{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YEZANSJBIDWUFKIOMG6ZK5FCZJ","short_pith_number":"pith:YEZANSJB","schema_version":"1.0","canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","source":{"kind":"arxiv","id":"2507.19204","version":2},"attestation_state":"computed","paper":{"title":"Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin van Niekerk, Herman Kamper, Simon Malan","submitted_at":"2025-07-25T12:19:16Z","abstract_excerpt":"We investigate the problem of segmenting unlabeled speech into word-like units and clustering these to create a lexicon. Prior work can be categorized into two frameworks. Bottom-up methods first determine boundaries and then cluster the fixed segmented words into a lexicon. In contrast, top-down methods incorporate information from the clustered words to inform boundary selection. However, it is unclear whether top-down information is necessary to improve segmentation. To explore this, we look at two similar approaches that differ in whether top-down clustering informs boundary selection. Our"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.19204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-25T12:19:16Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"77cdced0c157b42bc0cf39c1e390dbe99c5d1de3e17c44c21271a3eaa255671b","abstract_canon_sha256":"0da8dd0342e5a35df19f5cfdd04df149afac9b43746be1e751e3bc49eaed94a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:11.423865Z","signature_b64":"f3f8sjhsvLTJpkKqseTuOZd6/uAtKj45FkGZKg+wZQ2Fkjzgr7HKNPMqs1UU722SeqbZM98QG8MG2FZBFbOUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","last_reissued_at":"2026-07-05T11:44:11.423354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:11.423354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin van Niekerk, Herman Kamper, Simon Malan","submitted_at":"2025-07-25T12:19:16Z","abstract_excerpt":"We investigate the problem of segmenting unlabeled speech into word-like units and clustering these to create a lexicon. Prior work can be categorized into two frameworks. Bottom-up methods first determine boundaries and then cluster the fixed segmented words into a lexicon. In contrast, top-down methods incorporate information from the clustered words to inform boundary selection. However, it is unclear whether top-down information is necessary to improve segmentation. To explore this, we look at two similar approaches that differ in whether top-down clustering informs boundary selection. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19204","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.19204/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.19204","created_at":"2026-07-05T11:44:11.423412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19204v2","created_at":"2026-07-05T11:44:11.423412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19204","created_at":"2026-07-05T11:44:11.423412+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEZANSJBIDWU","created_at":"2026-07-05T11:44:11.423412+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEZANSJBIDWUFKIO","created_at":"2026-07-05T11:44:11.423412+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEZANSJB","created_at":"2026-07-05T11:44:11.423412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ","json":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ.json","graph_json":"https://pith.science/api/pith-number/YEZANSJBIDWUFKIOMG6ZK5FCZJ/graph.json","events_json":"https://pith.science/api/pith-number/YEZANSJBIDWUFKIOMG6ZK5FCZJ/events.json","paper":"https://pith.science/paper/YEZANSJB"},"agent_actions":{"view_html":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ","download_json":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ.json","view_paper":"https://pith.science/paper/YEZANSJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19204&json=true","fetch_graph":"https://pith.science/api/pith-number/YEZANSJBIDWUFKIOMG6ZK5FCZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YEZANSJBIDWUFKIOMG6ZK5FCZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/action/storage_attestation","attest_author":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/action/author_attestation","sign_citation":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/action/citation_signature","submit_replication":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/action/replication_record"}},"created_at":"2026-07-05T11:44:11.423412+00:00","updated_at":"2026-07-05T11:44:11.423412+00:00"}