{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O7MCSJU33F3U2ALFJ2JIKDKMB3","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":"167e405fff6610858b40d68a024ba0e03c66e75f258162862dbc9fbbb74c58fb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T09:13:59Z","title_canon_sha256":"f4bf84ee5f0ca32dfce9e6592dc25f31a5cd6c6754d01148a8c0239556ffe9d5"},"schema_version":"1.0","source":{"id":"2607.07179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07179","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07179v1","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07179","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"O7MCSJU33F3U","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"O7MCSJU33F3U2ALF","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"O7MCSJU3","created_at":"2026-07-09T01:20:16Z"}],"graph_snapshots":[{"event_id":"sha256:de87cffe25583f86801666d8df057cb077b3b740d52d996652687bad4f04798b","target":"graph","created_at":"2026-07-09T01:20:16Z","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/2607.07179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vision-Language Models (VLMs) have shown remarkable performance in text-vision tasks, their robustness and transferability to different document domains remains underexplored. In this study, we present a comprehensive evaluation of 8 open-source pretrained VLMs on DocVQA in three different document domains: industrial documents of varying type, infographics, and presentation slides. We systematically assess model perfo","authors_text":"Alvaro Ortigosa, Aythami Morales, Daniel DeAlcala, Elena Marrero, Javier Ortega-Garcia, Julian Fierrez, Marta Robledo-Moreno, Miguel Lopez-Duran, Oscar Delgado, Ruben Tolosana, Ruben Vera-Rodriguez","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T09:13:59Z","title":"Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07179","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:fd3e38617c879d560687c73098da2ba98f130c50c41857547bcf46c259e95b6a","target":"record","created_at":"2026-07-09T01:20:16Z","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":"167e405fff6610858b40d68a024ba0e03c66e75f258162862dbc9fbbb74c58fb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T09:13:59Z","title_canon_sha256":"f4bf84ee5f0ca32dfce9e6592dc25f31a5cd6c6754d01148a8c0239556ffe9d5"},"schema_version":"1.0","source":{"id":"2607.07179","kind":"arxiv","version":1}},"canonical_sha256":"77d829269bd9774d01654e92850d4c0edc581087af7e30d444c7d61530d9bc23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77d829269bd9774d01654e92850d4c0edc581087af7e30d444c7d61530d9bc23","first_computed_at":"2026-07-09T01:20:16.701471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:16.701471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQH4uCVpFfM1MTE7MBLqCBCpUeeLL2LpCvCgSyWI5dphNhA8tzylPCFcz+tXo7SKm232QJ5njwx14zrePUMWCg==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:16.701881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd3e38617c879d560687c73098da2ba98f130c50c41857547bcf46c259e95b6a","sha256:de87cffe25583f86801666d8df057cb077b3b740d52d996652687bad4f04798b"],"state_sha256":"761e333808c4f652b8d84cbd0c88f804539f121a1a3a0920cfa8d6e8a32f6df7"}