{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7BPB43YHCIQE35U5TOLRPJFJAM","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":"3d6ad2d046ad45ee07c9d1e47f1da6603755fe0a208df32936e3617395875b08","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-05T19:38:54Z","title_canon_sha256":"09dd842d7c3a6a5e0e9a675d4e784a5c5928d502aa67dfbca2fb3b5418223316"},"schema_version":"1.0","source":{"id":"2011.03072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03072","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03072v1","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03072","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"7BPB43YHCIQE","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"7BPB43YHCIQE35U5","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"7BPB43YH","created_at":"2026-07-05T01:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:2dca85b7a61104ce1c3219e509a64a75a88a1c55cdb7e095da199578b0c59287","target":"graph","created_at":"2026-07-05T01:53:00Z","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/2011.03072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal alignment of the training transcripts and audio. As a result, RNN-T models built with uni-directional long short term memory (LSTM) encoders tend to wait for longer spans of input audio, before streaming already decoded ASR tokens. In this work, we propose a modification to the RNN-T loss function and develop Alignment Restricted RNN-T (Ar-RNN-T) models, whic","authors_text":"Ching-Feng Yeh, Christian Fuegen, Duc Le, Gil Keren, Hang Su, Jay Mahadeokar, Michael L. Seltzer, Thong Le, Yuan Shangguan","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-05T19:38:54Z","title":"Alignment Restricted Streaming Recurrent Neural Network Transducer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03072","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:a803985d7451910e7b6b483c72b12e88c04c415c86e220acd212dd4cce0a3f0c","target":"record","created_at":"2026-07-05T01:53:00Z","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":"3d6ad2d046ad45ee07c9d1e47f1da6603755fe0a208df32936e3617395875b08","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-05T19:38:54Z","title_canon_sha256":"09dd842d7c3a6a5e0e9a675d4e784a5c5928d502aa67dfbca2fb3b5418223316"},"schema_version":"1.0","source":{"id":"2011.03072","kind":"arxiv","version":1}},"canonical_sha256":"f85e1e6f0712204df69d9b9717a4a9032961ae88da5fb6e67854e413bff8eb09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f85e1e6f0712204df69d9b9717a4a9032961ae88da5fb6e67854e413bff8eb09","first_computed_at":"2026-07-05T01:53:00.052260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:00.052260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n/cUpi9w6jzR7SBEtVgepCbjyl/M/AKO5D46tjHtVvrL6KYZornkiVLjARqH5ZOCp7k1TxNeYyGyHs52jEawAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:00.052709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a803985d7451910e7b6b483c72b12e88c04c415c86e220acd212dd4cce0a3f0c","sha256:2dca85b7a61104ce1c3219e509a64a75a88a1c55cdb7e095da199578b0c59287"],"state_sha256":"8e0f5fdd317be386d8734c7b7f67a2ba3e6893e634cc9ff74026a0b6f8399fdd"}