{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:423333Z7UBWF6JUAUIUEQQ5I3X","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":"36c71ec80ea3b00f6387f720f1964c6da8dc090f534c4765528fee9bd77d07a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-10-29T20:53:12Z","title_canon_sha256":"b03aaa73c5ad62736d7e57fc4cc7b31ca534c1020fa3ce36a80b177bac146719"},"schema_version":"1.0","source":{"id":"2510.25955","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.25955","created_at":"2026-06-23T03:13:49Z"},{"alias_kind":"arxiv_version","alias_value":"2510.25955v4","created_at":"2026-06-23T03:13:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.25955","created_at":"2026-06-23T03:13:49Z"},{"alias_kind":"pith_short_12","alias_value":"423333Z7UBWF","created_at":"2026-06-23T03:13:49Z"},{"alias_kind":"pith_short_16","alias_value":"423333Z7UBWF6JUA","created_at":"2026-06-23T03:13:49Z"},{"alias_kind":"pith_short_8","alias_value":"423333Z7","created_at":"2026-06-23T03:13:49Z"}],"graph_snapshots":[{"event_id":"sha256:bbc19dd394179c8c198c3419175c500b9d04550ffd3d3f518d4d8ea8d63296e6","target":"graph","created_at":"2026-06-23T03:13:49Z","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/2510.25955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains. We address this gap with SPEAR (SPEech and Audio Representations), a self-supervised framework that distils complementary knowledge from a speech-focused SSL teacher and a general-audio SSL teacher into a single unified model. SPEAR applies multi-codebook vector quantisation to continuous teacher representations to produce fine-grained discrete tokens that ","authors_text":"Baoxiang Li, Chao Zhang, Phil Woodland, Wen Wu, Xiaoyu Yang, Yifan Yang, Zengrui Jin, Ziyun Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-10-29T20:53:12Z","title":"SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.25955","kind":"arxiv","version":4},"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":"sha256:2c8b38b1390d9c62426f4ddef248d1afcef23057fc11e7ac1a5249ded1a9e388","target":"record","created_at":"2026-06-23T03:13:49Z","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":"36c71ec80ea3b00f6387f720f1964c6da8dc090f534c4765528fee9bd77d07a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-10-29T20:53:12Z","title_canon_sha256":"b03aaa73c5ad62736d7e57fc4cc7b31ca534c1020fa3ce36a80b177bac146719"},"schema_version":"1.0","source":{"id":"2510.25955","kind":"arxiv","version":4}},"canonical_sha256":"e6b7bdef3fa06c5f2680a2284843a8ddefb5f41ad4488301dfe0685f1f5b57e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6b7bdef3fa06c5f2680a2284843a8ddefb5f41ad4488301dfe0685f1f5b57e6","first_computed_at":"2026-06-23T03:13:49.104984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:49.104984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IYSq5aWUMhuTWu9vbrFNJWTylKed6q1+zO13iDWOmetNNAiA+CIsvARW0YlZgMPGONGpGaDgWjpfDRBAZ7IPCw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:49.105512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.25955","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8b38b1390d9c62426f4ddef248d1afcef23057fc11e7ac1a5249ded1a9e388","sha256:bbc19dd394179c8c198c3419175c500b9d04550ffd3d3f518d4d8ea8d63296e6"],"state_sha256":"e1c18fab7ec2e59992f7b5abc39c5d17a0f2623c61759866c414e3c96b20be8d"}