{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GTE5ZOB4HM7EEWZOPSMFR7KBEM","short_pith_number":"pith:GTE5ZOB4","schema_version":"1.0","canonical_sha256":"34c9dcb83c3b3e425b2e7c9858fd41230a565837527e47faddef408b7462111a","source":{"kind":"arxiv","id":"2305.15080","version":2},"attestation_state":"computed","paper":{"title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bado Lee, Daehee Kim, Geewook Kim, Haeji Jung, Hodong Lee, Sangdoo Yun, Sanghee Park, Seunghyun Park, Taeho Kil, Yoonsik Kim","submitted_at":"2023-05-24T11:59:13Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have stimulated a surge of research aimed at extending their applications to the visual domain. While these models exhibit promise in generating abstract image captions and facilitating natural conversations, their performance on text-rich images still requires improvement. In this paper, we introduce Contrastive Reading Model (Cream), a novel neural architecture designed to enhance the language-image understanding capability of LLMs by capturing intricate details that are often overlooked in existing methods. Cream combines vision and auxiliary "},"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":"2305.15080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f4f0e562005e53a16f6cf656446622117d9c9cb5f174c717d72fdbe5b415251","abstract_canon_sha256":"42cd2ab27f3265bc6ddd875471f0e4b148e67fb6d4a0b1aab4726251ce353f26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:31.054281Z","signature_b64":"cX0pGSlkr5hnMEDE6NNHrL7MI3tEQBXWRp8cPyN/ceRBQekA0g13NblJ0lgMixLxF55IVXFibg0QEKX1xyXjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c9dcb83c3b3e425b2e7c9858fd41230a565837527e47faddef408b7462111a","last_reissued_at":"2026-07-05T07:05:31.053851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:31.053851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bado Lee, Daehee Kim, Geewook Kim, Haeji Jung, Hodong Lee, Sangdoo Yun, Sanghee Park, Seunghyun Park, Taeho Kil, Yoonsik Kim","submitted_at":"2023-05-24T11:59:13Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have stimulated a surge of research aimed at extending their applications to the visual domain. While these models exhibit promise in generating abstract image captions and facilitating natural conversations, their performance on text-rich images still requires improvement. In this paper, we introduce Contrastive Reading Model (Cream), a novel neural architecture designed to enhance the language-image understanding capability of LLMs by capturing intricate details that are often overlooked in existing methods. Cream combines vision and auxiliary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15080","kind":"arxiv","version":2},"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/2305.15080/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":"2305.15080","created_at":"2026-07-05T07:05:31.053906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15080v2","created_at":"2026-07-05T07:05:31.053906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15080","created_at":"2026-07-05T07:05:31.053906+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTE5ZOB4HM7E","created_at":"2026-07-05T07:05:31.053906+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTE5ZOB4HM7EEWZO","created_at":"2026-07-05T07:05:31.053906+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTE5ZOB4","created_at":"2026-07-05T07:05:31.053906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM","json":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM.json","graph_json":"https://pith.science/api/pith-number/GTE5ZOB4HM7EEWZOPSMFR7KBEM/graph.json","events_json":"https://pith.science/api/pith-number/GTE5ZOB4HM7EEWZOPSMFR7KBEM/events.json","paper":"https://pith.science/paper/GTE5ZOB4"},"agent_actions":{"view_html":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM","download_json":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM.json","view_paper":"https://pith.science/paper/GTE5ZOB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15080&json=true","fetch_graph":"https://pith.science/api/pith-number/GTE5ZOB4HM7EEWZOPSMFR7KBEM/graph.json","fetch_events":"https://pith.science/api/pith-number/GTE5ZOB4HM7EEWZOPSMFR7KBEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM/action/storage_attestation","attest_author":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM/action/author_attestation","sign_citation":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM/action/citation_signature","submit_replication":"https://pith.science/pith/GTE5ZOB4HM7EEWZOPSMFR7KBEM/action/replication_record"}},"created_at":"2026-07-05T07:05:31.053906+00:00","updated_at":"2026-07-05T07:05:31.053906+00:00"}