{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XONJ7DJ3BNCF7PA2I7YG5HM5BY","short_pith_number":"pith:XONJ7DJ3","schema_version":"1.0","canonical_sha256":"bb9a9f8d3b0b445fbc1a47f06e9d9d0e259dd26e71e6604c90deb9be9f978824","source":{"kind":"arxiv","id":"2312.12783","version":1},"attestation_state":"computed","paper":{"title":"Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition","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":"2023-12-20T06:02:12Z","abstract_excerpt":"Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition (ASR). This paper proposes Stable Distillation, a simple and novel approach for SSL-based continued pre-training that boosts ASR performance in the target domain where both labeled and unlabeled data are limited. Stable Distillation employs self-distillation as regularization for continued pre-training, alleviating the over-fitting issue, a common problem continued pre-training faces when the source and target domai"},"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":"2312.12783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-12-20T06:02:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"2e8545777f1b1fb8924b048dff3747cf9a205548c0d28d554db1100988c743ba","abstract_canon_sha256":"35f43989f45d29b4d00d494a6416d5012618fda1fc5721c0ee53fa2b057ee52c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:26.568617Z","signature_b64":"7pCUMF6ayTfU+p6FyhLa+hSKzPp4yPvaoM699FLBRkwG9xz3VhP9awypiuIdCL85m4s71c0r+oj4omonIHxZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb9a9f8d3b0b445fbc1a47f06e9d9d0e259dd26e71e6604c90deb9be9f978824","last_reissued_at":"2026-07-05T07:26:26.568180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:26.568180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition","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":"2023-12-20T06:02:12Z","abstract_excerpt":"Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition (ASR). This paper proposes Stable Distillation, a simple and novel approach for SSL-based continued pre-training that boosts ASR performance in the target domain where both labeled and unlabeled data are limited. Stable Distillation employs self-distillation as regularization for continued pre-training, alleviating the over-fitting issue, a common problem continued pre-training faces when the source and target domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12783","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/2312.12783/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":"2312.12783","created_at":"2026-07-05T07:26:26.568235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12783v1","created_at":"2026-07-05T07:26:26.568235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12783","created_at":"2026-07-05T07:26:26.568235+00:00"},{"alias_kind":"pith_short_12","alias_value":"XONJ7DJ3BNCF","created_at":"2026-07-05T07:26:26.568235+00:00"},{"alias_kind":"pith_short_16","alias_value":"XONJ7DJ3BNCF7PA2","created_at":"2026-07-05T07:26:26.568235+00:00"},{"alias_kind":"pith_short_8","alias_value":"XONJ7DJ3","created_at":"2026-07-05T07:26:26.568235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00421","citing_title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY","json":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY.json","graph_json":"https://pith.science/api/pith-number/XONJ7DJ3BNCF7PA2I7YG5HM5BY/graph.json","events_json":"https://pith.science/api/pith-number/XONJ7DJ3BNCF7PA2I7YG5HM5BY/events.json","paper":"https://pith.science/paper/XONJ7DJ3"},"agent_actions":{"view_html":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY","download_json":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY.json","view_paper":"https://pith.science/paper/XONJ7DJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12783&json=true","fetch_graph":"https://pith.science/api/pith-number/XONJ7DJ3BNCF7PA2I7YG5HM5BY/graph.json","fetch_events":"https://pith.science/api/pith-number/XONJ7DJ3BNCF7PA2I7YG5HM5BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY/action/storage_attestation","attest_author":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY/action/author_attestation","sign_citation":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY/action/citation_signature","submit_replication":"https://pith.science/pith/XONJ7DJ3BNCF7PA2I7YG5HM5BY/action/replication_record"}},"created_at":"2026-07-05T07:26:26.568235+00:00","updated_at":"2026-07-05T07:26:26.568235+00:00"}