{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UEM7MCZ7HAFD2IVLS2W4QOUCLL","short_pith_number":"pith:UEM7MCZ7","schema_version":"1.0","canonical_sha256":"a119f60b3f380a3d22ab96adc83a825aecb86dab7ce7ece07cf2a24b277d33c5","source":{"kind":"arxiv","id":"2406.13219","version":2},"attestation_state":"computed","paper":{"title":"MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baizhou Huang, Huixuan Zhang, Junzhe Zhang, Xiaojun Wan, Xinyu Hu, Xunjian Yin, Xu Zhang","submitted_at":"2024-06-19T05:15:21Z","abstract_excerpt":"Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not systematically analyzed the performance of editing methods in correcting these two error types. To better represent and correct these errors, we decompose multimodal knowledge into its visual and textual components. Different error types correspond to different editing formats, which edit distinct parts of the multimodal knowledge. We present MC-MKE, a fine-grained M"},"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":"2406.13219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T05:15:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"63f03562abfd37c722960a174a66dc2ff62111bf6504af93656ab87f01ae6902","abstract_canon_sha256":"4ea578344199a37025baf6979c4495007a53457b44836c4ae218b984665e4b33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:32.557087Z","signature_b64":"+t3FrDq15EEeyp+IkG6ZbvJaWwOwZJTCHG9TECjYCJJVdSR9ZojtJLm/dOu8u4reP4Ptl4gzR6SWzRiKWl+CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a119f60b3f380a3d22ab96adc83a825aecb86dab7ce7ece07cf2a24b277d33c5","last_reissued_at":"2026-07-05T09:28:32.556588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:32.556588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baizhou Huang, Huixuan Zhang, Junzhe Zhang, Xiaojun Wan, Xinyu Hu, Xunjian Yin, Xu Zhang","submitted_at":"2024-06-19T05:15:21Z","abstract_excerpt":"Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not systematically analyzed the performance of editing methods in correcting these two error types. To better represent and correct these errors, we decompose multimodal knowledge into its visual and textual components. Different error types correspond to different editing formats, which edit distinct parts of the multimodal knowledge. We present MC-MKE, a fine-grained M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13219","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/2406.13219/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":"2406.13219","created_at":"2026-07-05T09:28:32.556647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13219v2","created_at":"2026-07-05T09:28:32.556647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13219","created_at":"2026-07-05T09:28:32.556647+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEM7MCZ7HAFD","created_at":"2026-07-05T09:28:32.556647+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEM7MCZ7HAFD2IVL","created_at":"2026-07-05T09:28:32.556647+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEM7MCZ7","created_at":"2026-07-05T09:28:32.556647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23780","citing_title":"Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06115","citing_title":"CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06115","citing_title":"CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL","json":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL.json","graph_json":"https://pith.science/api/pith-number/UEM7MCZ7HAFD2IVLS2W4QOUCLL/graph.json","events_json":"https://pith.science/api/pith-number/UEM7MCZ7HAFD2IVLS2W4QOUCLL/events.json","paper":"https://pith.science/paper/UEM7MCZ7"},"agent_actions":{"view_html":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL","download_json":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL.json","view_paper":"https://pith.science/paper/UEM7MCZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13219&json=true","fetch_graph":"https://pith.science/api/pith-number/UEM7MCZ7HAFD2IVLS2W4QOUCLL/graph.json","fetch_events":"https://pith.science/api/pith-number/UEM7MCZ7HAFD2IVLS2W4QOUCLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL/action/storage_attestation","attest_author":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL/action/author_attestation","sign_citation":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL/action/citation_signature","submit_replication":"https://pith.science/pith/UEM7MCZ7HAFD2IVLS2W4QOUCLL/action/replication_record"}},"created_at":"2026-07-05T09:28:32.556647+00:00","updated_at":"2026-07-05T09:28:32.556647+00:00"}