{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EXNI7KLW2N3MQPHJNB3PH7DL5B","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":"587986183a739f5cda67ba4c413f9bf0833b9d19b763273fa4cc8ccf7b09a7c0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:13:04Z","title_canon_sha256":"9218ed690e459af7868b9a69fa00c3e6dfc495ce102b10e9b9d0caece386af41"},"schema_version":"1.0","source":{"id":"2112.08718","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08718","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08718v3","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08718","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"EXNI7KLW2N3M","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"EXNI7KLW2N3MQPHJ","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"EXNI7KLW","created_at":"2026-07-05T04:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:13fab4fb861e8586e03870ac67f7d0a49e66dda178cee31e8c80766df8075309","target":"graph","created_at":"2026-07-05T04:42:32Z","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/2112.08718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains creating a need to adapt to new domains with small memory and deployment overhead. In this work, we introduce domain-prompts, a methodology that involves training a small number of domain embedding parameters to prime a Transformer-based Language Model (LM) to a particular domain. Using this domain-adapted LM for rescoring ASR hypotheses can achieve 7-13% WER reduction for a new domain with just 1000 unlabeled textual domain-specific sentences. This improvement is compara","authors_text":"Ankur Gandhe, Ashish Shenoy, Katrin Kirchhoff, Ravi Teja Gadde, Saket Dingliwal, Sravan Bodapati","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:13:04Z","title":"Prompt Tuning GPT-2 language model for parameter-efficient domain adaptation of ASR systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08718","kind":"arxiv","version":3},"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":"sha256:6f1d71980bebf2416289d7ac8cc682650f339552ca594a0d042415cb586ed3e2","target":"record","created_at":"2026-07-05T04:42:32Z","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":"587986183a739f5cda67ba4c413f9bf0833b9d19b763273fa4cc8ccf7b09a7c0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:13:04Z","title_canon_sha256":"9218ed690e459af7868b9a69fa00c3e6dfc495ce102b10e9b9d0caece386af41"},"schema_version":"1.0","source":{"id":"2112.08718","kind":"arxiv","version":3}},"canonical_sha256":"25da8fa976d376c83ce96876f3fc6be85474ba20a1aeba9bdf342e4d8bfe710a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25da8fa976d376c83ce96876f3fc6be85474ba20a1aeba9bdf342e4d8bfe710a","first_computed_at":"2026-07-05T04:42:32.574682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:32.574682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Li8tCtcxAVgtiP2VbVhcCxn2BpqC3NBP8w+dm0AfQ3/xp2CsrBbkWD5m23A7ahXQQLpF1LvyLOCKLFHZL9kVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:32.575271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08718","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f1d71980bebf2416289d7ac8cc682650f339552ca594a0d042415cb586ed3e2","sha256:13fab4fb861e8586e03870ac67f7d0a49e66dda178cee31e8c80766df8075309"],"state_sha256":"ea5b6bba578d541d5a04eb85d76251d728f61c19c0fdb47467502583f733d05b"}