{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OSRHXLN5WJVPLLVUSC3B3GYA7R","short_pith_number":"pith:OSRHXLN5","canonical_record":{"source":{"id":"2306.08920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T07:45:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0a2e7400745ff740c64e93774ee9f13ccb2970e2d1efae57bcbbdc9bffb3c7cc","abstract_canon_sha256":"264cbabac8546f9bac924214931c377830c158783bffb54b5500f22fdeeae77e"},"schema_version":"1.0"},"canonical_sha256":"74a27badbdb26af5aeb490b61d9b00fc502789f62f987555d8a66f026f8d2e04","source":{"kind":"arxiv","id":"2306.08920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08920","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08920v1","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08920","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_12","alias_value":"OSRHXLN5WJVP","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_16","alias_value":"OSRHXLN5WJVPLLVU","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_8","alias_value":"OSRHXLN5","created_at":"2026-07-05T06:20:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OSRHXLN5WJVPLLVUSC3B3GYA7R","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T07:45:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0a2e7400745ff740c64e93774ee9f13ccb2970e2d1efae57bcbbdc9bffb3c7cc","abstract_canon_sha256":"264cbabac8546f9bac924214931c377830c158783bffb54b5500f22fdeeae77e"},"schema_version":"1.0"},"canonical_sha256":"74a27badbdb26af5aeb490b61d9b00fc502789f62f987555d8a66f026f8d2e04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:57.970085Z","signature_b64":"Xrn+lXxFZLsVoc58b5L7S2aKuR+yC0pmEObQPx28mNl1eIxLgEGFoFGIvXMF9NHRs3ZjSGv8n+kzWK05YaZeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74a27badbdb26af5aeb490b61d9b00fc502789f62f987555d8a66f026f8d2e04","last_reissued_at":"2026-07-05T06:20:57.969581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:57.969581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08920","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vGlGmMDl9WTjTAAvpf+WLUFAJOt139XnItfJaQKeL/Xj0NKwm4OZHBa1j3hJ/t8yTj6QzqC40g09OR12ABhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T18:32:34.061914Z"},"content_sha256":"52d458d65e161e8be4346026c48c76a7edab313fa9e2b47cd0a51cebae31abaf","schema_version":"1.0","event_id":"sha256:52d458d65e161e8be4346026c48c76a7edab313fa9e2b47cd0a51cebae31abaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OSRHXLN5WJVPLLVUSC3B3GYA7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Guanrou Yang, Xie Chen, Yu Wang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2023-06-15T07:45:12Z","abstract_excerpt":"The excellent generalization ability of self-supervised learning (SSL) for speech foundation models has garnered significant attention. HuBERT is a successful example that utilizes offline clustering to convert speech features into discrete units for a masked language modeling pretext task. However, simply clustering features as targets by k-means does not fully inspire the model's performance. In this work, we present an unsupervised method to improve SSL targets. Two models are proposed, MonoBERT and PolyBERT, which leverage context-independent and context-dependent phoneme-based units for p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08920","kind":"arxiv","version":1},"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/2306.08920/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ieiEKbbcPN6/3OBAptqAGz/xeNhX4CnZYRRVZTMyejjlq8bzrCdB0UxbclfBIV+CiOETM17+GvwlCQm3FTHbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T18:32:34.062281Z"},"content_sha256":"0d14010214625928f6cf2a15a97e423e84bfad0a6d4e29ab7c17273566c9ce44","schema_version":"1.0","event_id":"sha256:0d14010214625928f6cf2a15a97e423e84bfad0a6d4e29ab7c17273566c9ce44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/bundle.json","state_url":"https://pith.science/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-18T18:32:34Z","links":{"resolver":"https://pith.science/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R","bundle":"https://pith.science/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/bundle.json","state":"https://pith.science/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSRHXLN5WJVPLLVUSC3B3GYA7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OSRHXLN5WJVPLLVUSC3B3GYA7R","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":"264cbabac8546f9bac924214931c377830c158783bffb54b5500f22fdeeae77e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T07:45:12Z","title_canon_sha256":"0a2e7400745ff740c64e93774ee9f13ccb2970e2d1efae57bcbbdc9bffb3c7cc"},"schema_version":"1.0","source":{"id":"2306.08920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08920","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08920v1","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08920","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_12","alias_value":"OSRHXLN5WJVP","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_16","alias_value":"OSRHXLN5WJVPLLVU","created_at":"2026-07-05T06:20:57Z"},{"alias_kind":"pith_short_8","alias_value":"OSRHXLN5","created_at":"2026-07-05T06:20:57Z"}],"graph_snapshots":[{"event_id":"sha256:0d14010214625928f6cf2a15a97e423e84bfad0a6d4e29ab7c17273566c9ce44","target":"graph","created_at":"2026-07-05T06:20:57Z","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/2306.08920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The excellent generalization ability of self-supervised learning (SSL) for speech foundation models has garnered significant attention. HuBERT is a successful example that utilizes offline clustering to convert speech features into discrete units for a masked language modeling pretext task. However, simply clustering features as targets by k-means does not fully inspire the model's performance. In this work, we present an unsupervised method to improve SSL targets. Two models are proposed, MonoBERT and PolyBERT, which leverage context-independent and context-dependent phoneme-based units for p","authors_text":"Chao Zhang, Guanrou Yang, Xie Chen, Yu Wang, Zhisheng Zheng, Ziyang Ma","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T07:45:12Z","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08920","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":"sha256:52d458d65e161e8be4346026c48c76a7edab313fa9e2b47cd0a51cebae31abaf","target":"record","created_at":"2026-07-05T06:20:57Z","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":"264cbabac8546f9bac924214931c377830c158783bffb54b5500f22fdeeae77e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T07:45:12Z","title_canon_sha256":"0a2e7400745ff740c64e93774ee9f13ccb2970e2d1efae57bcbbdc9bffb3c7cc"},"schema_version":"1.0","source":{"id":"2306.08920","kind":"arxiv","version":1}},"canonical_sha256":"74a27badbdb26af5aeb490b61d9b00fc502789f62f987555d8a66f026f8d2e04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74a27badbdb26af5aeb490b61d9b00fc502789f62f987555d8a66f026f8d2e04","first_computed_at":"2026-07-05T06:20:57.969581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:57.969581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xrn+lXxFZLsVoc58b5L7S2aKuR+yC0pmEObQPx28mNl1eIxLgEGFoFGIvXMF9NHRs3ZjSGv8n+kzWK05YaZeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:57.970085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52d458d65e161e8be4346026c48c76a7edab313fa9e2b47cd0a51cebae31abaf","sha256:0d14010214625928f6cf2a15a97e423e84bfad0a6d4e29ab7c17273566c9ce44"],"state_sha256":"e16cba8194982d20be1a0dddb50497c3191151a926c4f0984083226309fc2a3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+p+xfWCS+ehVxhBPkPK+aRiHDou7l0mzS/RGmt7g38aktpTzI7WIr0JaON/43jDlGvkxfPs52+HI1VW0ECJpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T18:32:34.064366Z","bundle_sha256":"fd328853531746cf1673c7509f96779ea9dea6f3186f1d1bbf5870d4f6c60386"}}