{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VO7VLRDWDOPWYBSUACTJT6AL7V","short_pith_number":"pith:VO7VLRDW","canonical_record":{"source":{"id":"2606.10781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T12:33:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a6718d15b4a9da78705cd9ab8b2da71193a9262d8f0497c6dd8539fa3c9d662e","abstract_canon_sha256":"0c755893387ac00cca9bb51677bb47f458c59684aa7e1b39129d566986f97d19"},"schema_version":"1.0"},"canonical_sha256":"abbf55c4761b9f6c065400a699f80bfd4db6564ad336d74e57fc171429fe93e5","source":{"kind":"arxiv","id":"2606.10781","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10781","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10781v1","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10781","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"VO7VLRDWDOPW","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"VO7VLRDWDOPWYBSU","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"VO7VLRDW","created_at":"2026-06-10T01:10:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VO7VLRDWDOPWYBSUACTJT6AL7V","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T12:33:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a6718d15b4a9da78705cd9ab8b2da71193a9262d8f0497c6dd8539fa3c9d662e","abstract_canon_sha256":"0c755893387ac00cca9bb51677bb47f458c59684aa7e1b39129d566986f97d19"},"schema_version":"1.0"},"canonical_sha256":"abbf55c4761b9f6c065400a699f80bfd4db6564ad336d74e57fc171429fe93e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:40.317956Z","signature_b64":"KlfEqCNvWs1ZEaRn7yFADLVHAPpSzmNTDTMlVW2qBs26lIJy7sS0CkYSstitcnI5uUpgYtKz8Fon10rencBBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abbf55c4761b9f6c065400a699f80bfd4db6564ad336d74e57fc171429fe93e5","last_reissued_at":"2026-06-10T01:10:40.317044Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:40.317044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10781","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0wKMYFgb98SWu+qv071DjybVd9XQsuLHEh1Em4yCbkVdUla5iBa72WaPBclcDWCBX69SB2Aay7DUZnWUJPqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T19:20:40.118396Z"},"content_sha256":"dc03872fe7fef986a71d8f2078719387fe32882fbf307c91316b97216167fba8","schema_version":"1.0","event_id":"sha256:dc03872fe7fef986a71d8f2078719387fe32882fbf307c91316b97216167fba8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VO7VLRDWDOPWYBSUACTJT6AL7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recovering the Zipfian Distribution in Unsupervised Term Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Danel Slabbert, Herman Kamper, Simon Malan","submitted_at":"2026-06-09T12:33:59Z","abstract_excerpt":"Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach -- K-means -- produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10781","kind":"arxiv","version":1},"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/2606.10781/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":"2026-06-10T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hkr1AyRy0kmIdgbMlswn4IeoPMWvseBtmHp1uErxRwL+xdWXMLfo89mrpaGVE8a3QrIfYlmxXp17On2mJ1qBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T19:20:40.118781Z"},"content_sha256":"0c15fe4f46aac8f83c92df3311469adb7f8e1d7be0a76d45080e0e0f60ba7a05","schema_version":"1.0","event_id":"sha256:0c15fe4f46aac8f83c92df3311469adb7f8e1d7be0a76d45080e0e0f60ba7a05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/bundle.json","state_url":"https://pith.science/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/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":"2026-06-24T19:20:40Z","links":{"resolver":"https://pith.science/pith/VO7VLRDWDOPWYBSUACTJT6AL7V","bundle":"https://pith.science/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/bundle.json","state":"https://pith.science/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VO7VLRDWDOPWYBSUACTJT6AL7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VO7VLRDWDOPWYBSUACTJT6AL7V","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":"0c755893387ac00cca9bb51677bb47f458c59684aa7e1b39129d566986f97d19","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T12:33:59Z","title_canon_sha256":"a6718d15b4a9da78705cd9ab8b2da71193a9262d8f0497c6dd8539fa3c9d662e"},"schema_version":"1.0","source":{"id":"2606.10781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10781","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10781v1","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10781","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"VO7VLRDWDOPW","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"VO7VLRDWDOPWYBSU","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"VO7VLRDW","created_at":"2026-06-10T01:10:40Z"}],"graph_snapshots":[{"event_id":"sha256:0c15fe4f46aac8f83c92df3311469adb7f8e1d7be0a76d45080e0e0f60ba7a05","target":"graph","created_at":"2026-06-10T01:10:40Z","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/2606.10781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach -- K-means -- produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-b","authors_text":"Danel Slabbert, Herman Kamper, Simon Malan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T12:33:59Z","title":"Recovering the Zipfian Distribution in Unsupervised Term Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10781","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:dc03872fe7fef986a71d8f2078719387fe32882fbf307c91316b97216167fba8","target":"record","created_at":"2026-06-10T01:10:40Z","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":"0c755893387ac00cca9bb51677bb47f458c59684aa7e1b39129d566986f97d19","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T12:33:59Z","title_canon_sha256":"a6718d15b4a9da78705cd9ab8b2da71193a9262d8f0497c6dd8539fa3c9d662e"},"schema_version":"1.0","source":{"id":"2606.10781","kind":"arxiv","version":1}},"canonical_sha256":"abbf55c4761b9f6c065400a699f80bfd4db6564ad336d74e57fc171429fe93e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abbf55c4761b9f6c065400a699f80bfd4db6564ad336d74e57fc171429fe93e5","first_computed_at":"2026-06-10T01:10:40.317044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:40.317044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KlfEqCNvWs1ZEaRn7yFADLVHAPpSzmNTDTMlVW2qBs26lIJy7sS0CkYSstitcnI5uUpgYtKz8Fon10rencBBAA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:40.317956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc03872fe7fef986a71d8f2078719387fe32882fbf307c91316b97216167fba8","sha256:0c15fe4f46aac8f83c92df3311469adb7f8e1d7be0a76d45080e0e0f60ba7a05"],"state_sha256":"af66f894fb41a883981fd3341b0f67522fd6d0d5205b62680a7afb123ae8bcd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jeNsh9yQpMQ67jyOPTE4bkwHzLs8xURdj09ehOjKC+XBri6eroYgzZc6edrbzJ6cM8cGTuoUkH2b8k6bRXOSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T19:20:40.120888Z","bundle_sha256":"af0f67375fe028480c661286a449c5fa8674995dcbe500257077ff1f46c6f455"}}