{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K6YTCBSMEO5I5UVCZESZFT5G63","short_pith_number":"pith:K6YTCBSM","schema_version":"1.0","canonical_sha256":"57b131064c23ba8ed2a2c92592cfa6f6f052a96d2889002cf496781c2009fba7","source":{"kind":"arxiv","id":"2404.03118","version":3},"attestation_state":"computed","paper":{"title":"LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anahita Bhiwandiwalla, Chenfei Wu, Estelle Aflalo, Gabriela Ben Melech Stan, Matthew Lyle Olson, Nan Duan, Raanan Yehezkel Rohekar, Shao-Yen Tseng, Vasudev Lal, Yaniv Gurwicz","submitted_at":"2024-04-03T23:57:34Z","abstract_excerpt":"In the rapidly evolving landscape of artificial intelligence, multi-modal large language models are emerging as a significant area of interest. These models, which combine various forms of data input, are becoming increasingly popular. However, understanding their internal mechanisms remains a complex task. Numerous advancements have been made in the field of explainability tools and mechanisms, yet there is still much to explore. In this work, we present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is design"},"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":"2404.03118","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-03T23:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"6b0ef2f395b1614add143156165ecc0aab6aad0789c22f0251b6871bb33cb78f","abstract_canon_sha256":"0a4646400910efc090c08ce4b07c4e1b9d32670cddf54e165cc0afa4ea2f0415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:24.966111Z","signature_b64":"7W46QidEoi13kHwbZAmLG+TS0OWKc8/53LJbIbl8AsCsGI9d9IWchY27ScGCnWnIzpfs6IrCeApqMz+rxchNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57b131064c23ba8ed2a2c92592cfa6f6f052a96d2889002cf496781c2009fba7","last_reissued_at":"2026-07-05T08:36:24.965627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:24.965627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anahita Bhiwandiwalla, Chenfei Wu, Estelle Aflalo, Gabriela Ben Melech Stan, Matthew Lyle Olson, Nan Duan, Raanan Yehezkel Rohekar, Shao-Yen Tseng, Vasudev Lal, Yaniv Gurwicz","submitted_at":"2024-04-03T23:57:34Z","abstract_excerpt":"In the rapidly evolving landscape of artificial intelligence, multi-modal large language models are emerging as a significant area of interest. These models, which combine various forms of data input, are becoming increasingly popular. However, understanding their internal mechanisms remains a complex task. Numerous advancements have been made in the field of explainability tools and mechanisms, yet there is still much to explore. In this work, we present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03118","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/2404.03118/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":"2404.03118","created_at":"2026-07-05T08:36:24.965683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03118v3","created_at":"2026-07-05T08:36:24.965683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03118","created_at":"2026-07-05T08:36:24.965683+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6YTCBSMEO5I","created_at":"2026-07-05T08:36:24.965683+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6YTCBSMEO5I5UVC","created_at":"2026-07-05T08:36:24.965683+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6YTCBSM","created_at":"2026-07-05T08:36:24.965683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01189","citing_title":"The Case for Model Science: Verify, Explore, Steer, Refine","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14159","citing_title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12789","citing_title":"Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63","json":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63.json","graph_json":"https://pith.science/api/pith-number/K6YTCBSMEO5I5UVCZESZFT5G63/graph.json","events_json":"https://pith.science/api/pith-number/K6YTCBSMEO5I5UVCZESZFT5G63/events.json","paper":"https://pith.science/paper/K6YTCBSM"},"agent_actions":{"view_html":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63","download_json":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63.json","view_paper":"https://pith.science/paper/K6YTCBSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03118&json=true","fetch_graph":"https://pith.science/api/pith-number/K6YTCBSMEO5I5UVCZESZFT5G63/graph.json","fetch_events":"https://pith.science/api/pith-number/K6YTCBSMEO5I5UVCZESZFT5G63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63/action/storage_attestation","attest_author":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63/action/author_attestation","sign_citation":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63/action/citation_signature","submit_replication":"https://pith.science/pith/K6YTCBSMEO5I5UVCZESZFT5G63/action/replication_record"}},"created_at":"2026-07-05T08:36:24.965683+00:00","updated_at":"2026-07-05T08:36:24.965683+00:00"}