{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QZU7SGTW23WLK3HY5PFKB2JNGY","short_pith_number":"pith:QZU7SGTW","schema_version":"1.0","canonical_sha256":"8669f91a76d6ecb56cf8ebcaa0e92d362aeb987f91747d07bd5c2681420dbb44","source":{"kind":"arxiv","id":"2505.07730","version":1},"attestation_state":"computed","paper":{"title":"Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Evangelos Kanoulas, Jia-Huei Ju, Jingfen Qiao, Xinyu Ma","submitted_at":"2025-05-12T16:37:47Z","abstract_excerpt":"Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent advance in VDR was introduced by ColPali, which significantly improved retrieval effectiveness through a late interaction mechanism. ColPali's approach demonstrated substantial performance gains over existing baselines that do not use late interaction on an established benchmark. In this study, we investigate the reproducibility and replicability of VDR methods with and withou"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.07730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T16:37:47Z","cross_cats_sorted":[],"title_canon_sha256":"903ecd18e03913850d22e972ed5cdff415e49d0b5c3d3b2425279bcc8d8a23a2","abstract_canon_sha256":"de72fbd5fd54fac0d7ed466bee212a2bf67e7f88eae9518f8fd9739a51499b56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:52.418872Z","signature_b64":"9XWcRLsiF9MDfPikL9LTJb58nXsKutRUvSPfH5hERcu2oY88zvcEwgdlZKGxoSeCCHH0bxscWRicKm4BC0kYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8669f91a76d6ecb56cf8ebcaa0e92d362aeb987f91747d07bd5c2681420dbb44","last_reissued_at":"2026-07-05T11:01:52.418441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:52.418441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Evangelos Kanoulas, Jia-Huei Ju, Jingfen Qiao, Xinyu Ma","submitted_at":"2025-05-12T16:37:47Z","abstract_excerpt":"Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent advance in VDR was introduced by ColPali, which significantly improved retrieval effectiveness through a late interaction mechanism. ColPali's approach demonstrated substantial performance gains over existing baselines that do not use late interaction on an established benchmark. In this study, we investigate the reproducibility and replicability of VDR methods with and withou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07730","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/2505.07730/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.07730","created_at":"2026-07-05T11:01:52.418496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07730v1","created_at":"2026-07-05T11:01:52.418496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07730","created_at":"2026-07-05T11:01:52.418496+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZU7SGTW23WL","created_at":"2026-07-05T11:01:52.418496+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZU7SGTW23WLK3HY","created_at":"2026-07-05T11:01:52.418496+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZU7SGTW","created_at":"2026-07-05T11:01:52.418496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY","json":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY.json","graph_json":"https://pith.science/api/pith-number/QZU7SGTW23WLK3HY5PFKB2JNGY/graph.json","events_json":"https://pith.science/api/pith-number/QZU7SGTW23WLK3HY5PFKB2JNGY/events.json","paper":"https://pith.science/paper/QZU7SGTW"},"agent_actions":{"view_html":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY","download_json":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY.json","view_paper":"https://pith.science/paper/QZU7SGTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07730&json=true","fetch_graph":"https://pith.science/api/pith-number/QZU7SGTW23WLK3HY5PFKB2JNGY/graph.json","fetch_events":"https://pith.science/api/pith-number/QZU7SGTW23WLK3HY5PFKB2JNGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY/action/storage_attestation","attest_author":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY/action/author_attestation","sign_citation":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY/action/citation_signature","submit_replication":"https://pith.science/pith/QZU7SGTW23WLK3HY5PFKB2JNGY/action/replication_record"}},"created_at":"2026-07-05T11:01:52.418496+00:00","updated_at":"2026-07-05T11:01:52.418496+00:00"}