{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EV7NYA3RHHGUGFQSWNB2WDKBDC","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":"034f89e17eae44064f794d600fa6454d09d4d83982c620028dd43e19d48c12d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T15:20:50Z","title_canon_sha256":"3daa5c6bd5c7d9835d49a5a50f98e835d2e6864f1c497a1716c97c37db68c5b0"},"schema_version":"1.0","source":{"id":"2501.16131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16131","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16131v1","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16131","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"EV7NYA3RHHGU","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"EV7NYA3RHHGUGFQS","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"EV7NYA3R","created_at":"2026-07-05T10:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:e45e90c2894146646d28b814295302df0baf92c3ec5f891148ccdd976197ac92","target":"graph","created_at":"2026-07-05T10:05:55Z","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/2501.16131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning has been successfully used for various speech related tasks, including automatic speech recognition. BERT-based Speech pre-Training with Random-projection Quantizer (BEST-RQ) has achieved state-of-the-art results in speech recognition. In this work, we further optimize the BEST-RQ approach using Kullback-Leibler divergence as an additional regularizing loss and multi-codebook extension per cluster derived from low-level feature clustering. Preliminary experiments on train-100 split of LibriSpeech result in a relative improvement of 11.2% on test-clean by using multiple","authors_text":"Dominik Wagner, Ilja Baumann, Korbinian Riedhammer, Tobias Bocklet","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T15:20:50Z","title":"Optimized Self-supervised Training with BEST-RQ for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16131","kind":"arxiv","version":1},"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:d22e0760ccc003e4fefd92d23446c57f03562d0b75acb09faea840b27b6cef58","target":"record","created_at":"2026-07-05T10:05:55Z","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":"034f89e17eae44064f794d600fa6454d09d4d83982c620028dd43e19d48c12d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T15:20:50Z","title_canon_sha256":"3daa5c6bd5c7d9835d49a5a50f98e835d2e6864f1c497a1716c97c37db68c5b0"},"schema_version":"1.0","source":{"id":"2501.16131","kind":"arxiv","version":1}},"canonical_sha256":"257edc037139cd431612b343ab0d4118b458cd468218aec92ff1ae3f727f1fb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"257edc037139cd431612b343ab0d4118b458cd468218aec92ff1ae3f727f1fb1","first_computed_at":"2026-07-05T10:05:55.803870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:55.803870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvn81qs4ecFdj31Yett1N+zM5ixkNSYQRYf5s6aIy9rAskmRO9gproqt9DRni2JlD3pmqUkvNkFVM5td2dLwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:55.804399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d22e0760ccc003e4fefd92d23446c57f03562d0b75acb09faea840b27b6cef58","sha256:e45e90c2894146646d28b814295302df0baf92c3ec5f891148ccdd976197ac92"],"state_sha256":"18fa408446c8ca93cdc894966d8ad4f64d19de4f598bbf94f9404c15dec35980"}