{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7RGKZWF5AQSJTKGEFBLLM5ZXKU","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":"c07eb41a228180e7b7c56b416f2f16e10a0302d1a6a0af39342800c316c290a3","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-19T17:42:56Z","title_canon_sha256":"a2dbaa19aa39d1fe6307bd049fcaa1d9382e185812a6fb3702bf6d8f77262c38"},"schema_version":"1.0","source":{"id":"1909.09116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.09116","created_at":"2026-07-05T01:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"1909.09116v2","created_at":"2026-07-05T01:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09116","created_at":"2026-07-05T01:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"7RGKZWF5AQSJ","created_at":"2026-07-05T01:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"7RGKZWF5AQSJTKGE","created_at":"2026-07-05T01:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"7RGKZWF5","created_at":"2026-07-05T01:01:00Z"}],"graph_snapshots":[{"event_id":"sha256:c9ff765718acefc04c977894b84d97bef22a4b0d4b6eab6796855650e4bf141f","target":"graph","created_at":"2026-07-05T01:01:00Z","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/1909.09116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and language model used to generate the pseudo-labels, filtering mechanisms tailored to common errors from sequence-to-sequence models, and a novel ensemble approach to increase pseudo-label diversity. Experiments on the LibriSpeech corpus show that with an ensemble of four models and label filtering, self-training yields a 33.9% relative improvement in WER compare","authors_text":"Ann Lee, Awni Hannun, Jacob Kahn","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-19T17:42:56Z","title":"Self-Training for End-to-End Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09116","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":"sha256:1cc29623849d8425f1127dc1342ec9546075b327b6c5eb93fcab6b98ed0d4046","target":"record","created_at":"2026-07-05T01:01:00Z","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":"c07eb41a228180e7b7c56b416f2f16e10a0302d1a6a0af39342800c316c290a3","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-19T17:42:56Z","title_canon_sha256":"a2dbaa19aa39d1fe6307bd049fcaa1d9382e185812a6fb3702bf6d8f77262c38"},"schema_version":"1.0","source":{"id":"1909.09116","kind":"arxiv","version":2}},"canonical_sha256":"fc4cacd8bd042499a8c42856b6773755009050608f6fa6a6d75b8fea1a33ebd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc4cacd8bd042499a8c42856b6773755009050608f6fa6a6d75b8fea1a33ebd6","first_computed_at":"2026-07-05T01:01:00.463422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:00.463422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PBv8DmyutRiDa23aPFHes8uxwG2lzU49v7s0H5wxzTSvVyaJUEFnjeebjuPBCCSahNLzlSOEvEazQAEgSB6nCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:00.463845Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.09116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc29623849d8425f1127dc1342ec9546075b327b6c5eb93fcab6b98ed0d4046","sha256:c9ff765718acefc04c977894b84d97bef22a4b0d4b6eab6796855650e4bf141f"],"state_sha256":"fa0facb51f447d085d5a6e09c9c610ce81b408a32608ff1d54cd8d9664af8f6c"}