{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YEZANSJBIDWUFKIOMG6ZK5FCZJ","short_pith_number":"pith:YEZANSJB","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"},"canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","source":{"kind":"arxiv","id":"2507.19204","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19204","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19204v2","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19204","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"YEZANSJBIDWU","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"YEZANSJBIDWUFKIO","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"YEZANSJB","created_at":"2026-07-05T11:44:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YEZANSJBIDWUFKIOMG6ZK5FCZJ","target":"record","payload":{"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"},"canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","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"},"source_kind":"arxiv","source_id":"2507.19204","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Lr8iA3Huq+ZfiHgaXg9MZrM5Dwi3D7nocv4yDOCXyzWJx5duAw+7Mq1Tc9o8whRFuJLhb8rp3E9O9JGd5rUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:15:02.874139Z"},"content_sha256":"7ff298c841dfdd2bd28db1af0e6f51b7b4790171b6e8657c094d1a3e310d0db3","schema_version":"1.0","event_id":"sha256:7ff298c841dfdd2bd28db1af0e6f51b7b4790171b6e8657c094d1a3e310d0db3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YEZANSJBIDWUFKIOMG6ZK5FCZJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvmH4oRZ5q+1YejlcELCup2vPp7BuHPcw7iykM0FQMs89sPGrqHDddm8rAXnnaYzujPz2InG4nruJCBTHJ7ZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:15:02.874685Z"},"content_sha256":"b05f893bc000e4569690e05560084c298f18aaad7d20ecae3a32206e7c3ee756","schema_version":"1.0","event_id":"sha256:b05f893bc000e4569690e05560084c298f18aaad7d20ecae3a32206e7c3ee756"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/bundle.json","state_url":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:15:02Z","links":{"resolver":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ","bundle":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/bundle.json","state":"https://pith.science/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEZANSJBIDWUFKIOMG6ZK5FCZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YEZANSJBIDWUFKIOMG6ZK5FCZJ","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":"0da8dd0342e5a35df19f5cfdd04df149afac9b43746be1e751e3bc49eaed94a0","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-25T12:19:16Z","title_canon_sha256":"77cdced0c157b42bc0cf39c1e390dbe99c5d1de3e17c44c21271a3eaa255671b"},"schema_version":"1.0","source":{"id":"2507.19204","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19204","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19204v2","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19204","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"YEZANSJBIDWU","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"YEZANSJBIDWUFKIO","created_at":"2026-07-05T11:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"YEZANSJB","created_at":"2026-07-05T11:44:11Z"}],"graph_snapshots":[{"event_id":"sha256:b05f893bc000e4569690e05560084c298f18aaad7d20ecae3a32206e7c3ee756","target":"graph","created_at":"2026-07-05T11:44:11Z","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/2507.19204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin van Niekerk, Herman Kamper, Simon Malan","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-25T12:19:16Z","title":"Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19204","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":"sha256:7ff298c841dfdd2bd28db1af0e6f51b7b4790171b6e8657c094d1a3e310d0db3","target":"record","created_at":"2026-07-05T11:44:11Z","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":"0da8dd0342e5a35df19f5cfdd04df149afac9b43746be1e751e3bc49eaed94a0","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-25T12:19:16Z","title_canon_sha256":"77cdced0c157b42bc0cf39c1e390dbe99c5d1de3e17c44c21271a3eaa255671b"},"schema_version":"1.0","source":{"id":"2507.19204","kind":"arxiv","version":2}},"canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c13206c92140ed42a90e61bd9574a2ca6eee12643c4c05b42d1cf98aa5bb3dbf","first_computed_at":"2026-07-05T11:44:11.423354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:11.423354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f3f8sjhsvLTJpkKqseTuOZd6/uAtKj45FkGZKg+wZQ2Fkjzgr7HKNPMqs1UU722SeqbZM98QG8MG2FZBFbOUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:11.423865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19204","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ff298c841dfdd2bd28db1af0e6f51b7b4790171b6e8657c094d1a3e310d0db3","sha256:b05f893bc000e4569690e05560084c298f18aaad7d20ecae3a32206e7c3ee756"],"state_sha256":"c8a699f73ab3c05f9835f3a8dc1d5f90dadc6e22649143dda0cdc7449ca57a9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqV6EYxGN3TzBCXviXfYXO+nHRt6wceCd+eFQsYaAlgTVUTVBWnK0Rr0E3Sn6O9OVzdBNllsEe5t00Kj2Cy5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:15:02.884207Z","bundle_sha256":"a50e7d7a03a9eb68d42ab3d7f9030a72d4a77fc067092d90ac3cc83d2cdbcd1f"}}