{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ","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":"2cc5157ba0e5c115b4c7d40049e88a0dd6a2adf3c1c9a805031ca0f5bc3e5908","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-08T22:01:42Z","title_canon_sha256":"86608fce0a1442905e73535928240473d0ac7148924fab5a566370d752452a30"},"schema_version":"1.0","source":{"id":"1911.04890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04890","created_at":"2026-07-05T00:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04890v1","created_at":"2026-07-05T00:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04890","created_at":"2026-07-05T00:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"6YNX3Y5DNLU7","created_at":"2026-07-05T00:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"6YNX3Y5DNLU7ZSN5","created_at":"2026-07-05T00:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"6YNX3Y5D","created_at":"2026-07-05T00:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:aed0f10be3bfee1e74ae40dc2489dc4bc8599faaf045c9e2b14fb89ca75d04da","target":"graph","created_at":"2026-07-05T00:18:45Z","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/1911.04890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of segmented utterances extracted from YouTube public videos, leading to 31k hours of audio-visual training content. The performance of an audio-only, visual-only, and audio-visual system are compared on two large-vocabulary test sets: a set of utterance segments from public YouTube videos called YTDEV18 and the publicly available LRS3-TED set. To highlight the contri","authors_text":"Basilio Garcia (1), Brendan Shillingford (2), Hank Liao (1), Olivier Siohan (1) ((1) Google Inc. (2) DeepMind), Otavio Braga (1), Takaki Makino (1), Yannis Assael (2)","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-08T22:01:42Z","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04890","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":"sha256:969c267e9b4fa8afd85e0eaba872979c6c6eb8cc386e6dbb3ed0b303789772d9","target":"record","created_at":"2026-07-05T00:18:45Z","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":"2cc5157ba0e5c115b4c7d40049e88a0dd6a2adf3c1c9a805031ca0f5bc3e5908","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-08T22:01:42Z","title_canon_sha256":"86608fce0a1442905e73535928240473d0ac7148924fab5a566370d752452a30"},"schema_version":"1.0","source":{"id":"1911.04890","kind":"arxiv","version":1}},"canonical_sha256":"f61b7de3a36ae9fcc9bd20d8bb561c3652b87a5dbcda4b706e2e738d2e1211e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f61b7de3a36ae9fcc9bd20d8bb561c3652b87a5dbcda4b706e2e738d2e1211e6","first_computed_at":"2026-07-05T00:18:45.950996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:18:45.950996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"prvroouDBvDsOGKz9j0EzBpYTdSIMrMRDKpI0sq9lEWUx1RHCggAIQHnkDJXKU2QVjMBF6r3DIhXvdeO/opUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:18:45.951404Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.04890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:969c267e9b4fa8afd85e0eaba872979c6c6eb8cc386e6dbb3ed0b303789772d9","sha256:aed0f10be3bfee1e74ae40dc2489dc4bc8599faaf045c9e2b14fb89ca75d04da"],"state_sha256":"d688d061657a5464ea26266898f3c632f1bec3094551b9ba5a25eb3069c5aa0f"}