{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7KIAFY6ABDXU3FTXORK22BB7D","short_pith_number":"pith:V7KIAFY6","schema_version":"1.0","canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","source":{"kind":"arxiv","id":"2412.08746","version":1},"attestation_state":"computed","paper":{"title":"DocVLM: Make Your VLM an Efficient Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","submitted_at":"2024-12-11T19:35:06Z","abstract_excerpt":"Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive applications demand high-resolution, resulting in significant computational overhead. Using OCR-extracted text in VLM prompts partially addresses this issue but underperforms compared to full-resolution counterpart, as it lacks the complete visual context needed for optimal performance. We introduce DocVLM, a method that integrates an OCR-based modality into V"},"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":"2412.08746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T19:35:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f55e0d748d59ea8fe1e4153b1caea9bb26f0d5b5822007405bced2699ff0d2f8","abstract_canon_sha256":"fd96093cfb3b58fa40fad4621b859d5692c93344ed4e7602c7b537b18ba4df58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:59.809545Z","signature_b64":"n7bI7KMQ12OocQ8AmYrUQnOWv+19wjXWAIWE4am/t9ZptYVbi0Fso5w8GNfMqlW98bIJW1L5eDc9vWHNT/hvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd480171e00477a6cb3bba2ad6821f8cb15f0ea88b661df0f71b9f856ed8375","last_reissued_at":"2026-07-05T09:47:59.809061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:59.809061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocVLM: Make Your VLM an Efficient Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alona Golts, Aviad Aberdam, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman, Roy Ganz, Shai Mazor, Yair Kittenplon","submitted_at":"2024-12-11T19:35:06Z","abstract_excerpt":"Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive applications demand high-resolution, resulting in significant computational overhead. Using OCR-extracted text in VLM prompts partially addresses this issue but underperforms compared to full-resolution counterpart, as it lacks the complete visual context needed for optimal performance. We introduce DocVLM, a method that integrates an OCR-based modality into V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08746","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/2412.08746/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":"2412.08746","created_at":"2026-07-05T09:47:59.809125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08746v1","created_at":"2026-07-05T09:47:59.809125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08746","created_at":"2026-07-05T09:47:59.809125+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7KIAFY6ABDX","created_at":"2026-07-05T09:47:59.809125+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7KIAFY6ABDXU3FT","created_at":"2026-07-05T09:47:59.809125+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7KIAFY6","created_at":"2026-07-05T09:47:59.809125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18818","citing_title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D","json":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D.json","graph_json":"https://pith.science/api/pith-number/V7KIAFY6ABDXU3FTXORK22BB7D/graph.json","events_json":"https://pith.science/api/pith-number/V7KIAFY6ABDXU3FTXORK22BB7D/events.json","paper":"https://pith.science/paper/V7KIAFY6"},"agent_actions":{"view_html":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D","download_json":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D.json","view_paper":"https://pith.science/paper/V7KIAFY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08746&json=true","fetch_graph":"https://pith.science/api/pith-number/V7KIAFY6ABDXU3FTXORK22BB7D/graph.json","fetch_events":"https://pith.science/api/pith-number/V7KIAFY6ABDXU3FTXORK22BB7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/action/storage_attestation","attest_author":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/action/author_attestation","sign_citation":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/action/citation_signature","submit_replication":"https://pith.science/pith/V7KIAFY6ABDXU3FTXORK22BB7D/action/replication_record"}},"created_at":"2026-07-05T09:47:59.809125+00:00","updated_at":"2026-07-05T09:47:59.809125+00:00"}