{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J2EL2EHQODVPNKLTUN52LOKRRX","short_pith_number":"pith:J2EL2EHQ","canonical_record":{"source":{"id":"2309.10707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"19b933ed69b2c6e39bfc4b9e27de9282aa8f93307d95c33af743ce0ff12bf99f","abstract_canon_sha256":"6d1a84cae9011f37670cf1cc44ca3eab61658f5521e09b5d0ddf22bc7e96657a"},"schema_version":"1.0"},"canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","source":{"kind":"arxiv","id":"2309.10707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10707","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10707v1","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10707","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"J2EL2EHQODVP","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"J2EL2EHQODVPNKLT","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"J2EL2EHQ","created_at":"2026-07-05T06:52:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J2EL2EHQODVPNKLTUN52LOKRRX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"19b933ed69b2c6e39bfc4b9e27de9282aa8f93307d95c33af743ce0ff12bf99f","abstract_canon_sha256":"6d1a84cae9011f37670cf1cc44ca3eab61658f5521e09b5d0ddf22bc7e96657a"},"schema_version":"1.0"},"canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:15.762379Z","signature_b64":"uPWiWyuvtVlItvQuU/Q1CKviiOmv9HAnCruo1DRrYgf50o9Gjzg5skotqBFVFA3K0g6by2K6K1fXyFxA86LXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","last_reissued_at":"2026-07-05T06:52:15.761877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:15.761877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10707","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":"2026-07-05T06:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XdtnAsRS0zh+RWLOQOyxc7NXjzSa8Big1kP1x4wFjcmNmOwWkKdc694WgRM/LbwT2hEOexrBER/Nrwwk2oICCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:04.898969Z"},"content_sha256":"cb732e30e632e40624a50b4225efb5bcc733725fac225dfabaed5d3ef84137b2","schema_version":"1.0","event_id":"sha256:cb732e30e632e40624a50b4225efb5bcc733725fac225dfabaed5d3ef84137b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J2EL2EHQODVPNKLTUN52LOKRRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gautam Varma Mantena, Hema Swetha Koppula, Hsuan Su, Jen-Hao Rick Chang, Karren Yang, Oncel Tuzel, Raviteja Vemulapalli, Ting-Yao Hu","submitted_at":"2023-09-18T15:43:08Z","abstract_excerpt":"While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10707","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/2309.10707/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":"2026-07-05T06:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nn0udbjGkKBR2POP1GXzUh058E1wSqFTGEog+sd2j1lsGm7KP0WJkLswZooN3TByasQlufIcD1Srl9axahOyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:04.899371Z"},"content_sha256":"96233e46aef41e30304c98d090eac97f7fba7538bd99c55fae57098975aa5d0a","schema_version":"1.0","event_id":"sha256:96233e46aef41e30304c98d090eac97f7fba7538bd99c55fae57098975aa5d0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/bundle.json","state_url":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2EL2EHQODVPNKLTUN52LOKRRX/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":"2026-07-06T23:31:04Z","links":{"resolver":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX","bundle":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/bundle.json","state":"https://pith.science/pith/J2EL2EHQODVPNKLTUN52LOKRRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2EL2EHQODVPNKLTUN52LOKRRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J2EL2EHQODVPNKLTUN52LOKRRX","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":"6d1a84cae9011f37670cf1cc44ca3eab61658f5521e09b5d0ddf22bc7e96657a","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","title_canon_sha256":"19b933ed69b2c6e39bfc4b9e27de9282aa8f93307d95c33af743ce0ff12bf99f"},"schema_version":"1.0","source":{"id":"2309.10707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10707","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10707v1","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10707","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"J2EL2EHQODVP","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"J2EL2EHQODVPNKLT","created_at":"2026-07-05T06:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"J2EL2EHQ","created_at":"2026-07-05T06:52:15Z"}],"graph_snapshots":[{"event_id":"sha256:96233e46aef41e30304c98d090eac97f7fba7538bd99c55fae57098975aa5d0a","target":"graph","created_at":"2026-07-05T06:52:15Z","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/2309.10707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech","authors_text":"Gautam Varma Mantena, Hema Swetha Koppula, Hsuan Su, Jen-Hao Rick Chang, Karren Yang, Oncel Tuzel, Raviteja Vemulapalli, Ting-Yao Hu","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10707","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:cb732e30e632e40624a50b4225efb5bcc733725fac225dfabaed5d3ef84137b2","target":"record","created_at":"2026-07-05T06:52:15Z","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":"6d1a84cae9011f37670cf1cc44ca3eab61658f5521e09b5d0ddf22bc7e96657a","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-18T15:43:08Z","title_canon_sha256":"19b933ed69b2c6e39bfc4b9e27de9282aa8f93307d95c33af743ce0ff12bf99f"},"schema_version":"1.0","source":{"id":"2309.10707","kind":"arxiv","version":1}},"canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e88bd10f070eaf6a973a37ba5b9518dd5d5e998aa414e7a1af92294f3074a54","first_computed_at":"2026-07-05T06:52:15.761877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:15.761877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPWiWyuvtVlItvQuU/Q1CKviiOmv9HAnCruo1DRrYgf50o9Gjzg5skotqBFVFA3K0g6by2K6K1fXyFxA86LXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:15.762379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb732e30e632e40624a50b4225efb5bcc733725fac225dfabaed5d3ef84137b2","sha256:96233e46aef41e30304c98d090eac97f7fba7538bd99c55fae57098975aa5d0a"],"state_sha256":"72222c0e585bd9d6358b93eff76f6ab8f06dfed119b6fc5f8cea8e4ac6cd01ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4B0sc1vQL7MRQgyCm2WdU6cvNuyLjz+7wWQIlkqd3pdkjfEKhUnlfPDL0fOo07Fxp72VvJTR4AlAOVTh4TSLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:31:04.901394Z","bundle_sha256":"c33080c23f4c68d20a3ba2859e56285ec11e4b8591513cde6823fd1d5a70b362"}}