{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SMEZ66277TBYFGQHC7N3TWPZCC","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":"2653eec2318286f3e89590af4d998655a50e8d4a09ca1c99e8811050a9e31e1a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T22:38:28Z","title_canon_sha256":"1f8a8679381316168ac15391f69cf97f7dba1dc82e486878e1208d10a2fe89a3"},"schema_version":"1.0","source":{"id":"2211.00174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00174","created_at":"2026-07-05T05:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00174v1","created_at":"2026-07-05T05:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00174","created_at":"2026-07-05T05:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"SMEZ66277TBY","created_at":"2026-07-05T05:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"SMEZ66277TBYFGQH","created_at":"2026-07-05T05:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"SMEZ6627","created_at":"2026-07-05T05:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:8df5f3f52fde48f6324aa25a7731eff93ad456b38992b475bc7060f91f4b9bbb","target":"graph","created_at":"2026-07-05T05:16:37Z","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/2211.00174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy while keeping latency low. One of the latest 2nd-pass rescoring model, Transformer Rescorer, takes the n-best initial outputs and audio embeddings from the 1st-pass model, and then choose the best output by re-scoring the n-best initial outputs. However, training this Transformer Rescorer requires expensive paired audio-text training data because the model us","authors_text":"Duc Le, Jiedan Zhu, Ke Li, Lucas Kabela, Ozlem Kalinli, Rongqing Huang, Suyoun Kim","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T22:38:28Z","title":"Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00174","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":"sha256:8e5b693d8b8c9af1b400399c828764987a9a3b19b343c08eaa7276782b58b1c3","target":"record","created_at":"2026-07-05T05:16:37Z","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":"2653eec2318286f3e89590af4d998655a50e8d4a09ca1c99e8811050a9e31e1a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T22:38:28Z","title_canon_sha256":"1f8a8679381316168ac15391f69cf97f7dba1dc82e486878e1208d10a2fe89a3"},"schema_version":"1.0","source":{"id":"2211.00174","kind":"arxiv","version":1}},"canonical_sha256":"93099f7b5ffcc3829a0717dbb9d9f910b1062085b01180b49da25632d8439048","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93099f7b5ffcc3829a0717dbb9d9f910b1062085b01180b49da25632d8439048","first_computed_at":"2026-07-05T05:16:37.789773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:37.789773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1ij3AI6kvE9iTwSWba8IYJc8sqD5GTby+uRZ+weiSv17HSD+GsTaC74isnA/8b3fEsMErmfEAjiAQm3mIkHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:37.790331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e5b693d8b8c9af1b400399c828764987a9a3b19b343c08eaa7276782b58b1c3","sha256:8df5f3f52fde48f6324aa25a7731eff93ad456b38992b475bc7060f91f4b9bbb"],"state_sha256":"c335aee69458317e6fb4201b4e04cfd3073506c81f11e3667efd3ce77d1b5252"}