{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XKHLWDPW74OOL2LAQ6DU6NPZZO","short_pith_number":"pith:XKHLWDPW","schema_version":"1.0","canonical_sha256":"ba8ebb0df6ff1ce5e96087874f35f9cb877dfc4a49434b627778c5bee1f16867","source":{"kind":"arxiv","id":"2207.00216","version":1},"attestation_state":"computed","paper":{"title":"Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Paola Garc\\'ia, Shinji Watanabe, Shota Horiguchi, Yohei Kawaguchi, Yuki Takashima","submitted_at":"2022-07-01T05:54:01Z","abstract_excerpt":"In this paper, we present an incremental domain adaptation technique to prevent catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model. Conventional approaches require extra parameters of the same size as the model for optimization, and it is difficult to apply these approaches to end-to-end ASR models because they have a huge amount of parameters. To solve this problem, we first investigate which parts of end-to-end ASR models contribute to high accuracy in the target domain while preventing catastrophic forgetting. We conduct experiments on incremental domain adap"},"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":"2207.00216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T05:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"4b4bef16bc991ab601139e5d270474d734b6d4a1ff8956827574b31a78524594","abstract_canon_sha256":"d9bb4c111e4ea3a6ed5cc5e016a71de2d38ef57d1ffb1aa3930a0ac24db85086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:40.560759Z","signature_b64":"zIGjrMOJKUcbgGsfmaPPn5rYwMbIcN5AmyAZ+1Md5aWiBl5oEicCwO95EwxR+4QJxQI/fe8m0jymqsOdXv3FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8ebb0df6ff1ce5e96087874f35f9cb877dfc4a49434b627778c5bee1f16867","last_reissued_at":"2026-07-05T04:36:40.560351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:40.560351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Paola Garc\\'ia, Shinji Watanabe, Shota Horiguchi, Yohei Kawaguchi, Yuki Takashima","submitted_at":"2022-07-01T05:54:01Z","abstract_excerpt":"In this paper, we present an incremental domain adaptation technique to prevent catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model. Conventional approaches require extra parameters of the same size as the model for optimization, and it is difficult to apply these approaches to end-to-end ASR models because they have a huge amount of parameters. To solve this problem, we first investigate which parts of end-to-end ASR models contribute to high accuracy in the target domain while preventing catastrophic forgetting. We conduct experiments on incremental domain adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00216","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/2207.00216/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":"2207.00216","created_at":"2026-07-05T04:36:40.560407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00216v1","created_at":"2026-07-05T04:36:40.560407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00216","created_at":"2026-07-05T04:36:40.560407+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKHLWDPW74OO","created_at":"2026-07-05T04:36:40.560407+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKHLWDPW74OOL2LA","created_at":"2026-07-05T04:36:40.560407+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKHLWDPW","created_at":"2026-07-05T04:36:40.560407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08384","citing_title":"TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO","json":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO.json","graph_json":"https://pith.science/api/pith-number/XKHLWDPW74OOL2LAQ6DU6NPZZO/graph.json","events_json":"https://pith.science/api/pith-number/XKHLWDPW74OOL2LAQ6DU6NPZZO/events.json","paper":"https://pith.science/paper/XKHLWDPW"},"agent_actions":{"view_html":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO","download_json":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO.json","view_paper":"https://pith.science/paper/XKHLWDPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00216&json=true","fetch_graph":"https://pith.science/api/pith-number/XKHLWDPW74OOL2LAQ6DU6NPZZO/graph.json","fetch_events":"https://pith.science/api/pith-number/XKHLWDPW74OOL2LAQ6DU6NPZZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO/action/storage_attestation","attest_author":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO/action/author_attestation","sign_citation":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO/action/citation_signature","submit_replication":"https://pith.science/pith/XKHLWDPW74OOL2LAQ6DU6NPZZO/action/replication_record"}},"created_at":"2026-07-05T04:36:40.560407+00:00","updated_at":"2026-07-05T04:36:40.560407+00:00"}