{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZY7R44U3Y72X23A5GQVT2OWVYA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5067f716e6c26d50c3121b2b4b636af384a54c1475ca0f7fd0d705c54f0c788c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-07T06:29:36Z","title_canon_sha256":"c76f7d8f13247ac2b8ba7201dd5fb9bff7d28198774f1fd1595c55d2d199cc3b"},"schema_version":"1.0","source":{"id":"2108.06209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.06209","created_at":"2026-07-05T03:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2108.06209v2","created_at":"2026-07-05T03:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06209","created_at":"2026-07-05T03:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZY7R44U3Y72X","created_at":"2026-07-05T03:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZY7R44U3Y72X23A5","created_at":"2026-07-05T03:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZY7R44U3","created_at":"2026-07-05T03:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:3bdad3c0816abd9996027e4a8fbecc7fd93672f664e92adb5e69f35a0cde3218","target":"graph","created_at":"2026-07-05T03:13:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.06209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-train","authors_text":"Chung-Cheng Chiu, James Qin, Ruoming Pang, Wei Han, Yonghui Wu, Yu-An Chung, Yu Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-07T06:29:36Z","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06209","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:052471b7830d06d785718f23182628170fd18bd2ef056d872dbf9890b41d6bec","target":"record","created_at":"2026-07-05T03:13:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5067f716e6c26d50c3121b2b4b636af384a54c1475ca0f7fd0d705c54f0c788c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-07T06:29:36Z","title_canon_sha256":"c76f7d8f13247ac2b8ba7201dd5fb9bff7d28198774f1fd1595c55d2d199cc3b"},"schema_version":"1.0","source":{"id":"2108.06209","kind":"arxiv","version":2}},"canonical_sha256":"ce3f1e729bc7f57d6c1d342b3d3ad5c012d466af372862dd1feb7f6c94e69899","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce3f1e729bc7f57d6c1d342b3d3ad5c012d466af372862dd1feb7f6c94e69899","first_computed_at":"2026-07-05T03:13:50.492355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:50.492355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zsrnITECeEqxJZzQ7eQdgKSBWC7SgJg+piXw9gRRSzMfq9V99Tm0BzFMUPyj0c21ziUaPz5CHsHd0OUtZYgOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:50.492797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.06209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:052471b7830d06d785718f23182628170fd18bd2ef056d872dbf9890b41d6bec","sha256:3bdad3c0816abd9996027e4a8fbecc7fd93672f664e92adb5e69f35a0cde3218"],"state_sha256":"3890ce3e4696df954ef46478b82fbd1a0acd467c783058501a9ec2f3ff4c20a2"}