{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ORS2VKCNUMI7P4NWTOPJ537Q2Q","short_pith_number":"pith:ORS2VKCN","schema_version":"1.0","canonical_sha256":"7465aaa84da311f7f1b69b9e9eeff0d4370e901b7e5ec7e43019f1308643790a","source":{"kind":"arxiv","id":"2312.13026","version":1},"attestation_state":"computed","paper":{"title":"FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ashish Seth, Dinesh Manocha, Sreyan Ghosh, S. Umesh","submitted_at":"2023-12-20T13:50:05Z","abstract_excerpt":"Continued pre-training (CP) offers multiple advantages, like target domain adaptation and the potential to exploit the continuous stream of unlabeled data available online. However, continued pre-training on out-of-domain distributions often leads to catastrophic forgetting of previously acquired knowledge, leading to sub-optimal ASR performance. This paper presents FusDom, a simple and novel methodology for SSL-based continued pre-training. FusDom learns speech representations that are robust and adaptive yet not forgetful of concepts seen in the past. Instead of solving the SSL pre-text task"},"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":"2312.13026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-12-20T13:50:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"760edb00423beaf6c8cef1912aa1714c776b0854b5776f2bb64dbbcb6231839b","abstract_canon_sha256":"b9362cc384bbd3b81ea71fff7c234cd83783b66b1f14d12c89872e0144d36921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:29.534400Z","signature_b64":"7945sNpRZ2n9wg+eser9qbucepliFgEe0fJqFejUGVhm9cvj1kR3/jvHvZx20quyTpIYjex/29kF920bcDe5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7465aaa84da311f7f1b69b9e9eeff0d4370e901b7e5ec7e43019f1308643790a","last_reissued_at":"2026-07-05T07:26:29.533963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:29.533963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ashish Seth, Dinesh Manocha, Sreyan Ghosh, S. Umesh","submitted_at":"2023-12-20T13:50:05Z","abstract_excerpt":"Continued pre-training (CP) offers multiple advantages, like target domain adaptation and the potential to exploit the continuous stream of unlabeled data available online. However, continued pre-training on out-of-domain distributions often leads to catastrophic forgetting of previously acquired knowledge, leading to sub-optimal ASR performance. This paper presents FusDom, a simple and novel methodology for SSL-based continued pre-training. FusDom learns speech representations that are robust and adaptive yet not forgetful of concepts seen in the past. Instead of solving the SSL pre-text task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13026","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/2312.13026/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":"2312.13026","created_at":"2026-07-05T07:26:29.534018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13026v1","created_at":"2026-07-05T07:26:29.534018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13026","created_at":"2026-07-05T07:26:29.534018+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORS2VKCNUMI7","created_at":"2026-07-05T07:26:29.534018+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORS2VKCNUMI7P4NW","created_at":"2026-07-05T07:26:29.534018+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORS2VKCN","created_at":"2026-07-05T07:26:29.534018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11439","citing_title":"Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q","json":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q.json","graph_json":"https://pith.science/api/pith-number/ORS2VKCNUMI7P4NWTOPJ537Q2Q/graph.json","events_json":"https://pith.science/api/pith-number/ORS2VKCNUMI7P4NWTOPJ537Q2Q/events.json","paper":"https://pith.science/paper/ORS2VKCN"},"agent_actions":{"view_html":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q","download_json":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q.json","view_paper":"https://pith.science/paper/ORS2VKCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13026&json=true","fetch_graph":"https://pith.science/api/pith-number/ORS2VKCNUMI7P4NWTOPJ537Q2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ORS2VKCNUMI7P4NWTOPJ537Q2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q/action/storage_attestation","attest_author":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q/action/author_attestation","sign_citation":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q/action/citation_signature","submit_replication":"https://pith.science/pith/ORS2VKCNUMI7P4NWTOPJ537Q2Q/action/replication_record"}},"created_at":"2026-07-05T07:26:29.534018+00:00","updated_at":"2026-07-05T07:26:29.534018+00:00"}