{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4P4IOVGM2R464GYORZW3VZ6GQK","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":"ace6afd30e296e802eed102605f768c5b47671405b25c67f5278beede0dc76fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-26T13:03:42Z","title_canon_sha256":"1d3bc8338c6001488e7d43e6ef2e5b563e8470829636e12387a334b5e4276c04"},"schema_version":"1.0","source":{"id":"2203.14072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14072","created_at":"2026-07-05T04:11:31Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14072v2","created_at":"2026-07-05T04:11:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14072","created_at":"2026-07-05T04:11:31Z"},{"alias_kind":"pith_short_12","alias_value":"4P4IOVGM2R46","created_at":"2026-07-05T04:11:31Z"},{"alias_kind":"pith_short_16","alias_value":"4P4IOVGM2R464GYO","created_at":"2026-07-05T04:11:31Z"},{"alias_kind":"pith_short_8","alias_value":"4P4IOVGM","created_at":"2026-07-05T04:11:31Z"}],"graph_snapshots":[{"event_id":"sha256:5c1c49667bc89f936225cd7e8111f4616f48756f1f33591d70297b134042f160","target":"graph","created_at":"2026-07-05T04:11:31Z","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/2203.14072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenliang Xu, Di Hu, Guangyao Li, Ji-Rong Wen, Yake Wei, Yapeng Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-26T13:03:42Z","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14072","kind":"arxiv","version":2},"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":"sha256:21d2dd03efe7638f788ef26d6358a97dcba8426797a8769cbee2879d342f7ec2","target":"record","created_at":"2026-07-05T04:11:31Z","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":"ace6afd30e296e802eed102605f768c5b47671405b25c67f5278beede0dc76fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-26T13:03:42Z","title_canon_sha256":"1d3bc8338c6001488e7d43e6ef2e5b563e8470829636e12387a334b5e4276c04"},"schema_version":"1.0","source":{"id":"2203.14072","kind":"arxiv","version":2}},"canonical_sha256":"e3f88754ccd479ee1b0e8e6dbae7c6829835a953d1995db8bf12650a65947362","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3f88754ccd479ee1b0e8e6dbae7c6829835a953d1995db8bf12650a65947362","first_computed_at":"2026-07-05T04:11:31.287238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:31.287238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wfgymyRjpkeJO1H7w5/+Cl29FvA1ZewjHPHVImay4hsRN3v97isEdQ/g3tYofFezAKbD7suS9/f9Ucl5o708DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:31.287732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.14072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21d2dd03efe7638f788ef26d6358a97dcba8426797a8769cbee2879d342f7ec2","sha256:5c1c49667bc89f936225cd7e8111f4616f48756f1f33591d70297b134042f160"],"state_sha256":"4923566ce45f845492ad42ffb0e7112e324719d96c4a37397283884cef051409"}