{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZAWKEQ5WFB6FMQI7RYFAKOY2FP","short_pith_number":"pith:ZAWKEQ5W","canonical_record":{"source":{"id":"2402.05457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T07:21:45Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"8ff1cf44315f4c32252f6dc87c49361e3a1b624fc9995239508d86527330605c","abstract_canon_sha256":"a125ff20e6c14f6fb8def62d8ec5b3222ad41d296fdd4be424d75b875fe3a110"},"schema_version":"1.0"},"canonical_sha256":"c82ca243b6287c56411f8e0a053b1a2bfdfa050514f9ceebbb325bb1445133f9","source":{"kind":"arxiv","id":"2402.05457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05457","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05457v1","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05457","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZAWKEQ5WFB6F","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZAWKEQ5WFB6FMQI7","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZAWKEQ5W","created_at":"2026-07-05T07:42:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZAWKEQ5WFB6FMQI7RYFAKOY2FP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T07:21:45Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"8ff1cf44315f4c32252f6dc87c49361e3a1b624fc9995239508d86527330605c","abstract_canon_sha256":"a125ff20e6c14f6fb8def62d8ec5b3222ad41d296fdd4be424d75b875fe3a110"},"schema_version":"1.0"},"canonical_sha256":"c82ca243b6287c56411f8e0a053b1a2bfdfa050514f9ceebbb325bb1445133f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:50.619418Z","signature_b64":"sY5QVKqnvxorNZk7iZrcHcdQiG7BpkSdD7z8vjP/lSOpomNwzK0vndV9kyi4eE3syBD05aNuWslk/rX8wRtXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c82ca243b6287c56411f8e0a053b1a2bfdfa050514f9ceebbb325bb1445133f9","last_reissued_at":"2026-07-05T07:42:50.618975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:50.618975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05457","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QM5aFBSf08E4dPuOSLPGIaUU3SfwDWm3hzh/C9MRgEkj1LglS+T6HS3vg/gatR/MriXUDnywcS6q4cEoN35/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:48:20.752632Z"},"content_sha256":"400c4884dc97218e8d30ea3dcc2f655af93d6f46b0a20630bbd0166634d596f2","schema_version":"1.0","event_id":"sha256:400c4884dc97218e8d30ea3dcc2f655af93d6f46b0a20630bbd0166634d596f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZAWKEQ5WFB6FMQI7RYFAKOY2FP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Chen Chen, EnSiong Chng, Pin-Yu Chen, Ruizhe Li, Sabato Marco Siniscalchi, Yuchen Hu","submitted_at":"2024-02-08T07:21:45Z","abstract_excerpt":"Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry out a direct mapping from the N-best hypotheses list generated by an ASR system to the predicted output transcription. However, despite its effectiveness, GER introduces extra data uncertainty since the LLM is trained without taking into account acoustic information available in the speech signal. In this work, we aim to overcome such a limitation by infusing aco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05457","kind":"arxiv","version":1},"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/2402.05457/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":"2026-07-05T07:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7KW8TjZoxBFYQmdqv5FqFLctUjMYyLcZaClfCd4zypLP4fnoOvpTv/YTVoSUzDBZyLT8O5EXk6JaO9XpMj9IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:48:20.753139Z"},"content_sha256":"e07daa1e84b17db637c3ef31f6e81a3afe9010160da8f639c87a4fda8a023faa","schema_version":"1.0","event_id":"sha256:e07daa1e84b17db637c3ef31f6e81a3afe9010160da8f639c87a4fda8a023faa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/bundle.json","state_url":"https://pith.science/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/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":"2026-08-17T05:48:20Z","links":{"resolver":"https://pith.science/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP","bundle":"https://pith.science/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/bundle.json","state":"https://pith.science/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAWKEQ5WFB6FMQI7RYFAKOY2FP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAWKEQ5WFB6FMQI7RYFAKOY2FP","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":"a125ff20e6c14f6fb8def62d8ec5b3222ad41d296fdd4be424d75b875fe3a110","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T07:21:45Z","title_canon_sha256":"8ff1cf44315f4c32252f6dc87c49361e3a1b624fc9995239508d86527330605c"},"schema_version":"1.0","source":{"id":"2402.05457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05457","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05457v1","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05457","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZAWKEQ5WFB6F","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZAWKEQ5WFB6FMQI7","created_at":"2026-07-05T07:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZAWKEQ5W","created_at":"2026-07-05T07:42:50Z"}],"graph_snapshots":[{"event_id":"sha256:e07daa1e84b17db637c3ef31f6e81a3afe9010160da8f639c87a4fda8a023faa","target":"graph","created_at":"2026-07-05T07:42:50Z","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/2402.05457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry out a direct mapping from the N-best hypotheses list generated by an ASR system to the predicted output transcription. However, despite its effectiveness, GER introduces extra data uncertainty since the LLM is trained without taking into account acoustic information available in the speech signal. In this work, we aim to overcome such a limitation by infusing aco","authors_text":"Chao-Han Huck Yang, Chen Chen, EnSiong Chng, Pin-Yu Chen, Ruizhe Li, Sabato Marco Siniscalchi, Yuchen Hu","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T07:21:45Z","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05457","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":"sha256:400c4884dc97218e8d30ea3dcc2f655af93d6f46b0a20630bbd0166634d596f2","target":"record","created_at":"2026-07-05T07:42:50Z","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":"a125ff20e6c14f6fb8def62d8ec5b3222ad41d296fdd4be424d75b875fe3a110","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T07:21:45Z","title_canon_sha256":"8ff1cf44315f4c32252f6dc87c49361e3a1b624fc9995239508d86527330605c"},"schema_version":"1.0","source":{"id":"2402.05457","kind":"arxiv","version":1}},"canonical_sha256":"c82ca243b6287c56411f8e0a053b1a2bfdfa050514f9ceebbb325bb1445133f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c82ca243b6287c56411f8e0a053b1a2bfdfa050514f9ceebbb325bb1445133f9","first_computed_at":"2026-07-05T07:42:50.618975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:50.618975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sY5QVKqnvxorNZk7iZrcHcdQiG7BpkSdD7z8vjP/lSOpomNwzK0vndV9kyi4eE3syBD05aNuWslk/rX8wRtXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:50.619418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:400c4884dc97218e8d30ea3dcc2f655af93d6f46b0a20630bbd0166634d596f2","sha256:e07daa1e84b17db637c3ef31f6e81a3afe9010160da8f639c87a4fda8a023faa"],"state_sha256":"60c9be57aa67e8d252dc58df631441c4a983823d06de601f2b2a81e7714a4374"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kye4ZU9XFkUi+/L1NjWjWYutJvf4UPNx67QfFaSNmTGk8xL2NT0ZLEUuA6MUbFh0fuWUpZ31uY9ocrprHaidCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:48:20.761126Z","bundle_sha256":"440671df426af2caeb0cbefcc19ad4f3c80fb57b86f6521961f7bbf9bac58a25"}}