{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBSADHGCTH6LICL75BWVU5O7OZ","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":"64715e2ec426496c62a6f425a576fc8f6366bd3616d6cea7840cf26d41ddae31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T12:51:37Z","title_canon_sha256":"402da5c9cc5b5ddfbba2db6e853813c52737654fba9d006c2ab109aef189ced6"},"schema_version":"1.0","source":{"id":"2403.06679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06679","created_at":"2026-07-05T07:54:41Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06679v1","created_at":"2026-07-05T07:54:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06679","created_at":"2026-07-05T07:54:41Z"},{"alias_kind":"pith_short_12","alias_value":"RBSADHGCTH6L","created_at":"2026-07-05T07:54:41Z"},{"alias_kind":"pith_short_16","alias_value":"RBSADHGCTH6LICL7","created_at":"2026-07-05T07:54:41Z"},{"alias_kind":"pith_short_8","alias_value":"RBSADHGC","created_at":"2026-07-05T07:54:41Z"}],"graph_snapshots":[{"event_id":"sha256:2d9afbe45c040a6c46abd15662e29085b34f1c3834cb9e8ae010a8555f6f5e0c","target":"graph","created_at":"2026-07-05T07:54:41Z","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/2403.06679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to interact with questions facilitates the multimodal fusion process, the redundancy of audio-visual parameters tends to reduce the generalization of the inference engine to multiple question-answer pairs in a single video. Indeed, the natural heterogeneous relationship between audiovisuals and text makes the perfect fusion challenging, to prevent high-level audio-v","authors_text":"Qilang Ye, Xin Liu, Zitong Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T12:51:37Z","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06679","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:ce7de5420d6787720c1fe93a6c347acc3d17e838cd1b5d2b63cfebe13c926180","target":"record","created_at":"2026-07-05T07:54:41Z","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":"64715e2ec426496c62a6f425a576fc8f6366bd3616d6cea7840cf26d41ddae31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T12:51:37Z","title_canon_sha256":"402da5c9cc5b5ddfbba2db6e853813c52737654fba9d006c2ab109aef189ced6"},"schema_version":"1.0","source":{"id":"2403.06679","kind":"arxiv","version":1}},"canonical_sha256":"8864019cc299fcb4097fe86d5a75df76554efe9f7eb6610f1bf11d92a598cd95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8864019cc299fcb4097fe86d5a75df76554efe9f7eb6610f1bf11d92a598cd95","first_computed_at":"2026-07-05T07:54:41.398622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:41.398622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1+ahzmZFl3f2VSqCoHWAUWlOnUpVhURUoVIP+pSXB2OUPVO/GFXx0yuFqXKHKucSs84eqcffmWSAbc2+nI8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:41.399156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce7de5420d6787720c1fe93a6c347acc3d17e838cd1b5d2b63cfebe13c926180","sha256:2d9afbe45c040a6c46abd15662e29085b34f1c3834cb9e8ae010a8555f6f5e0c"],"state_sha256":"fad167830113af9bc094f39d043eeea90852f90b721554fd991d9e400158ca2d"}