{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VKZDG4F6MABT4JKBVD3EM3TSVY","short_pith_number":"pith:VKZDG4F6","schema_version":"1.0","canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","source":{"kind":"arxiv","id":"2403.04640","version":1},"attestation_state":"computed","paper":{"title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Philip Torr, Qilang Ye, Rui Shao, Xiaochun Cao, Xinyu Xie, Zitong Yu","submitted_at":"2024-03-07T16:31:02Z","abstract_excerpt":"This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowl"},"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":"2403.04640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T16:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"a7927ab29b2b3c15f4b11d14e3224b8a57c1702ba2f8da598270e27c81a29c96","abstract_canon_sha256":"428e32ffe81045d70c03bafc48e59cb524f963d376c62db4515ce28755e9d76b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:26.446074Z","signature_b64":"yNCiyp4iPH4+aGVw27iRmW/YR/oIRhNQI6yADPaHvXyheb8RM/Ngh9PgyMpXli/mYS4svkylDTsQ0idyl07NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","last_reissued_at":"2026-07-05T07:53:26.445596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:26.445596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Philip Torr, Qilang Ye, Rui Shao, Xiaochun Cao, Xinyu Xie, Zitong Yu","submitted_at":"2024-03-07T16:31:02Z","abstract_excerpt":"This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04640","kind":"arxiv","version":1},"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/2403.04640/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":"2403.04640","created_at":"2026-07-05T07:53:26.445652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04640v1","created_at":"2026-07-05T07:53:26.445652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04640","created_at":"2026-07-05T07:53:26.445652+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKZDG4F6MABT","created_at":"2026-07-05T07:53:26.445652+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKZDG4F6MABT4JKB","created_at":"2026-07-05T07:53:26.445652+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKZDG4F6","created_at":"2026-07-05T07:53:26.445652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.02327","citing_title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16994","citing_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY","json":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY.json","graph_json":"https://pith.science/api/pith-number/VKZDG4F6MABT4JKBVD3EM3TSVY/graph.json","events_json":"https://pith.science/api/pith-number/VKZDG4F6MABT4JKBVD3EM3TSVY/events.json","paper":"https://pith.science/paper/VKZDG4F6"},"agent_actions":{"view_html":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY","download_json":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY.json","view_paper":"https://pith.science/paper/VKZDG4F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04640&json=true","fetch_graph":"https://pith.science/api/pith-number/VKZDG4F6MABT4JKBVD3EM3TSVY/graph.json","fetch_events":"https://pith.science/api/pith-number/VKZDG4F6MABT4JKBVD3EM3TSVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/action/storage_attestation","attest_author":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/action/author_attestation","sign_citation":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/action/citation_signature","submit_replication":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/action/replication_record"}},"created_at":"2026-07-05T07:53:26.445652+00:00","updated_at":"2026-07-05T07:53:26.445652+00:00"}