{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DHJCJXZJBGS6VHAUVJDYEWU7JJ","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":"130c5ab3737aa2b24e74652c1cf11c102bee9e80f50e30c7080ba136e9744b21","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-05T20:25:29Z","title_canon_sha256":"d35d14e7297e59703aa7b2ba8801fe54bd1963303b505e80d72b2d453bbba330"},"schema_version":"1.0","source":{"id":"2110.02345","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02345","created_at":"2026-07-05T03:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02345v2","created_at":"2026-07-05T03:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02345","created_at":"2026-07-05T03:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"DHJCJXZJBGS6","created_at":"2026-07-05T03:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"DHJCJXZJBGS6VHAU","created_at":"2026-07-05T03:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"DHJCJXZJ","created_at":"2026-07-05T03:21:14Z"}],"graph_snapshots":[{"event_id":"sha256:e0596fa7479ecbf85c7a19125ac4c08df9cdbec9bb8d6bb27cd33b648f5965e8","target":"graph","created_at":"2026-07-05T03:21:14Z","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/2110.02345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them and propose a technique that can jointly perform both, showing that these two tasks indeed benefit from each other. Recent attempts employ self-supervised learning, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation","authors_text":"Jes\\'us Villalba, Laureano Moro-Velazquez, Najim Dehak, Piotr \\.Zelasko, Saurabhchand Bhati","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-05T20:25:29Z","title":"Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02345","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":"sha256:9a9c3dbd28b4fa6a746d6c3e0926f41d2d862ed6a67400ef934933d4d10bf481","target":"record","created_at":"2026-07-05T03:21:14Z","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":"130c5ab3737aa2b24e74652c1cf11c102bee9e80f50e30c7080ba136e9744b21","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-05T20:25:29Z","title_canon_sha256":"d35d14e7297e59703aa7b2ba8801fe54bd1963303b505e80d72b2d453bbba330"},"schema_version":"1.0","source":{"id":"2110.02345","kind":"arxiv","version":2}},"canonical_sha256":"19d224df2909a5ea9c14aa47825a9f4a42f111cf761f26f997046104891e6a70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19d224df2909a5ea9c14aa47825a9f4a42f111cf761f26f997046104891e6a70","first_computed_at":"2026-07-05T03:21:14.914395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:14.914395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExEJJeiurAS5MbwgnM7OytNothmdyW4xReUsdYLo8gq3aenWzxeia7dj67AyR/IwYzVr0PWNR6Pp2ADweNVDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:14.914795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02345","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9c3dbd28b4fa6a746d6c3e0926f41d2d862ed6a67400ef934933d4d10bf481","sha256:e0596fa7479ecbf85c7a19125ac4c08df9cdbec9bb8d6bb27cd33b648f5965e8"],"state_sha256":"dd5d93e05ce4de3a972ea934f65528e146877f7e81790c109afeaa90552e170b"}