{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OEKBYRAV4ZLODQMCQCJP5EA254","short_pith_number":"pith:OEKBYRAV","canonical_record":{"source":{"id":"2403.14402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-21T13:52:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"0302e9c8f4f9847705bc23e49b4eecd4483b7fa1d55d81c86c988136891c953f","abstract_canon_sha256":"1994895b107f7903bff55a13f008411346514ff4388df87fa220918bbb108cec"},"schema_version":"1.0"},"canonical_sha256":"71141c4415e656e1c1828092fe901aef0cc5cacefc5879e0ab2b883cca0a4f07","source":{"kind":"arxiv","id":"2403.14402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14402","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14402v2","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14402","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"OEKBYRAV4ZLO","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"OEKBYRAV4ZLODQMC","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"OEKBYRAV","created_at":"2026-07-05T08:54:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OEKBYRAV4ZLODQMCQCJP5EA254","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-21T13:52:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"0302e9c8f4f9847705bc23e49b4eecd4483b7fa1d55d81c86c988136891c953f","abstract_canon_sha256":"1994895b107f7903bff55a13f008411346514ff4388df87fa220918bbb108cec"},"schema_version":"1.0"},"canonical_sha256":"71141c4415e656e1c1828092fe901aef0cc5cacefc5879e0ab2b883cca0a4f07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:08.891800Z","signature_b64":"9vArv2+QVmJK1jd1cai7Lc1jpN6hXfFHR8FKh/5NatGGcjjYxXxH6aibFEsl/OwSyChzMBnCdTOZoHfmN9OwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71141c4415e656e1c1828092fe901aef0cc5cacefc5879e0ab2b883cca0a4f07","last_reissued_at":"2026-07-05T08:54:08.891251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:08.891251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14402","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xi7Bc3FBnVUwl3iX0O1fkT9JFfvmjr/2ohB7ExFujTtVaTcX1Ir1yD1YgrIsMH4iTnxoCUk5395f2TfNftGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:56:14.856604Z"},"content_sha256":"a1408a284ce13b282ad7212672195ff98b84b5549a43a7572812cdc9096e8a23","schema_version":"1.0","event_id":"sha256:a1408a284ce13b282ad7212672195ff98b84b5549a43a7572812cdc9096e8a23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OEKBYRAV4ZLODQMCQCJP5EA254","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bowen Shi, Changhan Wang, HyoJung Han, Juan Pino, Marine Carpuat, Mohamed Anwar, Wei-Ning Hsu","submitted_at":"2024-03-21T13:52:17Z","abstract_excerpt":"Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual (AV) data is only available in limited amounts and for fewer languages than audio-only resources. To address this gap, we present XLAVS-R, a cross-lingual audio-visual speech representation model for noise-robust speech recognition and translation in over 100 languages. It is designed to maximize the benefits of limited multilingual AV pre-training data, by bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14402","kind":"arxiv","version":2},"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/2403.14402/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":"2026-07-05T08:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1tZ3nvl9+tnk5KUBFrq2fLdZ928qVkeMUAA4vGllEPOe+eqwq7Q1k67yJVVdVIru4URTRQtQQYmmqwYS2VYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:56:14.857563Z"},"content_sha256":"c29198ecc5166ddd8e95a038456f1cbbe0f7f25ed647a898daf4917f69d84260","schema_version":"1.0","event_id":"sha256:c29198ecc5166ddd8e95a038456f1cbbe0f7f25ed647a898daf4917f69d84260"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEKBYRAV4ZLODQMCQCJP5EA254/bundle.json","state_url":"https://pith.science/pith/OEKBYRAV4ZLODQMCQCJP5EA254/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEKBYRAV4ZLODQMCQCJP5EA254/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":"2026-08-17T04:56:14Z","links":{"resolver":"https://pith.science/pith/OEKBYRAV4ZLODQMCQCJP5EA254","bundle":"https://pith.science/pith/OEKBYRAV4ZLODQMCQCJP5EA254/bundle.json","state":"https://pith.science/pith/OEKBYRAV4ZLODQMCQCJP5EA254/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEKBYRAV4ZLODQMCQCJP5EA254/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OEKBYRAV4ZLODQMCQCJP5EA254","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":"1994895b107f7903bff55a13f008411346514ff4388df87fa220918bbb108cec","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-21T13:52:17Z","title_canon_sha256":"0302e9c8f4f9847705bc23e49b4eecd4483b7fa1d55d81c86c988136891c953f"},"schema_version":"1.0","source":{"id":"2403.14402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14402","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14402v2","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14402","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"OEKBYRAV4ZLO","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"OEKBYRAV4ZLODQMC","created_at":"2026-07-05T08:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"OEKBYRAV","created_at":"2026-07-05T08:54:08Z"}],"graph_snapshots":[{"event_id":"sha256:c29198ecc5166ddd8e95a038456f1cbbe0f7f25ed647a898daf4917f69d84260","target":"graph","created_at":"2026-07-05T08:54:08Z","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/2403.14402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual (AV) data is only available in limited amounts and for fewer languages than audio-only resources. To address this gap, we present XLAVS-R, a cross-lingual audio-visual speech representation model for noise-robust speech recognition and translation in over 100 languages. It is designed to maximize the benefits of limited multilingual AV pre-training data, by bu","authors_text":"Bowen Shi, Changhan Wang, HyoJung Han, Juan Pino, Marine Carpuat, Mohamed Anwar, Wei-Ning Hsu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-21T13:52:17Z","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14402","kind":"arxiv","version":2},"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:a1408a284ce13b282ad7212672195ff98b84b5549a43a7572812cdc9096e8a23","target":"record","created_at":"2026-07-05T08:54:08Z","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":"1994895b107f7903bff55a13f008411346514ff4388df87fa220918bbb108cec","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-21T13:52:17Z","title_canon_sha256":"0302e9c8f4f9847705bc23e49b4eecd4483b7fa1d55d81c86c988136891c953f"},"schema_version":"1.0","source":{"id":"2403.14402","kind":"arxiv","version":2}},"canonical_sha256":"71141c4415e656e1c1828092fe901aef0cc5cacefc5879e0ab2b883cca0a4f07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71141c4415e656e1c1828092fe901aef0cc5cacefc5879e0ab2b883cca0a4f07","first_computed_at":"2026-07-05T08:54:08.891251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:08.891251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9vArv2+QVmJK1jd1cai7Lc1jpN6hXfFHR8FKh/5NatGGcjjYxXxH6aibFEsl/OwSyChzMBnCdTOZoHfmN9OwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:08.891800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1408a284ce13b282ad7212672195ff98b84b5549a43a7572812cdc9096e8a23","sha256:c29198ecc5166ddd8e95a038456f1cbbe0f7f25ed647a898daf4917f69d84260"],"state_sha256":"747a992468ccd9ef9b6c9ab9e8803ae49f9ac0f328e813fecbd068c4a5ac977a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYOjoofpJYsmuZ5vLv9FTU9GqYWrw/4KvYwa6CJAyQKOa9BsMY48+FKLSdDQCJjPv7DBD3wxIJK07mhyZ9+RBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:56:14.949512Z","bundle_sha256":"4f438b116230de9711904e28919d542ed93a8c01aa893ffc9c5bcd0c9b0694e1"}}