{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:73JGJMFM3YA7RGHXJJ7VNI2AGZ","short_pith_number":"pith:73JGJMFM","schema_version":"1.0","canonical_sha256":"fed264b0acde01f898f74a7f56a3403673ac4af13d640e6c39b4849d7d89ae28","source":{"kind":"arxiv","id":"2211.06007","version":2},"attestation_state":"computed","paper":{"title":"Continuous Soft Pseudo-Labeling in ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Navdeep Jaitly, Ronan Collobert, Samy Bengio, Tatiana Likhomanenko","submitted_at":"2022-11-11T05:16:18Z","abstract_excerpt":"Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and generating pseudo-labels (PLs) with it, here PLs are generated in end-to-end manner as training proceeds, improving training speed and the accuracy of the final model. PL shares a common theme with teacher-student models such as distillation in that a teacher model generates targets that need to be mimicked by the student model being trained. However, interesti"},"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":"2211.06007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T05:16:18Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"c59a1e56cf9ec614b515c8c6a57f00bd425d4a396958c0ed815fc2a00955d701","abstract_canon_sha256":"706d250e42dbea6f11725e84b08c50ee0acf11292c670cb3e4e0dd2be7f5709c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:10.232676Z","signature_b64":"iHdzNqlZxR/wVCl1KLa5fJ/wX5/+q2hEV27MXdqHEPOzQtyptb0IXiMo3Dfui8TgKepMsiU0Qt9O0zzkIWoiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed264b0acde01f898f74a7f56a3403673ac4af13d640e6c39b4849d7d89ae28","last_reissued_at":"2026-07-05T05:37:10.232108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:10.232108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Soft Pseudo-Labeling in ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Navdeep Jaitly, Ronan Collobert, Samy Bengio, Tatiana Likhomanenko","submitted_at":"2022-11-11T05:16:18Z","abstract_excerpt":"Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and generating pseudo-labels (PLs) with it, here PLs are generated in end-to-end manner as training proceeds, improving training speed and the accuracy of the final model. PL shares a common theme with teacher-student models such as distillation in that a teacher model generates targets that need to be mimicked by the student model being trained. However, interesti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06007","kind":"arxiv","version":2},"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/2211.06007/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":"2211.06007","created_at":"2026-07-05T05:37:10.232164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06007v2","created_at":"2026-07-05T05:37:10.232164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06007","created_at":"2026-07-05T05:37:10.232164+00:00"},{"alias_kind":"pith_short_12","alias_value":"73JGJMFM3YA7","created_at":"2026-07-05T05:37:10.232164+00:00"},{"alias_kind":"pith_short_16","alias_value":"73JGJMFM3YA7RGHX","created_at":"2026-07-05T05:37:10.232164+00:00"},{"alias_kind":"pith_short_8","alias_value":"73JGJMFM","created_at":"2026-07-05T05:37:10.232164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05224","citing_title":"Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ","json":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ.json","graph_json":"https://pith.science/api/pith-number/73JGJMFM3YA7RGHXJJ7VNI2AGZ/graph.json","events_json":"https://pith.science/api/pith-number/73JGJMFM3YA7RGHXJJ7VNI2AGZ/events.json","paper":"https://pith.science/paper/73JGJMFM"},"agent_actions":{"view_html":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ","download_json":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ.json","view_paper":"https://pith.science/paper/73JGJMFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06007&json=true","fetch_graph":"https://pith.science/api/pith-number/73JGJMFM3YA7RGHXJJ7VNI2AGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/73JGJMFM3YA7RGHXJJ7VNI2AGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ/action/storage_attestation","attest_author":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ/action/author_attestation","sign_citation":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ/action/citation_signature","submit_replication":"https://pith.science/pith/73JGJMFM3YA7RGHXJJ7VNI2AGZ/action/replication_record"}},"created_at":"2026-07-05T05:37:10.232164+00:00","updated_at":"2026-07-05T05:37:10.232164+00:00"}