{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YH56TVTGNZADK5UHBIHTUEC5AY","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":"2b4e857e5f2cfb2c8870050e2eb9d0f2e73c5422f5413965a8580616029c65b8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T17:05:00Z","title_canon_sha256":"cd1f0ed76af323db44b30ee25f5802a4ff204ad2d1cff7d7fe2be96212c5411b"},"schema_version":"1.0","source":{"id":"2310.05235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05235","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05235v1","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05235","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"YH56TVTGNZAD","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"YH56TVTGNZADK5UH","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"YH56TVTG","created_at":"2026-07-05T06:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:7ee1ec155ef48db41cc353d2d3088e07eb0ad4cf8e798c43736d4600d7206b2a","target":"graph","created_at":"2026-07-05T06:58:28Z","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/2310.05235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the absence of explicit word boundaries in the speech stream, the task of segmenting spoken sentences into word units without text supervision is particularly challenging. In this work, we leverage the most recent self-supervised speech models that have proved to quickly adapt to new tasks through fine-tuning, even in low resource conditions. Taking inspiration from semi-supervised learning, we fine-tune an XLS-R model to predict word boundaries themselves produced by top-tier speech segmentation systems: DPDP, VG-HuBERT, GradSeg and DP-Parse. Once XLS-R is fine-tuned, it is used to inf","authors_text":"Benoit Sagot, Emmanuel Dupoux, Pablo Diego-Simon, Robin Algayres","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T17:05:00Z","title":"XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05235","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:b6113b3c244a05e21e4e52140d7ec4d27cd6855a17560a7cf6fa9c65a7568bc8","target":"record","created_at":"2026-07-05T06:58:28Z","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":"2b4e857e5f2cfb2c8870050e2eb9d0f2e73c5422f5413965a8580616029c65b8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T17:05:00Z","title_canon_sha256":"cd1f0ed76af323db44b30ee25f5802a4ff204ad2d1cff7d7fe2be96212c5411b"},"schema_version":"1.0","source":{"id":"2310.05235","kind":"arxiv","version":1}},"canonical_sha256":"c1fbe9d6666e403576870a0f3a105d062d1b3ba4600dd85a6c1cc40a432f94ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1fbe9d6666e403576870a0f3a105d062d1b3ba4600dd85a6c1cc40a432f94ed","first_computed_at":"2026-07-05T06:58:28.503854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:28.503854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aWhAXzn4ru7M9vDzc4YpoEYVixJfpZ20E+42yki9n5tvOj8Cw8mxl+9+WqykA1/gYLRIE1xl9Gd3n+KWDTn+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:28.504258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6113b3c244a05e21e4e52140d7ec4d27cd6855a17560a7cf6fa9c65a7568bc8","sha256:7ee1ec155ef48db41cc353d2d3088e07eb0ad4cf8e798c43736d4600d7206b2a"],"state_sha256":"303a3a89b66fa9e7d6dd3ca61aab8e303f740bf7cb7760250290d0b83990dac3"}