{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q33I4SSQC4RQ3WWYWW46UMJZZ7","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":"0569412b73d943863a07dda0ec1ed09af32c16635f90fe75b5f7dc4f0e4500e1","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T15:59:36Z","title_canon_sha256":"2b242e3ca8e2b22290a2975a7cf915028dce9407e3e3c209e4dbd76b5f59b7ec"},"schema_version":"1.0","source":{"id":"2305.11072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11072","created_at":"2026-07-05T06:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11072v1","created_at":"2026-07-05T06:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11072","created_at":"2026-07-05T06:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"Q33I4SSQC4RQ","created_at":"2026-07-05T06:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"Q33I4SSQC4RQ3WWY","created_at":"2026-07-05T06:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"Q33I4SSQ","created_at":"2026-07-05T06:11:30Z"}],"graph_snapshots":[{"event_id":"sha256:88caeb0cc1f296fce8a63daf4a6c0a4f1ce810be3a84b4dfb3904bbcaf62a250","target":"graph","created_at":"2026-07-05T06:11:30Z","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/2305.11072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised speech representation models have succeeded in various tasks, but improving them for content-related problems using unlabeled data is challenging. We propose speaker-invariant clustering (Spin), a novel self-supervised learning method that clusters speech representations and performs swapped prediction between the original and speaker-perturbed utterances. Spin disentangles speaker information and preserves content representations with just 45 minutes of fine-tuning on a single GPU. Spin improves pre-trained networks and outperforms prior methods in speech recognition and acous","authors_text":"Alexander H. Liu, Heng-Jui Chang, James Glass","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T15:59:36Z","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11072","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":"sha256:8ec593c8e3250c49ee7209bce09c349351a090e8544947e8a7f214ba6b74e81b","target":"record","created_at":"2026-07-05T06:11:30Z","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":"0569412b73d943863a07dda0ec1ed09af32c16635f90fe75b5f7dc4f0e4500e1","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T15:59:36Z","title_canon_sha256":"2b242e3ca8e2b22290a2975a7cf915028dce9407e3e3c209e4dbd76b5f59b7ec"},"schema_version":"1.0","source":{"id":"2305.11072","kind":"arxiv","version":1}},"canonical_sha256":"86f68e4a5017230ddad8b5b9ea3139cff5b329528a72deec9141ea7af93631e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86f68e4a5017230ddad8b5b9ea3139cff5b329528a72deec9141ea7af93631e1","first_computed_at":"2026-07-05T06:11:30.099662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:30.099662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnN5ROujndEm+czVX7EaZmQ260V5ASryzr419t5Q037ZtYNWANgZ2zhPVERSE/nKOISYhsQ4/KeZc0ZUd4mUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:30.100055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ec593c8e3250c49ee7209bce09c349351a090e8544947e8a7f214ba6b74e81b","sha256:88caeb0cc1f296fce8a63daf4a6c0a4f1ce810be3a84b4dfb3904bbcaf62a250"],"state_sha256":"204149ddc6224bddd5818502148ed6a68c9ca324122ed6e00d936e372b2a95ee"}