{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REFISX67ADMVZ2TA5YMIWDUQKZ","short_pith_number":"pith:REFISX67","schema_version":"1.0","canonical_sha256":"890a895fdf00d95cea60ee188b0e905668efff92d089f29aa06b77fb21d4a744","source":{"kind":"arxiv","id":"2403.07350","version":3},"attestation_state":"computed","paper":{"title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Haitian Zhong, Han Huang, Liang Wang, Qiang Liu, Shu Wu, Tao Yu, Tieniu Tan","submitted_at":"2024-03-12T06:16:33Z","abstract_excerpt":"Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to constru"},"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":"2403.07350","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T06:16:33Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c80ea565ae59616706e2ca93338e5d9100fd56569cd48f13d035a4be0823c4f6","abstract_canon_sha256":"4bcaf2058a12a71aba90c3e38a1eb11a2675bfe74067c0e3084023e9681ff8d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:52.797776Z","signature_b64":"VRk1kyy/PbZ4fhPIAVq9DcTNgGDBCN3qmmrLsjlAw52YtxNYqM3jlFcBJnb+VYgI7+GDlqUFyMj/qMLPCX2mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890a895fdf00d95cea60ee188b0e905668efff92d089f29aa06b77fb21d4a744","last_reissued_at":"2026-07-05T09:27:52.797291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:52.797291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Haitian Zhong, Han Huang, Liang Wang, Qiang Liu, Shu Wu, Tao Yu, Tieniu Tan","submitted_at":"2024-03-12T06:16:33Z","abstract_excerpt":"Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to constru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07350","kind":"arxiv","version":3},"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/2403.07350/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":"2403.07350","created_at":"2026-07-05T09:27:52.797369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07350v3","created_at":"2026-07-05T09:27:52.797369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07350","created_at":"2026-07-05T09:27:52.797369+00:00"},{"alias_kind":"pith_short_12","alias_value":"REFISX67ADMV","created_at":"2026-07-05T09:27:52.797369+00:00"},{"alias_kind":"pith_short_16","alias_value":"REFISX67ADMVZ2TA","created_at":"2026-07-05T09:27:52.797369+00:00"},{"alias_kind":"pith_short_8","alias_value":"REFISX67","created_at":"2026-07-05T09:27:52.797369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05714","citing_title":"Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ","json":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ.json","graph_json":"https://pith.science/api/pith-number/REFISX67ADMVZ2TA5YMIWDUQKZ/graph.json","events_json":"https://pith.science/api/pith-number/REFISX67ADMVZ2TA5YMIWDUQKZ/events.json","paper":"https://pith.science/paper/REFISX67"},"agent_actions":{"view_html":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ","download_json":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ.json","view_paper":"https://pith.science/paper/REFISX67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07350&json=true","fetch_graph":"https://pith.science/api/pith-number/REFISX67ADMVZ2TA5YMIWDUQKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/REFISX67ADMVZ2TA5YMIWDUQKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ/action/storage_attestation","attest_author":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ/action/author_attestation","sign_citation":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ/action/citation_signature","submit_replication":"https://pith.science/pith/REFISX67ADMVZ2TA5YMIWDUQKZ/action/replication_record"}},"created_at":"2026-07-05T09:27:52.797369+00:00","updated_at":"2026-07-05T09:27:52.797369+00:00"}