{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZIDN254BXDQIBKES2INRNYSEWC","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":"4d02d598065742a3e25abc3e4a2ab6fe7378956a82044f0ce20c7ce05238c4f6","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T05:19:04Z","title_canon_sha256":"e5a0d9073b5e3104f3ad928902274ab8d4b04d8ca1dcdb043a35a2764b2b16d9"},"schema_version":"1.0","source":{"id":"2305.11435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11435","created_at":"2026-07-05T06:33:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11435v2","created_at":"2026-07-05T06:33:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11435","created_at":"2026-07-05T06:33:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZIDN254BXDQI","created_at":"2026-07-05T06:33:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZIDN254BXDQIBKES","created_at":"2026-07-05T06:33:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZIDN254B","created_at":"2026-07-05T06:33:45Z"}],"graph_snapshots":[{"event_id":"sha256:fe7ca8ca56086e3a90b11ea25f085da0f415b3bd547b004317b89faed1710e03","target":"graph","created_at":"2026-07-05T06:33:45Z","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/2305.11435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we show that representations capturing syllabic units emerge when training a self-supervised speech model with a visually-grounded training objective. We demonstrate that a nearly identical model architecture (HuBERT) trained with a masked language modeling loss does not exhibit this same ability, suggesting that the visual grounding objective is responsible for the emergence of this phenomenon. We propose the use of a minimum cut algorithm to automatically predict syllable boundaries in speech, followed by a 2-stage clustering method to group identical syllables together. We sh","authors_text":"Abdelrahman Mohamed, David Harwath, Okko R\\\"as\\\"anen, Puyuan Peng, Shang-Wen Li","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T05:19:04Z","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11435","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":"sha256:1456167e3d7a4e73039a6ce2a3c346863e906722c49092cd5ff057836bc76ddb","target":"record","created_at":"2026-07-05T06:33:45Z","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":"4d02d598065742a3e25abc3e4a2ab6fe7378956a82044f0ce20c7ce05238c4f6","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T05:19:04Z","title_canon_sha256":"e5a0d9073b5e3104f3ad928902274ab8d4b04d8ca1dcdb043a35a2764b2b16d9"},"schema_version":"1.0","source":{"id":"2305.11435","kind":"arxiv","version":2}},"canonical_sha256":"ca06dd7781b8e080a892d21b16e244b09ded6c34ddae55f0bf02d878776ece1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca06dd7781b8e080a892d21b16e244b09ded6c34ddae55f0bf02d878776ece1a","first_computed_at":"2026-07-05T06:33:45.781852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:45.781852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ijR3QIv0uMk339VSKcjSoO56Boz4TtMAJONKXmyDTBhSsWR64yMdkSTXRyFdZJbx9fEwVTxAhRNODJZvURvUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:45.782302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1456167e3d7a4e73039a6ce2a3c346863e906722c49092cd5ff057836bc76ddb","sha256:fe7ca8ca56086e3a90b11ea25f085da0f415b3bd547b004317b89faed1710e03"],"state_sha256":"a99aade61a5f75bd16984d719a7986858b8b2314e450658998542b3e12ec69f4"}