{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DTRCKTIAKN3QTYPI4CBIPMDQFH","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":"f5d16f29eb41c78081c5a46b64392612df8786154a2105afeb23ff7568eafb64","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:34:46Z","title_canon_sha256":"3958dad1a684b8461fd97217fe12690d29778431fd609b1bd62df1250313a8d6"},"schema_version":"1.0","source":{"id":"2402.13561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13561","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13561v2","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13561","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"DTRCKTIAKN3Q","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"DTRCKTIAKN3QTYPI","created_at":"2026-07-05T08:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"DTRCKTIA","created_at":"2026-07-05T08:36:46Z"}],"graph_snapshots":[{"event_id":"sha256:427df6246573f3be6b41105a904050c765b94d799f874d4de53726a0cf3ae26d","target":"graph","created_at":"2026-07-05T08:36:46Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.13561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baotian Hu, Haoyuan Shi, Min Zhang, Xinyu Chen, Yunxin Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:34:46Z","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13561","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66e33e3affa49c05d02aeaf43bb3b5cbf6ce39f7331ee91b8ebbebea9ce3f363","target":"record","created_at":"2026-07-05T08:36:46Z","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":"f5d16f29eb41c78081c5a46b64392612df8786154a2105afeb23ff7568eafb64","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:34:46Z","title_canon_sha256":"3958dad1a684b8461fd97217fe12690d29778431fd609b1bd62df1250313a8d6"},"schema_version":"1.0","source":{"id":"2402.13561","kind":"arxiv","version":2}},"canonical_sha256":"1ce2254d00537709e1e8e08287b07029d205bd929c48b4de2bc7676ff52634fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ce2254d00537709e1e8e08287b07029d205bd929c48b4de2bc7676ff52634fa","first_computed_at":"2026-07-05T08:36:46.013720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:46.013720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GJSeHry276UM2rdd9Og+O3oipdrRkD1FV8wvBdhm7rjcLQyKtnllHS3mOzHFGLIFXT3qqRhnU7lKmH+JOObAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:46.014240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e33e3affa49c05d02aeaf43bb3b5cbf6ce39f7331ee91b8ebbebea9ce3f363","sha256:427df6246573f3be6b41105a904050c765b94d799f874d4de53726a0cf3ae26d"],"state_sha256":"4109cb275efac1b8ec282e69b98535ff9d0e6dbee26be9b27d5d528162917ac2"}