{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BELLFSLYWJQBKSNC3Z3JGZ6INW","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"25ccce010c085ed923868d526785f8425a13b73d373e155c8be0b3c59a5d772a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:03:51Z","title_canon_sha256":"6659dfcf8172ee5a4b2e96c1a493ab4f9cb6962d17fc0578a6a80e56d7650fae"},"schema_version":"1.0","source":{"id":"2608.01792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01792","created_at":"2026-08-04T02:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01792v1","created_at":"2026-08-04T02:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01792","created_at":"2026-08-04T02:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"BELLFSLYWJQB","created_at":"2026-08-04T02:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"BELLFSLYWJQBKSNC","created_at":"2026-08-04T02:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"BELLFSLY","created_at":"2026-08-04T02:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:b5bceafa413669d1f11372b0405ad937db74ae384001042f86dad5997d5d9796","target":"graph","created_at":"2026-08-04T02:07:11Z","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/2608.01792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intelligent document processing (IDP) with vision-language models (VLMs) hinges on confidence scores trustworthy enough to route extractions between automation and human review. Existing document benchmarks are dominated by clean, high-quality samples, leaving low accuracy regions too sparse for calibration assessment. We introduce ConfBench, the first calibration-specific benchmark for key information extraction (KIE), built by applying 20 controlled degradation pipelines to a diverse document set, yielding 1,346 variants and 70K+ entity-level evaluations spanning the full accuracy spectrum. ","authors_text":"Bob Strahan, Boyi Xie, Diego A. Socolinsky, Md Mofijul Islam, Mohammad Rostami, Priyashree Roy, Renhao Xue, Spencer Romo, Sujitha Martin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:03:51Z","title":"Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01792","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":"sha256:13b8531a29c318d2c687a7df872f0b4825863a533c10e4a6f9a8f8a435083deb","target":"record","created_at":"2026-08-04T02:07:11Z","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":"25ccce010c085ed923868d526785f8425a13b73d373e155c8be0b3c59a5d772a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:03:51Z","title_canon_sha256":"6659dfcf8172ee5a4b2e96c1a493ab4f9cb6962d17fc0578a6a80e56d7650fae"},"schema_version":"1.0","source":{"id":"2608.01792","kind":"arxiv","version":1}},"canonical_sha256":"0916b2c978b2601549a2de769367c86d97ca9a904e09fc30c1441303b9f0fb3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0916b2c978b2601549a2de769367c86d97ca9a904e09fc30c1441303b9f0fb3f","first_computed_at":"2026-08-04T02:07:11.045258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:07:11.045258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQTnSelIHMZ4TG2h9S3PYevsvr6zJ7+ZmqaGuc2/NAbTuZ2U/ZHUK8J7iVM/kZXdUFIl6mnOPOXQ5psEKWWRDw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:07:11.046738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13b8531a29c318d2c687a7df872f0b4825863a533c10e4a6f9a8f8a435083deb","sha256:b5bceafa413669d1f11372b0405ad937db74ae384001042f86dad5997d5d9796","sha256:6863ed2b7c1b7357904d3cf731d535cf645e6783db86b85fbbf66517189dc8b6"],"state_sha256":"c0473504dff4d9a60fd1d2ead878bc3c25722e0b94e8f137fe1460ee6d7411c3"}