{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QPDX7HD4LFKLOI2UKNELIFD5SZ","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":"f905ab9631bbc3c1be3677c0c598b04c998baaf52e573f05db652aae3eb87818","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T20:05:36Z","title_canon_sha256":"583f64f7b7720676e3bf5b1353c98159dbc3b2f3ffd532951fe2df7ee3f4bb2b"},"schema_version":"1.0","source":{"id":"2310.10803","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10803","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10803v3","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10803","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"QPDX7HD4LFKL","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"QPDX7HD4LFKLOI2U","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"QPDX7HD4","created_at":"2026-07-05T10:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:5b4823f21dc98ed512fa7256480d0a0d0118bf6292b2908b480d7d5b330f45f9","target":"graph","created_at":"2026-07-05T10:46:52Z","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/2310.10803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we demonstrate that a syllabic organization emerges in learning sentence-level representation of speech. In particular, we adopt \"self-distillation\" objective to fine-tune the pretrained HuBERT with an aggregator token that summarizes the entire sentence. Without any supervision, the resulting model draws definite boundaries in speech, and the repres","authors_text":"Abdelrahman Mohamed, Alan W Black, Cheol Jun Cho, Gopala K. Anumanchipalli, Shang-Wen Li","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T20:05:36Z","title":"SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10803","kind":"arxiv","version":3},"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":"sha256:8f64c5b9789175da1a8f19d42c3fda30f871a01ff0972888d8c9d6f1dc4abbf2","target":"record","created_at":"2026-07-05T10:46:52Z","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":"f905ab9631bbc3c1be3677c0c598b04c998baaf52e573f05db652aae3eb87818","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T20:05:36Z","title_canon_sha256":"583f64f7b7720676e3bf5b1353c98159dbc3b2f3ffd532951fe2df7ee3f4bb2b"},"schema_version":"1.0","source":{"id":"2310.10803","kind":"arxiv","version":3}},"canonical_sha256":"83c77f9c7c5954b723545348b4147d96694eced132ed8f66dce67ab76179921e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83c77f9c7c5954b723545348b4147d96694eced132ed8f66dce67ab76179921e","first_computed_at":"2026-07-05T10:46:52.995539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:52.995539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9FCZKeuiXMLVruE4n0w+xJKWEJJNSgkS2dB+qCsdDUU+ZR9clm9sCUaFrP/W69lLVqSEtQIBZxbG3y1Kh0kDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:52.996095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10803","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f64c5b9789175da1a8f19d42c3fda30f871a01ff0972888d8c9d6f1dc4abbf2","sha256:5b4823f21dc98ed512fa7256480d0a0d0118bf6292b2908b480d7d5b330f45f9"],"state_sha256":"3a2dbad6f89d32cdc335c4d936211ac60d21169ccb61826db070b0b2792b4e98"}