","authors_text":"Taylor Archibald, Tony Martinez","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title":"Improving MLLM Historical Record Extraction with Test-Time Image"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09722","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":"sha256:6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941","target":"record","created_at":"2026-07-05T12:09:47Z","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":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9"},"schema_version":"1.0","source":{"id":"2509.09722","kind":"arxiv","version":1}},"canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","first_computed_at":"2026-07-05T12:09:47.863537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:47.863537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vw/Ftd0B0yXLwt6ZxWwVeAYQ0IWnJZDzL+2J7toXuqQaMPUIxpFx4aAb3jK6JN0sGNFbJNj5VZKa4xXAnM7lAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:47.864120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941","sha256:88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b"],"state_sha256":"39ed690198c796bc3db7ab25c3b2a4a58315e2830ad5a99239eb1f38d4b1a334"}