{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IOMXWLIRV5ZXLTGCKCKKIIHJG2","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":"8f8c1ce2695fdc242c57a78c8d773b32f2871c3fa301a65d2138bb8bf94befe1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T07:23:46Z","title_canon_sha256":"756552f46011a7c1de237c4b38a75bb29594b680ce89e044537dae076b305ac8"},"schema_version":"1.0","source":{"id":"2305.10005","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10005","created_at":"2026-07-05T07:33:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10005v2","created_at":"2026-07-05T07:33:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10005","created_at":"2026-07-05T07:33:50Z"},{"alias_kind":"pith_short_12","alias_value":"IOMXWLIRV5ZX","created_at":"2026-07-05T07:33:50Z"},{"alias_kind":"pith_short_16","alias_value":"IOMXWLIRV5ZXLTGC","created_at":"2026-07-05T07:33:50Z"},{"alias_kind":"pith_short_8","alias_value":"IOMXWLIR","created_at":"2026-07-05T07:33:50Z"}],"graph_snapshots":[{"event_id":"sha256:8df5bd5ad8cc9a10dc1d2b61ccbc2af5b33fd0a288e8393a84a285ea7cbc69b2","target":"graph","created_at":"2026-07-05T07:33:50Z","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/2305.10005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts complement each other and result in a strong representation learning model for speech. DinoSR first extracts contextualized embeddings from the input audio with a teacher network, then runs an online clustering system on the embeddings to yield a machine-discovered phone inventory, and finally uses the discretized tokens to guide a student network. We show th","authors_text":"Alexander H. Liu, Heng-Jui Chang, James R. Glass, Michael Auli, Wei-Ning Hsu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T07:23:46Z","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10005","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:da1527eb18e8624b401210b3921021d02c7ccfbb901b849f5897294a16bdba32","target":"record","created_at":"2026-07-05T07:33:50Z","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":"8f8c1ce2695fdc242c57a78c8d773b32f2871c3fa301a65d2138bb8bf94befe1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T07:23:46Z","title_canon_sha256":"756552f46011a7c1de237c4b38a75bb29594b680ce89e044537dae076b305ac8"},"schema_version":"1.0","source":{"id":"2305.10005","kind":"arxiv","version":2}},"canonical_sha256":"43997b2d11af7375ccc25094a420e936993f3497bf90b4e3b00a0f2a30914b9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43997b2d11af7375ccc25094a420e936993f3497bf90b4e3b00a0f2a30914b9c","first_computed_at":"2026-07-05T07:33:50.919239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:50.919239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6h4KmJEintZPW/9vOmR2E14Taj0urampfjQw1HgiBrqIRmDrc3UPrkVlJiLciWRN4Uc2+4jiJk2xV+jXlz9xAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:50.919595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10005","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1527eb18e8624b401210b3921021d02c7ccfbb901b849f5897294a16bdba32","sha256:8df5bd5ad8cc9a10dc1d2b61ccbc2af5b33fd0a288e8393a84a285ea7cbc69b2"],"state_sha256":"669e74be53ad3dc3c5a55e0e58ef005f5b62061d3b4f942b9b9e90625d2940ea"}