{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZLSA2BYQ2YNTRPFUIJTBLVUV6","short_pith_number":"pith:LZLSA2BY","schema_version":"1.0","canonical_sha256":"5e5720683886b0d9c5e5a21330aeb4afb558f60399a92888594f43d07a3316f3","source":{"kind":"arxiv","id":"2309.15317","version":2},"attestation_state":"computed","paper":{"title":"Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Dan Berrebbi, Jiatong Shi, Shinji Watanabe, Soumi Maiti, Wangyou Zhang, William Chen, Xuankai Chang, Yifan Peng","submitted_at":"2023-09-26T23:55:57Z","abstract_excerpt":"Multilingual self-supervised learning (SSL) has often lagged behind state-of-the-art (SOTA) methods due to the expenses and complexity required to handle many languages. This further harms the reproducibility of SSL, which is already limited to few research groups due to its resource usage. We show that more powerful techniques can actually lead to more efficient pre-training, opening SSL to more research groups. We propose WavLabLM, which extends WavLM's joint prediction and denoising to 40k hours of data across 136 languages. To build WavLabLM, we devise a novel multi-stage pre-training meth"},"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":"2309.15317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T23:55:57Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"08c128624845c6de531c113618145d8e8cf4bce284b8b8875b0cf10edf9d1133","abstract_canon_sha256":"cc2ac75f0fbf0089f3a791b21506a3021238f6c272dcd1722594292fc7c61c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:07.205865Z","signature_b64":"OmTH52jPxzKaiO4HXWzwASws/T5dbQ8/MG30o2Cpzo++rNlKah2ALpEcVVMkE3kgQlvj82EEIdxuf8sHBbzEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e5720683886b0d9c5e5a21330aeb4afb558f60399a92888594f43d07a3316f3","last_reissued_at":"2026-07-05T06:55:07.205475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:07.205475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Dan Berrebbi, Jiatong Shi, Shinji Watanabe, Soumi Maiti, Wangyou Zhang, William Chen, Xuankai Chang, Yifan Peng","submitted_at":"2023-09-26T23:55:57Z","abstract_excerpt":"Multilingual self-supervised learning (SSL) has often lagged behind state-of-the-art (SOTA) methods due to the expenses and complexity required to handle many languages. This further harms the reproducibility of SSL, which is already limited to few research groups due to its resource usage. We show that more powerful techniques can actually lead to more efficient pre-training, opening SSL to more research groups. We propose WavLabLM, which extends WavLM's joint prediction and denoising to 40k hours of data across 136 languages. To build WavLabLM, we devise a novel multi-stage pre-training meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15317","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/2309.15317/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":"2309.15317","created_at":"2026-07-05T06:55:07.205531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15317v2","created_at":"2026-07-05T06:55:07.205531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15317","created_at":"2026-07-05T06:55:07.205531+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZLSA2BYQ2YN","created_at":"2026-07-05T06:55:07.205531+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZLSA2BYQ2YNTRPF","created_at":"2026-07-05T06:55:07.205531+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZLSA2BY","created_at":"2026-07-05T06:55:07.205531+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/LZLSA2BYQ2YNTRPFUIJTBLVUV6","json":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6.json","graph_json":"https://pith.science/api/pith-number/LZLSA2BYQ2YNTRPFUIJTBLVUV6/graph.json","events_json":"https://pith.science/api/pith-number/LZLSA2BYQ2YNTRPFUIJTBLVUV6/events.json","paper":"https://pith.science/paper/LZLSA2BY"},"agent_actions":{"view_html":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6","download_json":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6.json","view_paper":"https://pith.science/paper/LZLSA2BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15317&json=true","fetch_graph":"https://pith.science/api/pith-number/LZLSA2BYQ2YNTRPFUIJTBLVUV6/graph.json","fetch_events":"https://pith.science/api/pith-number/LZLSA2BYQ2YNTRPFUIJTBLVUV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6/action/storage_attestation","attest_author":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6/action/author_attestation","sign_citation":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6/action/citation_signature","submit_replication":"https://pith.science/pith/LZLSA2BYQ2YNTRPFUIJTBLVUV6/action/replication_record"}},"created_at":"2026-07-05T06:55:07.205531+00:00","updated_at":"2026-07-05T06:55:07.205531+00:00"}