{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AC3QYYT5CYRVQGE5DDNCGSLWIC","short_pith_number":"pith:AC3QYYT5","canonical_record":{"source":{"id":"2502.01547","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-03T17:29:52Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"fbf9058ef1ba2fa8d5fdc539f7c79d19858ccf12eec80e58feed8092521e563a","abstract_canon_sha256":"acf3c084c660d24f988ca6e23e040a95b067562c55f81ea84048881280a350c9"},"schema_version":"1.0"},"canonical_sha256":"00b70c627d162358189d18da23497640a1576d3d26111c59e2037d2e627df94e","source":{"kind":"arxiv","id":"2502.01547","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AC3QYYT5CYRVQGE5DDNCGSLWIC","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01547","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-03T17:29:52Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"fbf9058ef1ba2fa8d5fdc539f7c79d19858ccf12eec80e58feed8092521e563a","abstract_canon_sha256":"acf3c084c660d24f988ca6e23e040a95b067562c55f81ea84048881280a350c9"},"schema_version":"1.0"},"canonical_sha256":"00b70c627d162358189d18da23497640a1576d3d26111c59e2037d2e627df94e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:49.026290Z","signature_b64":"Sd5u9PlqluAxhQERJmgpzbrObess2ZPn5vEDOWfxECw00xlT4HuJQc0TPNIxhzHfHpg27EHdiEUIVZc/G6eKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b70c627d162358189d18da23497640a1576d3d26111c59e2037d2e627df94e","last_reissued_at":"2026-07-05T10:59:49.025824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:49.025824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01547","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GfS+akRxHlZmKqTnPgWhKyf9imzYDbRAoNW1Pm8i4EuATLyZHYnPj+7WSA1FyD5kzia91dD4ucwQKq/qOm3hBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:41:48.158119Z"},"content_sha256":"67e680b037aaa051f4830e506f8bde8831c539a43b9d48cfb9856dd19acbcf9d","schema_version":"1.0","event_id":"sha256:67e680b037aaa051f4830e506f8bde8831c539a43b9d48cfb9856dd19acbcf9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AC3QYYT5CYRVQGE5DDNCGSLWIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Rouditchenko, Hilde Kuehne, James Glass, Rogerio Feris, Samuel Thomas","submitted_at":"2025-02-03T17:29:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01547","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.01547/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DcNbHyYcP5hCoJ3XmtbFCTrAuyBYKNkt21IyK2hkgqVdXQOsH1jljjEDuF/B8BOJD4hET0/GwiW4G/nh884AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:41:48.159210Z"},"content_sha256":"f2185bead1468c0e546ae9e6072efe670faa57c4a09160ffca6ff577da666660","schema_version":"1.0","event_id":"sha256:f2185bead1468c0e546ae9e6072efe670faa57c4a09160ffca6ff577da666660"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/bundle.json","state_url":"https://pith.science/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T21:41:48Z","links":{"resolver":"https://pith.science/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC","bundle":"https://pith.science/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/bundle.json","state":"https://pith.science/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AC3QYYT5CYRVQGE5DDNCGSLWIC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIA0A8jB+AU1U3QYYFd3n0NQj2yMiny6pFqicLrQvF/rXUltZXR6R80CzWKHod0J1bGtzDfeULgEO7b52F1LBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:41:48.165573Z","bundle_sha256":"3ebf574cb6a4cf270fb6c08152f2ec6c873a6b66192837bc7dc221d1a16287ca"}}