{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RKFTRFEZMEDIIJ4CGYXQL7DZ7W","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":"92c8fd429fd267bd6cd6580f7dcc7d051966e0e1219204e484516caedccf1759","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-28T07:08:17Z","title_canon_sha256":"b8a2589abbb73f13c7c7d04185aa9a6e740cb2a136319cddf21fcc62754d1ec6"},"schema_version":"1.0","source":{"id":"2505.22045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22045","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22045v1","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22045","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_12","alias_value":"RKFTRFEZMEDI","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_16","alias_value":"RKFTRFEZMEDIIJ4C","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_8","alias_value":"RKFTRFEZ","created_at":"2026-07-05T11:11:08Z"}],"graph_snapshots":[{"event_id":"sha256:eb9142ab95f7f23a4c826c176a797ffff5bdc83522c9995eaf57ca4e11f02563","target":"graph","created_at":"2026-07-05T11:11:08Z","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/2505.22045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current vision-guided audio captioning systems frequently fail to address audiovisual misalignment in real-world scenarios, such as dubbed content or off-screen sounds. To bridge this critical gap, we present an entropy-aware gated fusion framework that dynamically modulates visual information flow through cross-modal uncertainty quantification. Our novel approach employs attention entropy analysis in cross-attention layers to automatically identify and suppress misleading visual cues during modal fusion. Complementing this architecture, we develop a batch-wise audiovisual shuffling technique ","authors_text":"Chenxing Li, Dong Yu, Le Xu, Ruibo Fu, Shan Yang, Yong Ren, Yu Gu, Yujie Chen","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-28T07:08:17Z","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22045","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:c99b397cdb620c8e2d2dcda82f2bae3e408c9b97260a5b5b28d62c153cfdd4f4","target":"record","created_at":"2026-07-05T11:11:08Z","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":"92c8fd429fd267bd6cd6580f7dcc7d051966e0e1219204e484516caedccf1759","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-28T07:08:17Z","title_canon_sha256":"b8a2589abbb73f13c7c7d04185aa9a6e740cb2a136319cddf21fcc62754d1ec6"},"schema_version":"1.0","source":{"id":"2505.22045","kind":"arxiv","version":1}},"canonical_sha256":"8a8b3894996106842782362f05fc79fd94ceba8eda49bdc946525279892e09fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a8b3894996106842782362f05fc79fd94ceba8eda49bdc946525279892e09fb","first_computed_at":"2026-07-05T11:11:08.764829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:08.764829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vl+F2FKMA0bXTVgMr65K3quksy6MmJpVKEpMmnwG2GZFL6PHTVbe4ExGf5uuwNh/Ov0Gc8Sa7QsB4xqHM3EqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:08.765393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c99b397cdb620c8e2d2dcda82f2bae3e408c9b97260a5b5b28d62c153cfdd4f4","sha256:eb9142ab95f7f23a4c826c176a797ffff5bdc83522c9995eaf57ca4e11f02563"],"state_sha256":"99b12e5f420fc01fb9cdc10a96ad01d06168805e843132e5783f06a2bf0af2ad"}