{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VKZDG4F6MABT4JKBVD3EM3TSVY","short_pith_number":"pith:VKZDG4F6","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"},"canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","source":{"kind":"arxiv","id":"2403.04640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04640","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04640v1","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04640","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"VKZDG4F6MABT","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"VKZDG4F6MABT4JKB","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"VKZDG4F6","created_at":"2026-07-05T07:53:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VKZDG4F6MABT4JKBVD3EM3TSVY","target":"record","payload":{"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"},"canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","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"},"source_kind":"arxiv","source_id":"2403.04640","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/KZhwNG2yPHaMPqna+vl/oJ46eGZ5TgLBl8+222h+fOQwoqtTvRRPEWkS1YTnrFVk4GQzearx2iceTIjG2BCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:15:25.126460Z"},"content_sha256":"eea3c4ad0784a48845c6f9fa04541222afdb64516570fc37a06737384d0e3f4f","schema_version":"1.0","event_id":"sha256:eea3c4ad0784a48845c6f9fa04541222afdb64516570fc37a06737384d0e3f4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VKZDG4F6MABT4JKBVD3EM3TSVY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NORFOelgVw/FzeNFKQ9vtNCpM1zhbQqHbSdU2yMeunU8PLrJAE6oBvuA5nhCAGO2oFdAa81d6o6HfqdsxioqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:15:25.127357Z"},"content_sha256":"4c0120820a5802da5105c75e216863133df633f4a0432ed8805a82283c7a526c","schema_version":"1.0","event_id":"sha256:4c0120820a5802da5105c75e216863133df633f4a0432ed8805a82283c7a526c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/bundle.json","state_url":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T16:15:25Z","links":{"resolver":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY","bundle":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/bundle.json","state":"https://pith.science/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKZDG4F6MABT4JKBVD3EM3TSVY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VKZDG4F6MABT4JKBVD3EM3TSVY","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":"428e32ffe81045d70c03bafc48e59cb524f963d376c62db4515ce28755e9d76b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T16:31:02Z","title_canon_sha256":"a7927ab29b2b3c15f4b11d14e3224b8a57c1702ba2f8da598270e27c81a29c96"},"schema_version":"1.0","source":{"id":"2403.04640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04640","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04640v1","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04640","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"VKZDG4F6MABT","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"VKZDG4F6MABT4JKB","created_at":"2026-07-05T07:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"VKZDG4F6","created_at":"2026-07-05T07:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:4c0120820a5802da5105c75e216863133df633f4a0432ed8805a82283c7a526c","target":"graph","created_at":"2026-07-05T07:53:26Z","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/2403.04640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Philip Torr, Qilang Ye, Rui Shao, Xiaochun Cao, Xinyu Xie, Zitong Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T16:31:02Z","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04640","kind":"arxiv","version":1},"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:eea3c4ad0784a48845c6f9fa04541222afdb64516570fc37a06737384d0e3f4f","target":"record","created_at":"2026-07-05T07:53:26Z","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":"428e32ffe81045d70c03bafc48e59cb524f963d376c62db4515ce28755e9d76b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T16:31:02Z","title_canon_sha256":"a7927ab29b2b3c15f4b11d14e3224b8a57c1702ba2f8da598270e27c81a29c96"},"schema_version":"1.0","source":{"id":"2403.04640","kind":"arxiv","version":1}},"canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aab23370be60033e2541a8f6466e72ae3dc2609d68b814d7ab01ff51ec99600b","first_computed_at":"2026-07-05T07:53:26.445596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:26.445596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNCiyp4iPH4+aGVw27iRmW/YR/oIRhNQI6yADPaHvXyheb8RM/Ngh9PgyMpXli/mYS4svkylDTsQ0idyl07NAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:26.446074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eea3c4ad0784a48845c6f9fa04541222afdb64516570fc37a06737384d0e3f4f","sha256:4c0120820a5802da5105c75e216863133df633f4a0432ed8805a82283c7a526c"],"state_sha256":"c2f38ea44c980732cf96867df1bb3c89377fa3dd70c953e6f0c1b0d805b10d40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdDVLajDDG3YWb8t599nnt4+q2iKHdazcctwPzvakbJjR7lSswlvsSfsSOBiNCWoeLAZFmo/x2/tFKzKduSsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:15:25.141291Z","bundle_sha256":"ee9848f1591c5f9097f26ec2e53d80215cafb5279eb3abff3ceeab89b05508cf"}}