{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OFFMGTFYLDPCOR7I45PZXVKIY5","short_pith_number":"pith:OFFMGTFY","canonical_record":{"source":{"id":"2408.08027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-15T08:50:58Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2259c4e856e844112442886778ab72c44ff5dd175e38180ec4ba07f8fc0a6059","abstract_canon_sha256":"d1a8521567af49aa2b64cbd3edf6feed60c0a19335638a6c0708065ff34ff840"},"schema_version":"1.0"},"canonical_sha256":"714ac34cb858de2747e8e75f9bd548c74bcd345f62418270d3182552eb1aed63","source":{"kind":"arxiv","id":"2408.08027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08027","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08027v2","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08027","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"OFFMGTFYLDPC","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"OFFMGTFYLDPCOR7I","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"OFFMGTFY","created_at":"2026-07-05T09:19:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OFFMGTFYLDPCOR7I45PZXVKIY5","target":"record","payload":{"canonical_record":{"source":{"id":"2408.08027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-15T08:50:58Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2259c4e856e844112442886778ab72c44ff5dd175e38180ec4ba07f8fc0a6059","abstract_canon_sha256":"d1a8521567af49aa2b64cbd3edf6feed60c0a19335638a6c0708065ff34ff840"},"schema_version":"1.0"},"canonical_sha256":"714ac34cb858de2747e8e75f9bd548c74bcd345f62418270d3182552eb1aed63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:11.769489Z","signature_b64":"DEwnMGm2Q2OKkv0K/RPlGcaKQ/n2gKSUrp+6s10Pxaalu04p7+DDqpqRT4lXP61e55XcJ4fJfSZm9eJJF1AjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"714ac34cb858de2747e8e75f9bd548c74bcd345f62418270d3182552eb1aed63","last_reissued_at":"2026-07-05T09:19:11.768997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:11.768997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.08027","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":"2026-07-05T09:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcI33TyDx2WPmIcma3l4SFADCDSSLLSpDfkcN+56VThIz9bOHAdrW9S9HhGiQWSDZEIYHGb3W7eOZQq/JA5BDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:14:09.912571Z"},"content_sha256":"6e4a83157e56b71b8408458acdb713d52972880e62f63589b9d4c591c0ed9285","schema_version":"1.0","event_id":"sha256:6e4a83157e56b71b8408458acdb713d52972880e62f63589b9d4c591c0ed9285"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OFFMGTFYLDPCOR7I45PZXVKIY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Kento Nozawa, Takashi Masuko, Toru Taniguchi","submitted_at":"2024-08-15T08:50:58Z","abstract_excerpt":"We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM, PLaMo-100B, pre-trained from scratch using datasets dominated by Japanese and English texts as the decoder. We adopt a pre-trained Whisper encoder as an audio encoder, and the audio embeddings from the audio encoder are projected to the text embedding space by an adapter layer and concatenated with text embeddings converted from text prompts to form inputs to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08027","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/2408.08027/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":"2026-07-05T09:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DH0UfBDUL1avgXa+5qfErQ3D56acvpsTgjwV4MtMW2LtRd6WT00hHgItBFdrT60WUpwtr9VjzJMQPKHEuLTHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:14:09.912961Z"},"content_sha256":"320008f1669d41ac790c0e1849d1a660b5db539fc1bab9fe2c2bde332b729ab0","schema_version":"1.0","event_id":"sha256:320008f1669d41ac790c0e1849d1a660b5db539fc1bab9fe2c2bde332b729ab0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/bundle.json","state_url":"https://pith.science/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/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":"2026-07-08T17:14:09Z","links":{"resolver":"https://pith.science/pith/OFFMGTFYLDPCOR7I45PZXVKIY5","bundle":"https://pith.science/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/bundle.json","state":"https://pith.science/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFFMGTFYLDPCOR7I45PZXVKIY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OFFMGTFYLDPCOR7I45PZXVKIY5","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":"d1a8521567af49aa2b64cbd3edf6feed60c0a19335638a6c0708065ff34ff840","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-15T08:50:58Z","title_canon_sha256":"2259c4e856e844112442886778ab72c44ff5dd175e38180ec4ba07f8fc0a6059"},"schema_version":"1.0","source":{"id":"2408.08027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08027","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08027v2","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08027","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"OFFMGTFYLDPC","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"OFFMGTFYLDPCOR7I","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"OFFMGTFY","created_at":"2026-07-05T09:19:11Z"}],"graph_snapshots":[{"event_id":"sha256:320008f1669d41ac790c0e1849d1a660b5db539fc1bab9fe2c2bde332b729ab0","target":"graph","created_at":"2026-07-05T09:19:11Z","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/2408.08027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM, PLaMo-100B, pre-trained from scratch using datasets dominated by Japanese and English texts as the decoder. We adopt a pre-trained Whisper encoder as an audio encoder, and the audio embeddings from the audio encoder are projected to the text embedding space by an adapter layer and concatenated with text embeddings converted from text prompts to form inputs to th","authors_text":"Kento Nozawa, Takashi Masuko, Toru Taniguchi","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-15T08:50:58Z","title":"Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08027","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":"sha256:6e4a83157e56b71b8408458acdb713d52972880e62f63589b9d4c591c0ed9285","target":"record","created_at":"2026-07-05T09:19:11Z","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":"d1a8521567af49aa2b64cbd3edf6feed60c0a19335638a6c0708065ff34ff840","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-15T08:50:58Z","title_canon_sha256":"2259c4e856e844112442886778ab72c44ff5dd175e38180ec4ba07f8fc0a6059"},"schema_version":"1.0","source":{"id":"2408.08027","kind":"arxiv","version":2}},"canonical_sha256":"714ac34cb858de2747e8e75f9bd548c74bcd345f62418270d3182552eb1aed63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"714ac34cb858de2747e8e75f9bd548c74bcd345f62418270d3182552eb1aed63","first_computed_at":"2026-07-05T09:19:11.768997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:11.768997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DEwnMGm2Q2OKkv0K/RPlGcaKQ/n2gKSUrp+6s10Pxaalu04p7+DDqpqRT4lXP61e55XcJ4fJfSZm9eJJF1AjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:11.769489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e4a83157e56b71b8408458acdb713d52972880e62f63589b9d4c591c0ed9285","sha256:320008f1669d41ac790c0e1849d1a660b5db539fc1bab9fe2c2bde332b729ab0"],"state_sha256":"87239a22238a44cfda94759a0fcfde87a5a826a2561b40576d8ad629cd89a181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dda0X69uu/sXiY2nwrisdXJ5NX4fVIN4f3WGSqNNvPuShGzXjydhdPQMqZ3OzEeKsP7t4aCMgBhTrIs/23t+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T17:14:09.916051Z","bundle_sha256":"4b5c3a530674da21e023b82ea890d16cd200f28c49336360fc4bbfc24b0c589b"}}