{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6DYOAMZZAHQNKK55BXTQ7QT3F7","short_pith_number":"pith:6DYOAMZZ","schema_version":"1.0","canonical_sha256":"f0f0e0333901e0d52bbd0de70fc27b2ffbb8c165bc7ca83018ebf99e54a72caf","source":{"kind":"arxiv","id":"2301.02736","version":1},"attestation_state":"computed","paper":{"title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Bj\\\"orn Hoffmeister, David M. Chan, Shalini Ghosh","submitted_at":"2023-01-06T22:32:50Z","abstract_excerpt":"Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating increased data collection), and rapidly shifting data distributions (requiring more frequent model fine-tuning). In this work, we investigate the potential of leveraging external knowledge, particularly through off-policy key-value stores generated with text-to-speech methods, to allow for flexible post-training adaptation to new data distributions. In our approach,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.02736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-01-06T22:32:50Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"9200b0742a7c4ce507fce3e646155892502e4d14e99fac00ec9c9c92d30c4978","abstract_canon_sha256":"f6b8eb1a5d2fb6a7cbf82791c320488e53cb5d68be9bd5f8a921c2cba057e0e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:21.056478Z","signature_b64":"y4Cpw0Vu/oDEELLL2Hll3fzPKz/sCrF21DgaY8jwA7Mr38H6oIA5IT5R1Tk9aJjxxL6gcFelqy/j0U4kItEhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f0e0333901e0d52bbd0de70fc27b2ffbb8c165bc7ca83018ebf99e54a72caf","last_reissued_at":"2026-07-05T05:31:21.055963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:21.055963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Bj\\\"orn Hoffmeister, David M. Chan, Shalini Ghosh","submitted_at":"2023-01-06T22:32:50Z","abstract_excerpt":"Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating increased data collection), and rapidly shifting data distributions (requiring more frequent model fine-tuning). In this work, we investigate the potential of leveraging external knowledge, particularly through off-policy key-value stores generated with text-to-speech methods, to allow for flexible post-training adaptation to new data distributions. In our approach,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02736","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/2301.02736/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.02736","created_at":"2026-07-05T05:31:21.056036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02736v1","created_at":"2026-07-05T05:31:21.056036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02736","created_at":"2026-07-05T05:31:21.056036+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DYOAMZZAHQN","created_at":"2026-07-05T05:31:21.056036+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DYOAMZZAHQNKK55","created_at":"2026-07-05T05:31:21.056036+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DYOAMZZ","created_at":"2026-07-05T05:31:21.056036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7","json":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7.json","graph_json":"https://pith.science/api/pith-number/6DYOAMZZAHQNKK55BXTQ7QT3F7/graph.json","events_json":"https://pith.science/api/pith-number/6DYOAMZZAHQNKK55BXTQ7QT3F7/events.json","paper":"https://pith.science/paper/6DYOAMZZ"},"agent_actions":{"view_html":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7","download_json":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7.json","view_paper":"https://pith.science/paper/6DYOAMZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02736&json=true","fetch_graph":"https://pith.science/api/pith-number/6DYOAMZZAHQNKK55BXTQ7QT3F7/graph.json","fetch_events":"https://pith.science/api/pith-number/6DYOAMZZAHQNKK55BXTQ7QT3F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7/action/storage_attestation","attest_author":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7/action/author_attestation","sign_citation":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7/action/citation_signature","submit_replication":"https://pith.science/pith/6DYOAMZZAHQNKK55BXTQ7QT3F7/action/replication_record"}},"created_at":"2026-07-05T05:31:21.056036+00:00","updated_at":"2026-07-05T05:31:21.056036+00:00"}