{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBKAZ7ADGTBMDY7K2SR4DB7UD5","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":"d5f28713d6a2afcb63490758f7208bc4f97ffac8fcf8140a266c97ffe4f0ecda","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-27T15:45:29Z","title_canon_sha256":"fe7ac4341d12ea95464629e8bc1ed64f6ef6f6341694a7fe2fbe9923c7a430fd"},"schema_version":"1.0","source":{"id":"2407.01449","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01449","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01449v6","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01449","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"RBKAZ7ADGTBM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RBKAZ7ADGTBMDY7K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RBKAZ7AD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e452e01b90a838763ef36e47a777ac013e651417bf4b101dee95af78ef35c2d4","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ColPali largely outperforms modern document retrieval pipelines while being drastically simpler, faster and end-to-end trainable."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That direct image embeddings from a vision-language model capture all necessary semantic and layout information better than text extraction pipelines across the tested domains and languages."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ColPali embeds document page images with a vision-language model and late interaction to outperform text-based retrieval pipelines on a new visual document benchmark while being simpler and faster."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Directly embedding images of document pages with a vision language model outperforms text extraction pipelines in retrieval tasks."}],"snapshot_sha256":"c55c656f01ef3c2cc60171e80457a9f9bcb352ccce0771ed29df5d7e88d0abbc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be80503df53eb046728f77a4a7100b93f594ebf97972885e0e178eaeb500b404"},"paper":{"abstract_excerpt":"Documents are visually rich structures that convey information through text, but also figures, page layouts, tables, or even fonts. Since modern retrieval systems mainly rely on the textual information they extract from document pages to index documents -often through lengthy and brittle processes-, they struggle to exploit key visual cues efficiently. This limits their capabilities in many practical document retrieval applications such as Retrieval Augmented Generation (RAG). To benchmark current systems on visually rich document retrieval, we introduce the Visual Document Retrieval Benchmark","authors_text":"Bilel Omrani, C\\'eline Hudelot, Gautier Viaud, Hugues Sibille, Manuel Faysse, Pierre Colombo, Tony Wu","cross_cats":["cs.CL","cs.CV"],"headline":"Directly embedding images of document pages with a vision language model outperforms text extraction pipelines in retrieval tasks.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-27T15:45:29Z","title":"ColPali: Efficient Document Retrieval with Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01449","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-15T02:32:05.572657Z","id":"da0a4371-b525-469e-ac83-2d944729d746","model_set":{"reader":"grok-4.3"},"one_line_summary":"ColPali embeds document page images with a vision-language model and late interaction to outperform text-based retrieval pipelines on a new visual document benchmark while being simpler and faster.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Directly embedding images of document pages with a vision language model outperforms text extraction pipelines in retrieval tasks.","strongest_claim":"ColPali largely outperforms modern document retrieval pipelines while being drastically simpler, faster and end-to-end trainable.","weakest_assumption":"That direct image embeddings from a vision-language model capture all necessary semantic and layout information better than text extraction pipelines across the tested domains and languages."}},"verdict_id":"da0a4371-b525-469e-ac83-2d944729d746"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a9feb4e5a6e1aa496e98e6e4837a545ccd1f1146a3e644026733cf535cefe3f4","target":"record","created_at":"2026-05-17T23:38:53Z","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":"d5f28713d6a2afcb63490758f7208bc4f97ffac8fcf8140a266c97ffe4f0ecda","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-27T15:45:29Z","title_canon_sha256":"fe7ac4341d12ea95464629e8bc1ed64f6ef6f6341694a7fe2fbe9923c7a430fd"},"schema_version":"1.0","source":{"id":"2407.01449","kind":"arxiv","version":6}},"canonical_sha256":"88540cfc0334c2c1e3ead4a3c187f41f59f6489d63cba4485a298a737bd882eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88540cfc0334c2c1e3ead4a3c187f41f59f6489d63cba4485a298a737bd882eb","first_computed_at":"2026-05-17T23:38:53.807452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.807452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mS8d8uD63bLEqjCFb7U6mdHnav5ianRSfKkq84+MKnU/9olpMJr2YEZp25BHFpKjDsKPtlpIWrXamyKWUgRNAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.808067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01449","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9feb4e5a6e1aa496e98e6e4837a545ccd1f1146a3e644026733cf535cefe3f4","sha256:e452e01b90a838763ef36e47a777ac013e651417bf4b101dee95af78ef35c2d4"],"state_sha256":"a661444b0652fc9171363aef6738c2bdb92475b8f658196a2d6fa7cc65e9dde0"}