{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4P4IOVGM2R464GYORZW3VZ6GQK","short_pith_number":"pith:4P4IOVGM","schema_version":"1.0","canonical_sha256":"e3f88754ccd479ee1b0e8e6dbae7c6829835a953d1995db8bf12650a65947362","source":{"kind":"arxiv","id":"2203.14072","version":2},"attestation_state":"computed","paper":{"title":"Learning 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":"Chenliang Xu, Di Hu, Guangyao Li, Ji-Rong Wen, Yake Wei, Yapeng Tian","submitted_at":"2022-03-26T13:03:42Z","abstract_excerpt":"In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in videos. The problem requires comprehensive multimodal understanding and spatio-temporal reasoning over audio-visual scenes. To benchmark this task and facilitate our study, we introduce a large-scale MUSIC-AVQA dataset, which contains more than 45K question-answer pairs covering 33 different question templates spanning over different modalities and question types. We develop several baselines and introduce a spatio-temp"},"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":"2203.14072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-26T13:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"1d3bc8338c6001488e7d43e6ef2e5b563e8470829636e12387a334b5e4276c04","abstract_canon_sha256":"ace6afd30e296e802eed102605f768c5b47671405b25c67f5278beede0dc76fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:31.287732Z","signature_b64":"wfgymyRjpkeJO1H7w5/+Cl29FvA1ZewjHPHVImay4hsRN3v97isEdQ/g3tYofFezAKbD7suS9/f9Ucl5o708DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3f88754ccd479ee1b0e8e6dbae7c6829835a953d1995db8bf12650a65947362","last_reissued_at":"2026-07-05T04:11:31.287238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:31.287238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning 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":"Chenliang Xu, Di Hu, Guangyao Li, Ji-Rong Wen, Yake Wei, Yapeng Tian","submitted_at":"2022-03-26T13:03:42Z","abstract_excerpt":"In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in videos. The problem requires comprehensive multimodal understanding and spatio-temporal reasoning over audio-visual scenes. To benchmark this task and facilitate our study, we introduce a large-scale MUSIC-AVQA dataset, which contains more than 45K question-answer pairs covering 33 different question templates spanning over different modalities and question types. We develop several baselines and introduce a spatio-temp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14072","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/2203.14072/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":"2203.14072","created_at":"2026-07-05T04:11:31.287288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14072v2","created_at":"2026-07-05T04:11:31.287288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14072","created_at":"2026-07-05T04:11:31.287288+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P4IOVGM2R46","created_at":"2026-07-05T04:11:31.287288+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P4IOVGM2R464GYO","created_at":"2026-07-05T04:11:31.287288+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P4IOVGM","created_at":"2026-07-05T04:11:31.287288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14129","citing_title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK","json":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK.json","graph_json":"https://pith.science/api/pith-number/4P4IOVGM2R464GYORZW3VZ6GQK/graph.json","events_json":"https://pith.science/api/pith-number/4P4IOVGM2R464GYORZW3VZ6GQK/events.json","paper":"https://pith.science/paper/4P4IOVGM"},"agent_actions":{"view_html":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK","download_json":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK.json","view_paper":"https://pith.science/paper/4P4IOVGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14072&json=true","fetch_graph":"https://pith.science/api/pith-number/4P4IOVGM2R464GYORZW3VZ6GQK/graph.json","fetch_events":"https://pith.science/api/pith-number/4P4IOVGM2R464GYORZW3VZ6GQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK/action/storage_attestation","attest_author":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK/action/author_attestation","sign_citation":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK/action/citation_signature","submit_replication":"https://pith.science/pith/4P4IOVGM2R464GYORZW3VZ6GQK/action/replication_record"}},"created_at":"2026-07-05T04:11:31.287288+00:00","updated_at":"2026-07-05T04:11:31.287288+00:00"}