{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CMLEP6DZY53XY3QCE74GRT4EE4","short_pith_number":"pith:CMLEP6DZ","canonical_record":{"source":{"id":"2309.08876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0","abstract_canon_sha256":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c"},"schema_version":"1.0"},"canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","source":{"kind":"arxiv","id":"2309.08876","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08876v2","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_12","alias_value":"CMLEP6DZY53X","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"CMLEP6DZY53XY3QC","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"CMLEP6DZ","created_at":"2026-07-05T07:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CMLEP6DZY53XY3QCE74GRT4EE4","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0","abstract_canon_sha256":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c"},"schema_version":"1.0"},"canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:31.950083Z","signature_b64":"vk/a44iO4afC/jO4oVVEX3ODTDQI2vuIk+JUbRc9OOeylPDx4VUez9Htkb8+F9yvcVL15xKZOQ6tVVxAlQe7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","last_reissued_at":"2026-07-05T07:31:31.949542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:31.949542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08876","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:31:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXv01oQQmpMRphQHr2ZNr3z2MeuLzYXgfIwZanTPxKtwT7aq3hLtMtPaAltXiRNDRmtsl6bpo5VAPhS1RZEpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:58:29.007887Z"},"content_sha256":"0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971","schema_version":"1.0","event_id":"sha256:0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CMLEP6DZY53XY3QCE74GRT4EE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-09-16T04:57:37Z","abstract_excerpt":"Collecting audio-text pairs is expensive; however, it is much easier to access text-only data. Unless using shallow fusion, end-to-end automatic speech recognition (ASR) models require architecture modifications or additional training schemes to use text-only data. Inspired by recent advances in decoder-only language models (LMs), such as GPT-3 and PaLM adopted for speech-processing tasks, we propose using a decoder-only architecture for ASR with simple text augmentation. To provide audio information, encoder features compressed by CTC prediction are used as prompts for the decoder, which can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08876","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.08876/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:31:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+wFv9AexAclgQ6SXNyoteuWYHvYt2a1Jocq+cS+GDrVyLDRUVim6BcYvYtTmCQKgUMi86qHsWwq61xYEcgcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:58:29.008402Z"},"content_sha256":"f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d","schema_version":"1.0","event_id":"sha256:f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMLEP6DZY53XY3QCE74GRT4EE4/bundle.json","state_url":"https://pith.science/pith/CMLEP6DZY53XY3QCE74GRT4EE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMLEP6DZY53XY3QCE74GRT4EE4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T07:58:29Z","links":{"resolver":"https://pith.science/pith/CMLEP6DZY53XY3QCE74GRT4EE4","bundle":"https://pith.science/pith/CMLEP6DZY53XY3QCE74GRT4EE4/bundle.json","state":"https://pith.science/pith/CMLEP6DZY53XY3QCE74GRT4EE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMLEP6DZY53XY3QCE74GRT4EE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CMLEP6DZY53XY3QCE74GRT4EE4","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":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0"},"schema_version":"1.0","source":{"id":"2309.08876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08876v2","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_12","alias_value":"CMLEP6DZY53X","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"CMLEP6DZY53XY3QC","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"CMLEP6DZ","created_at":"2026-07-05T07:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d","target":"graph","created_at":"2026-07-05T07:31:31Z","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/2309.08876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collecting audio-text pairs is expensive; however, it is much easier to access text-only data. Unless using shallow fusion, end-to-end automatic speech recognition (ASR) models require architecture modifications or additional training schemes to use text-only data. Inspired by recent advances in decoder-only language models (LMs), such as GPT-3 and PaLM adopted for speech-processing tasks, we propose using a decoder-only architecture for ASR with simple text augmentation. To provide audio information, encoder features compressed by CTC prediction are used as prompts for the decoder, which can ","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08876","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":"sha256:0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971","target":"record","created_at":"2026-07-05T07:31:31Z","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":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0"},"schema_version":"1.0","source":{"id":"2309.08876","kind":"arxiv","version":2}},"canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","first_computed_at":"2026-07-05T07:31:31.949542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:31.949542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vk/a44iO4afC/jO4oVVEX3ODTDQI2vuIk+JUbRc9OOeylPDx4VUez9Htkb8+F9yvcVL15xKZOQ6tVVxAlQe7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:31.950083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971","sha256:f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d"],"state_sha256":"ad53009295e23bfd9a0cac9c7ac1fa1afcbcedf1390665c81725e086d68dd127"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+YlFMWf8DZz18KCpptk7bC8nIoxYnVNUMeKQtuF81JJ86Yt2RF+vQeYM5slCJ95TRJ5RwU6bQPG48gbqchGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:58:29.013198Z","bundle_sha256":"0547e552bace2acc10a8735c9f8aa6f2e017bb8f80c71ef568434982073924f7"}}