{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5ZMKGHKLSOOPS6WXITZ6BOACXZ","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":"72d7f40eede655fb467e5085e833cf3c14c689fba5b900cd78f1e9aa927c4010","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T09:14:31Z","title_canon_sha256":"d9f175c4dfdf3336a7c468e257a3e3d22a8ad1485ea3a8c852a4419ad72c446c"},"schema_version":"1.0","source":{"id":"2410.00528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00528","created_at":"2026-07-05T09:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00528v1","created_at":"2026-07-05T09:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00528","created_at":"2026-07-05T09:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"5ZMKGHKLSOOP","created_at":"2026-07-05T09:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"5ZMKGHKLSOOPS6WX","created_at":"2026-07-05T09:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"5ZMKGHKL","created_at":"2026-07-05T09:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:e149fd555aa2cc3b3992b7ca5b1a50361c5c4d5edf52b01ef9fa85b644398162","target":"graph","created_at":"2026-07-05T09:14:06Z","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/2410.00528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are specifically designed to effectively integrate pre-trained LMs (e.g., BERT) into end-to-end ASR models. BERT-CTC adapts BERT for connectionist temporal classification (CTC) by addressing the constraint of the conditional independence assumption between output tokens. This enables explicit conditioning of BERT's contextualized embeddings in the ASR process, seamles","authors_text":"Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T09:14:31Z","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00528","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":"sha256:66b9e154eeb3ce89e8733dffd79983feab049d04e70126b31c2a6fcd7f953f81","target":"record","created_at":"2026-07-05T09:14:06Z","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":"72d7f40eede655fb467e5085e833cf3c14c689fba5b900cd78f1e9aa927c4010","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T09:14:31Z","title_canon_sha256":"d9f175c4dfdf3336a7c468e257a3e3d22a8ad1485ea3a8c852a4419ad72c446c"},"schema_version":"1.0","source":{"id":"2410.00528","kind":"arxiv","version":1}},"canonical_sha256":"ee58a31d4b939cf97ad744f3e0b802be628cc92277ad582c5cffb5c0ff898441","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee58a31d4b939cf97ad744f3e0b802be628cc92277ad582c5cffb5c0ff898441","first_computed_at":"2026-07-05T09:14:06.157878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:06.157878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mIbqjcLFozUofYThm+agJrB48rxhNKDfR6aoZCFlmoUSvTd0E9YQhW2iwdN3nUwqDyYKqywB9kaex4Eofr9ECw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:06.158346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66b9e154eeb3ce89e8733dffd79983feab049d04e70126b31c2a6fcd7f953f81","sha256:e149fd555aa2cc3b3992b7ca5b1a50361c5c4d5edf52b01ef9fa85b644398162"],"state_sha256":"752b903f6110f57f7838f6e4a318779d8676876dcd61cd458ab2ca9f46b7573c"}