{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZHD2GEDBGUSTGO56JQUYHOXSO","short_pith_number":"pith:LZHD2GED","schema_version":"1.0","canonical_sha256":"5e4e3d188309a92999ddf2614c1dd793bb759e24c68586664b4b716ac1f79d82","source":{"kind":"arxiv","id":"2404.12020","version":4},"attestation_state":"computed","paper":{"title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Pei, Jie Ma, Jun Liu, Lingyun Song, Min Hu, Pinghui Wang, Wangchun Sun, Youtian Du","submitted_at":"2024-04-18T09:16:02Z","abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, MUSIC-AVQA-R, crafted in two steps: rephrasing questions within the test split of a public dataset (MUSIC-AVQA) and subsequently introducing di"},"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":"2404.12020","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T09:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"366108334e558455fad8df1e5f90d734f895f9cce5157713a214c71880dd95f2","abstract_canon_sha256":"a43e48e6002fa498733f946a03335d7d624f585b1105245c7fcc2684a1ea56f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:21.437302Z","signature_b64":"8I/vkEuUbgn2SOsKjpJ5Ue9ALudc2F0IUlcaYfkJxThPnuGj2QT3nvIZkU+ljrd6RxCYhn7elczVQNw+M8qiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4e3d188309a92999ddf2614c1dd793bb759e24c68586664b4b716ac1f79d82","last_reissued_at":"2026-07-05T10:24:21.436777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:21.436777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Pei, Jie Ma, Jun Liu, Lingyun Song, Min Hu, Pinghui Wang, Wangchun Sun, Youtian Du","submitted_at":"2024-04-18T09:16:02Z","abstract_excerpt":"Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, MUSIC-AVQA-R, crafted in two steps: rephrasing questions within the test split of a public dataset (MUSIC-AVQA) and subsequently introducing di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12020","kind":"arxiv","version":4},"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/2404.12020/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":"2404.12020","created_at":"2026-07-05T10:24:21.436844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12020v4","created_at":"2026-07-05T10:24:21.436844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12020","created_at":"2026-07-05T10:24:21.436844+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZHD2GEDBGUS","created_at":"2026-07-05T10:24:21.436844+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZHD2GEDBGUSTGO5","created_at":"2026-07-05T10:24:21.436844+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZHD2GED","created_at":"2026-07-05T10:24:21.436844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18346","citing_title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO","json":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO.json","graph_json":"https://pith.science/api/pith-number/LZHD2GEDBGUSTGO56JQUYHOXSO/graph.json","events_json":"https://pith.science/api/pith-number/LZHD2GEDBGUSTGO56JQUYHOXSO/events.json","paper":"https://pith.science/paper/LZHD2GED"},"agent_actions":{"view_html":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO","download_json":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO.json","view_paper":"https://pith.science/paper/LZHD2GED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12020&json=true","fetch_graph":"https://pith.science/api/pith-number/LZHD2GEDBGUSTGO56JQUYHOXSO/graph.json","fetch_events":"https://pith.science/api/pith-number/LZHD2GEDBGUSTGO56JQUYHOXSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO/action/storage_attestation","attest_author":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO/action/author_attestation","sign_citation":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO/action/citation_signature","submit_replication":"https://pith.science/pith/LZHD2GEDBGUSTGO56JQUYHOXSO/action/replication_record"}},"created_at":"2026-07-05T10:24:21.436844+00:00","updated_at":"2026-07-05T10:24:21.436844+00:00"}