{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AA7QQVI2SDMBZ2F7GPINWQ6TJS","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":"d57f06ce26595bf5816b0ffb22b718e71898662c57d7177cf5f6cf1d92eacdff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T15:53:13Z","title_canon_sha256":"29093bfbc7e1518f241ac8ca44eaefa33f7d5924f4d86da5114db41acde0bd46"},"schema_version":"1.0","source":{"id":"2411.17537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17537","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17537v1","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17537","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"AA7QQVI2SDMB","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"AA7QQVI2SDMBZ2F7","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"AA7QQVI2","created_at":"2026-07-05T09:40:48Z"}],"graph_snapshots":[{"event_id":"sha256:1827b25509fae9b6e9d05e8a57f7c3979a88769d9b4b6ecdf8f703efdadecabe","target":"graph","created_at":"2026-07-05T09:40:48Z","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/2411.17537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and latency. In the conventional framework, streaming transducer models are trained to maximize the likelihood function based on non-streaming recursion rules. However, this approach leads to a mismatch between training and inference, resulting in the issue of deformed likelihood and consequently suboptimal ASR accuracy. We introduce a mathematical quantification of the gap between the actual likelihood and the deformed","authors_text":"Hyeonseung Lee, Ji Won Yoon, Nam Soo Kim, Sungsoo Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T15:53:13Z","title":"Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17537","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":"sha256:747c9666dc9947e8c07b5459073e667a41d547336883f30b199d327859e2662e","target":"record","created_at":"2026-07-05T09:40:48Z","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":"d57f06ce26595bf5816b0ffb22b718e71898662c57d7177cf5f6cf1d92eacdff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T15:53:13Z","title_canon_sha256":"29093bfbc7e1518f241ac8ca44eaefa33f7d5924f4d86da5114db41acde0bd46"},"schema_version":"1.0","source":{"id":"2411.17537","kind":"arxiv","version":1}},"canonical_sha256":"003f08551a90d81ce8bf33d0db43d34c9d9433cac4aa8ea75eac55c3618245aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"003f08551a90d81ce8bf33d0db43d34c9d9433cac4aa8ea75eac55c3618245aa","first_computed_at":"2026-07-05T09:40:48.657597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:48.657597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7qhNYJWtoB467ML+ghWZWAA6mq6VRNVIHQ7mnV+I08GyFZj8MSSu5MAvyEQ43AnDoKpKoJHLALk6EARgcbjwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:48.658043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:747c9666dc9947e8c07b5459073e667a41d547336883f30b199d327859e2662e","sha256:1827b25509fae9b6e9d05e8a57f7c3979a88769d9b4b6ecdf8f703efdadecabe"],"state_sha256":"e1d1e5281755f6cb74b20287119dc85dc421c14c8e66bb4be64c5cfbba6548cf"}