{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DTRCKTIAKN3QTYPI4CBIPMDQFH","short_pith_number":"pith:DTRCKTIA","schema_version":"1.0","canonical_sha256":"1ce2254d00537709e1e8e08287b07029d205bd929c48b4de2bc7676ff52634fa","source":{"kind":"arxiv","id":"2402.13561","version":2},"attestation_state":"computed","paper":{"title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Haoyuan Shi, Min Zhang, Xinyu Chen, Yunxin Li","submitted_at":"2024-02-21T06:34:46Z","abstract_excerpt":"Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alig"},"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":"2402.13561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:34:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3958dad1a684b8461fd97217fe12690d29778431fd609b1bd62df1250313a8d6","abstract_canon_sha256":"f5d16f29eb41c78081c5a46b64392612df8786154a2105afeb23ff7568eafb64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:46.014240Z","signature_b64":"2GJSeHry276UM2rdd9Og+O3oipdrRkD1FV8wvBdhm7rjcLQyKtnllHS3mOzHFGLIFXT3qqRhnU7lKmH+JOObAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce2254d00537709e1e8e08287b07029d205bd929c48b4de2bc7676ff52634fa","last_reissued_at":"2026-07-05T08:36:46.013720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:46.013720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Haoyuan Shi, Min Zhang, Xinyu Chen, Yunxin Li","submitted_at":"2024-02-21T06:34:46Z","abstract_excerpt":"Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13561","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/2402.13561/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":"2402.13561","created_at":"2026-07-05T08:36:46.013778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13561v2","created_at":"2026-07-05T08:36:46.013778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13561","created_at":"2026-07-05T08:36:46.013778+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTRCKTIAKN3Q","created_at":"2026-07-05T08:36:46.013778+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTRCKTIAKN3QTYPI","created_at":"2026-07-05T08:36:46.013778+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTRCKTIA","created_at":"2026-07-05T08:36:46.013778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH","json":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH.json","graph_json":"https://pith.science/api/pith-number/DTRCKTIAKN3QTYPI4CBIPMDQFH/graph.json","events_json":"https://pith.science/api/pith-number/DTRCKTIAKN3QTYPI4CBIPMDQFH/events.json","paper":"https://pith.science/paper/DTRCKTIA"},"agent_actions":{"view_html":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH","download_json":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH.json","view_paper":"https://pith.science/paper/DTRCKTIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13561&json=true","fetch_graph":"https://pith.science/api/pith-number/DTRCKTIAKN3QTYPI4CBIPMDQFH/graph.json","fetch_events":"https://pith.science/api/pith-number/DTRCKTIAKN3QTYPI4CBIPMDQFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH/action/storage_attestation","attest_author":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH/action/author_attestation","sign_citation":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH/action/citation_signature","submit_replication":"https://pith.science/pith/DTRCKTIAKN3QTYPI4CBIPMDQFH/action/replication_record"}},"created_at":"2026-07-05T08:36:46.013778+00:00","updated_at":"2026-07-05T08:36:46.013778+00:00"}