{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ","short_pith_number":"pith:6YNX3Y5D","canonical_record":{"source":{"id":"1911.04890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-08T22:01:42Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"86608fce0a1442905e73535928240473d0ac7148924fab5a566370d752452a30","abstract_canon_sha256":"2cc5157ba0e5c115b4c7d40049e88a0dd6a2adf3c1c9a805031ca0f5bc3e5908"},"schema_version":"1.0"},"canonical_sha256":"f61b7de3a36ae9fcc9bd20d8bb561c3652b87a5dbcda4b706e2e738d2e1211e6","source":{"kind":"arxiv","id":"1911.04890","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ","target":"record","payload":{"canonical_record":{"source":{"id":"1911.04890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-08T22:01:42Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"86608fce0a1442905e73535928240473d0ac7148924fab5a566370d752452a30","abstract_canon_sha256":"2cc5157ba0e5c115b4c7d40049e88a0dd6a2adf3c1c9a805031ca0f5bc3e5908"},"schema_version":"1.0"},"canonical_sha256":"f61b7de3a36ae9fcc9bd20d8bb561c3652b87a5dbcda4b706e2e738d2e1211e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:45.951404Z","signature_b64":"prvroouDBvDsOGKz9j0EzBpYTdSIMrMRDKpI0sq9lEWUx1RHCggAIQHnkDJXKU2QVjMBF6r3DIhXvdeO/opUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61b7de3a36ae9fcc9bd20d8bb561c3652b87a5dbcda4b706e2e738d2e1211e6","last_reissued_at":"2026-07-05T00:18:45.950996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:45.950996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.04890","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o56C3Ud/bKGrMN3z+1NBHdpZpg+p1ynZpjdyJEfoefXhb6vifhId0HYP6I2H2YPArnxfA6vhzq/IDmXCo0ykBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:23:17.866335Z"},"content_sha256":"969c267e9b4fa8afd85e0eaba872979c6c6eb8cc386e6dbb3ed0b303789772d9","schema_version":"1.0","event_id":"sha256:969c267e9b4fa8afd85e0eaba872979c6c6eb8cc386e6dbb3ed0b303789772d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","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)","submitted_at":"2019-11-08T22:01:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04890","kind":"arxiv","version":1},"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/1911.04890/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":"2026-07-05T00:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mnkJAXZO4/1Ro8rQXcaT5qHwBRlyx/XbVMUtRjmYPmfx8ZNESa6nq/S1n7DxUKlaztjp8XtusOKtMUf1jwkEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:23:17.866856Z"},"content_sha256":"aed0f10be3bfee1e74ae40dc2489dc4bc8599faaf045c9e2b14fb89ca75d04da","schema_version":"1.0","event_id":"sha256:aed0f10be3bfee1e74ae40dc2489dc4bc8599faaf045c9e2b14fb89ca75d04da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/bundle.json","state_url":"https://pith.science/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/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":"2026-08-11T10:23:17Z","links":{"resolver":"https://pith.science/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ","bundle":"https://pith.science/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/bundle.json","state":"https://pith.science/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YNX3Y5DNLU7ZSN5EDMLWVQ4GZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOJbcyFIZXNmjZ4lhojiv3nYSSupAxNq2gsiTikmABwCjDmbaSOxsPSfuFQmoFix18CO5QzdmlrKGfjnbwDJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:23:17.871982Z","bundle_sha256":"91d9e11f88cc24dcfca332aaaf33070c0db77f29ab0681cf91db9c39e9dcdca7"}}