{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6XVM2WQN2KN6OOJ5CJWBMYK6QE","short_pith_number":"pith:6XVM2WQN","canonical_record":{"source":{"id":"2607.21617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T20:33:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a3152a03801cf4442baa14738964c64e5ce049c221c5da767758a9564e7c7a2f","abstract_canon_sha256":"209fd2294adde6e6c1c6f9c6d7456ae93175b9deca3d3b26271a3eba147b5f4a"},"schema_version":"1.0"},"canonical_sha256":"f5eacd5a0dd29be7393d126c16615e8136ee42bfe9bd8c1c4a3fb3841eecfbfb","source":{"kind":"arxiv","id":"2607.21617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21617","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21617v1","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21617","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"6XVM2WQN2KN6","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"6XVM2WQN2KN6OOJ5","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"6XVM2WQN","created_at":"2026-07-27T00:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6XVM2WQN2KN6OOJ5CJWBMYK6QE","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T20:33:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a3152a03801cf4442baa14738964c64e5ce049c221c5da767758a9564e7c7a2f","abstract_canon_sha256":"209fd2294adde6e6c1c6f9c6d7456ae93175b9deca3d3b26271a3eba147b5f4a"},"schema_version":"1.0"},"canonical_sha256":"f5eacd5a0dd29be7393d126c16615e8136ee42bfe9bd8c1c4a3fb3841eecfbfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:11.302229Z","signature_b64":"xWuFat0KA+6QdZyjJvmU1R/ZRaQCQzxz3CFtI8tx5nlyD0w2FJk7b7SlKUoz24oL6WTy4VnJIkzqMKyxAMqDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5eacd5a0dd29be7393d126c16615e8136ee42bfe9bd8c1c4a3fb3841eecfbfb","last_reissued_at":"2026-07-27T00:20:11.301278Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:11.301278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21617","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":"2026-07-27T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bC2sh8+0DUQgNQBy5pODnaMTWszesBVEfZNDv1kBa9ucEADaOGU85ZK3vxnXZgZfxmjawu84suM+f23E7+UvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:46:03.499782Z"},"content_sha256":"ddc8f9c86520e6988ea0db2c7050a70ebb2545f17826378e50d52702dc33e193","schema_version":"1.0","event_id":"sha256:ddc8f9c86520e6988ea0db2c7050a70ebb2545f17826378e50d52702dc33e193"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6XVM2WQN2KN6OOJ5CJWBMYK6QE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dimitrios Dimitriadis, Gwang Gook Lee, Jay Mohta, Kenan Emir Ak, Yan Xu","submitted_at":"2026-05-29T20:33:35Z","abstract_excerpt":"Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do not always act as faithful transcribers: when text is imperfect, they often tend to rewrite it into a more plausible form - a behavior that clean-text OCR benchmarks cannot detect. We introduce FaithC4, a multilingual perturbation benchmark of 1,455 single-page documents (English, Chinese, Korean) with three perturbation families: scramble, random substitution, and visually similar substitution. We use the benchmark to evaluate 15 systems spanning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21617","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/2607.21617/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":"2026-07-27T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cX1vJwFjjIBXM3r7yNJheRFJr8APLPAiHxJjYOp6mu/23ciGUmSUcATHgai6/sgOJQ9gqLX5TzwZJ27LcDKvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:46:03.500372Z"},"content_sha256":"8903d16f20e9edfcebbfab63306d126f031a2b8aee4e9294097ecc6efe43c653","schema_version":"1.0","event_id":"sha256:8903d16f20e9edfcebbfab63306d126f031a2b8aee4e9294097ecc6efe43c653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/bundle.json","state_url":"https://pith.science/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/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":"2026-08-04T15:46:03Z","links":{"resolver":"https://pith.science/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE","bundle":"https://pith.science/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/bundle.json","state":"https://pith.science/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XVM2WQN2KN6OOJ5CJWBMYK6QE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6XVM2WQN2KN6OOJ5CJWBMYK6QE","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":"209fd2294adde6e6c1c6f9c6d7456ae93175b9deca3d3b26271a3eba147b5f4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T20:33:35Z","title_canon_sha256":"a3152a03801cf4442baa14738964c64e5ce049c221c5da767758a9564e7c7a2f"},"schema_version":"1.0","source":{"id":"2607.21617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21617","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21617v1","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21617","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"6XVM2WQN2KN6","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"6XVM2WQN2KN6OOJ5","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"6XVM2WQN","created_at":"2026-07-27T00:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:8903d16f20e9edfcebbfab63306d126f031a2b8aee4e9294097ecc6efe43c653","target":"graph","created_at":"2026-07-27T00:20:11Z","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/2607.21617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do not always act as faithful transcribers: when text is imperfect, they often tend to rewrite it into a more plausible form - a behavior that clean-text OCR benchmarks cannot detect. We introduce FaithC4, a multilingual perturbation benchmark of 1,455 single-page documents (English, Chinese, Korean) with three perturbation families: scramble, random substitution, and visually similar substitution. We use the benchmark to evaluate 15 systems spanning","authors_text":"Dimitrios Dimitriadis, Gwang Gook Lee, Jay Mohta, Kenan Emir Ak, Yan Xu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T20:33:35Z","title":"Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21617","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:ddc8f9c86520e6988ea0db2c7050a70ebb2545f17826378e50d52702dc33e193","target":"record","created_at":"2026-07-27T00:20:11Z","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":"209fd2294adde6e6c1c6f9c6d7456ae93175b9deca3d3b26271a3eba147b5f4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T20:33:35Z","title_canon_sha256":"a3152a03801cf4442baa14738964c64e5ce049c221c5da767758a9564e7c7a2f"},"schema_version":"1.0","source":{"id":"2607.21617","kind":"arxiv","version":1}},"canonical_sha256":"f5eacd5a0dd29be7393d126c16615e8136ee42bfe9bd8c1c4a3fb3841eecfbfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5eacd5a0dd29be7393d126c16615e8136ee42bfe9bd8c1c4a3fb3841eecfbfb","first_computed_at":"2026-07-27T00:20:11.301278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:11.301278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWuFat0KA+6QdZyjJvmU1R/ZRaQCQzxz3CFtI8tx5nlyD0w2FJk7b7SlKUoz24oL6WTy4VnJIkzqMKyxAMqDBA==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:11.302229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddc8f9c86520e6988ea0db2c7050a70ebb2545f17826378e50d52702dc33e193","sha256:8903d16f20e9edfcebbfab63306d126f031a2b8aee4e9294097ecc6efe43c653"],"state_sha256":"4561414506ab6bab581251968983ee4326b92af01372b8b13292d253411332a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RtCT5plO34axudQMZU4eABG6sB9AkGp36RAm/69nuuryvkWHIAr3fxrZ0BnXrVgqZiFfof6COxuN5HmB2p2FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:46:03.507169Z","bundle_sha256":"68efeb717fcc0afdf1fec58a335e035b1548dd896f388f52770a340247b43a78"}}