{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TO2KYDTOSCEYR6X65ICK6NBG2W","short_pith_number":"pith:TO2KYDTO","schema_version":"1.0","canonical_sha256":"9bb4ac0e6e908988fafeea04af3426d5a27bc1ae32552c1c4e0ce18b226b8953","source":{"kind":"arxiv","id":"2311.08402","version":1},"attestation_state":"computed","paper":{"title":"Retrieve and Copy: Scaling ASR Personalization to Large Catalogs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Devang Kulshreshtha, Sai Muralidhar Jayanthi, Saket Dingliwal, Sravan Bodapati, Srikanth Ronanki","submitted_at":"2023-11-14T18:59:24Z","abstract_excerpt":"Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare words and domain specific entities. However, due to performance constraints, the biasing is often limited to a few thousand entities, restricting real-world usability. To address this, we first propose a \"Retrieve and Copy\" mechanism to improve latency while retaining the accuracy even when scaled to a large catalog. We also propose a training strategy to overco"},"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":"2311.08402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T18:59:24Z","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"title_canon_sha256":"70816ca6e47054ba4da8bed3997ff77750461a89696897867f3e75d294ef0ae4","abstract_canon_sha256":"5e3642b1cf6ffc28810a5e05c312d3f821212b9fea6f0b2d6a0d44dff504713d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:44.657940Z","signature_b64":"I92+6cJ/9DIxhwvsaWz4C0/UJLntTrHTXyO6pc8zjOdMufjm4M340m+0TA96//GMWlevBcG4ilsGk6Mfaz1WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bb4ac0e6e908988fafeea04af3426d5a27bc1ae32552c1c4e0ce18b226b8953","last_reissued_at":"2026-07-05T07:12:44.657458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:44.657458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieve and Copy: Scaling ASR Personalization to Large Catalogs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Devang Kulshreshtha, Sai Muralidhar Jayanthi, Saket Dingliwal, Sravan Bodapati, Srikanth Ronanki","submitted_at":"2023-11-14T18:59:24Z","abstract_excerpt":"Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare words and domain specific entities. However, due to performance constraints, the biasing is often limited to a few thousand entities, restricting real-world usability. To address this, we first propose a \"Retrieve and Copy\" mechanism to improve latency while retaining the accuracy even when scaled to a large catalog. We also propose a training strategy to overco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08402","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/2311.08402/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":"2311.08402","created_at":"2026-07-05T07:12:44.657528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08402v1","created_at":"2026-07-05T07:12:44.657528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08402","created_at":"2026-07-05T07:12:44.657528+00:00"},{"alias_kind":"pith_short_12","alias_value":"TO2KYDTOSCEY","created_at":"2026-07-05T07:12:44.657528+00:00"},{"alias_kind":"pith_short_16","alias_value":"TO2KYDTOSCEYR6X6","created_at":"2026-07-05T07:12:44.657528+00:00"},{"alias_kind":"pith_short_8","alias_value":"TO2KYDTO","created_at":"2026-07-05T07:12:44.657528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W","json":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W.json","graph_json":"https://pith.science/api/pith-number/TO2KYDTOSCEYR6X65ICK6NBG2W/graph.json","events_json":"https://pith.science/api/pith-number/TO2KYDTOSCEYR6X65ICK6NBG2W/events.json","paper":"https://pith.science/paper/TO2KYDTO"},"agent_actions":{"view_html":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W","download_json":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W.json","view_paper":"https://pith.science/paper/TO2KYDTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08402&json=true","fetch_graph":"https://pith.science/api/pith-number/TO2KYDTOSCEYR6X65ICK6NBG2W/graph.json","fetch_events":"https://pith.science/api/pith-number/TO2KYDTOSCEYR6X65ICK6NBG2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W/action/storage_attestation","attest_author":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W/action/author_attestation","sign_citation":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W/action/citation_signature","submit_replication":"https://pith.science/pith/TO2KYDTOSCEYR6X65ICK6NBG2W/action/replication_record"}},"created_at":"2026-07-05T07:12:44.657528+00:00","updated_at":"2026-07-05T07:12:44.657528+00:00"}