{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37YYULFFMGVZA64UQW4UVS7N4R","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":"327be9db772c112af93de067e38d5b6b05308f187263fa427b3d0d8d40fdd428","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T00:26:45Z","title_canon_sha256":"615ef8bb87d65eda716c83a5f72e7878c4ca61caea84c7f825e4117c85fe1291"},"schema_version":"1.0","source":{"id":"2412.19005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19005","created_at":"2026-07-05T09:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19005v1","created_at":"2026-07-05T09:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19005","created_at":"2026-07-05T09:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"37YYULFFMGVZ","created_at":"2026-07-05T09:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"37YYULFFMGVZA64U","created_at":"2026-07-05T09:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"37YYULFF","created_at":"2026-07-05T09:54:14Z"}],"graph_snapshots":[{"event_id":"sha256:400db6ca7af4a3dbfa3767f9196e19d7e702cb2767ef90c355716b0eacb292c0","target":"graph","created_at":"2026-07-05T09:54:14Z","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/2412.19005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-world scenarios across various domains due to noisy acoustic environments, spontaneous speech, and the uncertain use of visual information. Most previous works fine-tune audio-only ASR models on audiovisual datasets, optimizing them for conventional ASR objectives. However, they often neglect visual features and common errors in unconstrained video scenarios. In this paper, we propose using a preference optimization str","authors_text":"Ruihua Song, Shinji Watanabe, Xihua Wang, Yichen Lu, Yifan Peng, Yihan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T00:26:45Z","title":"Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19005","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:dee28904b1c626388458526b49432d54ad3f7fee9e06967ba103a6cbd0adda58","target":"record","created_at":"2026-07-05T09:54:14Z","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":"327be9db772c112af93de067e38d5b6b05308f187263fa427b3d0d8d40fdd428","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T00:26:45Z","title_canon_sha256":"615ef8bb87d65eda716c83a5f72e7878c4ca61caea84c7f825e4117c85fe1291"},"schema_version":"1.0","source":{"id":"2412.19005","kind":"arxiv","version":1}},"canonical_sha256":"dff18a2ca561ab907b9485b94acbede452e6631a43e6aa9fdbf13e2e80643d8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dff18a2ca561ab907b9485b94acbede452e6631a43e6aa9fdbf13e2e80643d8f","first_computed_at":"2026-07-05T09:54:14.618445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:14.618445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gJVzl3Iv8uHVwBejC0j/N0V13QJPnE6UImo70SYPS3sGlGrT9jaO+2VfDGwB0VB+5lVM79g5cWXMmBEZ/DRTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:14.618844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dee28904b1c626388458526b49432d54ad3f7fee9e06967ba103a6cbd0adda58","sha256:400db6ca7af4a3dbfa3767f9196e19d7e702cb2767ef90c355716b0eacb292c0"],"state_sha256":"9ad8e647987b43fd3b231a2eb10e5e5716ef00b7176d7fd76000ddcc044afbab"}