{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3UVMOWQRY5WNBFEXQHY6ZBCJ4L","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":"645753527834c31aaa748907e5a34f06643679eb3e19be4b499ae322462bbbfe","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-12-06T18:34:42Z","title_canon_sha256":"45f3f48f117db633646365b2bbf6dc8e881bcc62132d504d2c77517515f22b8e"},"schema_version":"1.0","source":{"id":"2312.03668","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03668","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03668v2","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03668","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"3UVMOWQRY5WN","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"3UVMOWQRY5WNBFEX","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"3UVMOWQR","created_at":"2026-07-05T08:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:5a5dd3126bfaa2de483abda76388a6646de43e2eed50d76bfe3c101083cad809","target":"graph","created_at":"2026-07-05T08:28:04Z","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/2312.03668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E2E approaches utilizing pre-trained models are gaining attention for conserving training data and resources. However, most of their applications in ASR involve only one of either a pre-trained speech or a language model. This paper proposes integrating a pre-trained speech representation model and a large language model (LLM) for E2E ASR. The proposed model enables the optimization of the entire ASR process, includin","authors_text":"Kei Sawada, Kentaro Mitsui, Koh Mitsuda, Tianyu Zhao, Toshiaki Wakatsuki, Yukiya Hono","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-12-06T18:34:42Z","title":"Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03668","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":"sha256:12ac841fa0abd6eb4191282e9f8c424df8407f5db9ad0a2dc94e258714f4fc17","target":"record","created_at":"2026-07-05T08:28:04Z","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":"645753527834c31aaa748907e5a34f06643679eb3e19be4b499ae322462bbbfe","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-12-06T18:34:42Z","title_canon_sha256":"45f3f48f117db633646365b2bbf6dc8e881bcc62132d504d2c77517515f22b8e"},"schema_version":"1.0","source":{"id":"2312.03668","kind":"arxiv","version":2}},"canonical_sha256":"dd2ac75a11c76cd0949781f1ec8449e2c67c905811ae4f6d042c020368fe31c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd2ac75a11c76cd0949781f1ec8449e2c67c905811ae4f6d042c020368fe31c1","first_computed_at":"2026-07-05T08:28:04.107560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:04.107560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ISsqHPboUnhHT3AiOOCkRkyM6iER88cmgluCkeVtjhvKbyON40pHSsFY0bGPrXAsucmo2cSb7dQBBQY+w21rBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:04.108011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03668","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12ac841fa0abd6eb4191282e9f8c424df8407f5db9ad0a2dc94e258714f4fc17","sha256:5a5dd3126bfaa2de483abda76388a6646de43e2eed50d76bfe3c101083cad809"],"state_sha256":"b8ab9cbb8b3d454d9041d7148707e8efd331f3b91dd5b62fb522e9cfb26fc05c"}