{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4RGXCEP7YXOFJI6IZJMB6BZUSR","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":"7c7348afef343bc5b4dba4f9092a709efd41e89cf51ac5b023058842904ae518","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T14:48:51Z","title_canon_sha256":"9adced908e64b520d76e5c7b14391b650b9416cf00f3e60eb0184f1e23286ea1"},"schema_version":"1.0","source":{"id":"2406.00038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00038","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00038v1","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00038","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"4RGXCEP7YXOF","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"4RGXCEP7YXOFJI6I","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"4RGXCEP7","created_at":"2026-07-05T08:25:55Z"}],"graph_snapshots":[{"event_id":"sha256:3ab3d515dd044c75119f3d03039ac35b70efdbcb0a12be36cb57fcf1c49eff8e","target":"graph","created_at":"2026-07-05T08:25:55Z","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/2406.00038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents an extensive and detailed study on Audio-Visual Speech Recognition (AVSR) for five widely spoken languages: Chinese, Spanish, English, Arabic, and French. We have collected large-scale datasets for each language except for English, and have engaged in the training of supervised learning models. Our model, ViSpeR, is trained in a multi-lingual setting, resulting in competitive performance on newly established benchmarks for each language. The datasets and models are released to the community with an aim to serve as a foundation for triggering and feeding further research work","authors_text":"Ankit Singh, Eustache Le Bihan, Hakim Hacid, Sanath Narayan, Yasser Abdelaziz Dahou Djilali","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T14:48:51Z","title":"ViSpeR: Multilingual Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00038","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:b843c587cb030985e9019d3e8d244a12d48265de0b01f670cf025139558ac754","target":"record","created_at":"2026-07-05T08:25:55Z","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":"7c7348afef343bc5b4dba4f9092a709efd41e89cf51ac5b023058842904ae518","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T14:48:51Z","title_canon_sha256":"9adced908e64b520d76e5c7b14391b650b9416cf00f3e60eb0184f1e23286ea1"},"schema_version":"1.0","source":{"id":"2406.00038","kind":"arxiv","version":1}},"canonical_sha256":"e44d7111ffc5dc54a3c8ca581f0734946fb63e04c17a918e8d555e2f48a9d982","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e44d7111ffc5dc54a3c8ca581f0734946fb63e04c17a918e8d555e2f48a9d982","first_computed_at":"2026-07-05T08:25:55.914190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:55.914190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rfb2riJibks6g1ODXnru+RRbkAb+naV3YmU8CAteZ9wqMJOF7VXs9sQdYqqjnQGHVXJ5moi8Y/VctOCaI4TVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:55.914803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b843c587cb030985e9019d3e8d244a12d48265de0b01f670cf025139558ac754","sha256:3ab3d515dd044c75119f3d03039ac35b70efdbcb0a12be36cb57fcf1c49eff8e"],"state_sha256":"48e16e6b700cc6d4e275c0b659a78a1971b3a68e55f76fbb544c5d40c2c3ad1e"}