{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AC3QYYT5CYRVQGE5DDNCGSLWIC","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":"acf3c084c660d24f988ca6e23e040a95b067562c55f81ea84048881280a350c9","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-03T17:29:52Z","title_canon_sha256":"fbf9058ef1ba2fa8d5fdc539f7c79d19858ccf12eec80e58feed8092521e563a"},"schema_version":"1.0","source":{"id":"2502.01547","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01547","created_at":"2026-07-05T10:59:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01547v3","created_at":"2026-07-05T10:59:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01547","created_at":"2026-07-05T10:59:49Z"},{"alias_kind":"pith_short_12","alias_value":"AC3QYYT5CYRV","created_at":"2026-07-05T10:59:49Z"},{"alias_kind":"pith_short_16","alias_value":"AC3QYYT5CYRVQGE5","created_at":"2026-07-05T10:59:49Z"},{"alias_kind":"pith_short_8","alias_value":"AC3QYYT5","created_at":"2026-07-05T10:59:49Z"}],"graph_snapshots":[{"event_id":"sha256:f2185bead1468c0e546ae9e6072efe670faa57c4a09160ffca6ff577da666660","target":"graph","created_at":"2026-07-05T10:59:49Z","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/2502.01547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) combines lip-based video with audio and can improve performance in noise, but most methods are trained only on English data. One limitation is the lack of large-scale multilingual video data, which makes it hard to train models from scratch. In this work, we propose mWhisper-Flamingo for multilingual AVSR which combines the strengths of a pre-trained audio model (Whisper) and video model (AV-HuBERT). To enable better multi-modal integration and improve the noisy multilingual performance, we introduce decoder modality dropout where the model is trained bot","authors_text":"Andrew Rouditchenko, Hilde Kuehne, James Glass, Rogerio Feris, Samuel Thomas","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-03T17:29:52Z","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01547","kind":"arxiv","version":3},"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":"sha256:67e680b037aaa051f4830e506f8bde8831c539a43b9d48cfb9856dd19acbcf9d","target":"record","created_at":"2026-07-05T10:59:49Z","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":"acf3c084c660d24f988ca6e23e040a95b067562c55f81ea84048881280a350c9","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-03T17:29:52Z","title_canon_sha256":"fbf9058ef1ba2fa8d5fdc539f7c79d19858ccf12eec80e58feed8092521e563a"},"schema_version":"1.0","source":{"id":"2502.01547","kind":"arxiv","version":3}},"canonical_sha256":"00b70c627d162358189d18da23497640a1576d3d26111c59e2037d2e627df94e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00b70c627d162358189d18da23497640a1576d3d26111c59e2037d2e627df94e","first_computed_at":"2026-07-05T10:59:49.025824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:49.025824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sd5u9PlqluAxhQERJmgpzbrObess2ZPn5vEDOWfxECw00xlT4HuJQc0TPNIxhzHfHpg27EHdiEUIVZc/G6eKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:49.026290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01547","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67e680b037aaa051f4830e506f8bde8831c539a43b9d48cfb9856dd19acbcf9d","sha256:f2185bead1468c0e546ae9e6072efe670faa57c4a09160ffca6ff577da666660"],"state_sha256":"6a1a2aba885b5de1426f3ebcfe29222caa803529f99a763444a2bbe55464b8bc"}