{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FAAEILFL35NQG6UQSWMRLF5YNV","short_pith_number":"pith:FAAEILFL","canonical_record":{"source":{"id":"2002.02701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T10:20:49Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"265b9aab005e7723e139a5fb28f12a09e51f9cdb7532d81b70438cd00a467c0a","abstract_canon_sha256":"89cdbde4bc5355531f7d162dfd857771338a849e3c4be82ceba9e1c203859543"},"schema_version":"1.0"},"canonical_sha256":"2800442cabdf5b037a9095991597b86d4cec9ce8e5ecdcce8c8e4f351edf8012","source":{"kind":"arxiv","id":"2002.02701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02701","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02701v1","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02701","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"FAAEILFL35NQ","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"FAAEILFL35NQG6UQ","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"FAAEILFL","created_at":"2026-07-05T00:38:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FAAEILFL35NQG6UQSWMRLF5YNV","target":"record","payload":{"canonical_record":{"source":{"id":"2002.02701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T10:20:49Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"265b9aab005e7723e139a5fb28f12a09e51f9cdb7532d81b70438cd00a467c0a","abstract_canon_sha256":"89cdbde4bc5355531f7d162dfd857771338a849e3c4be82ceba9e1c203859543"},"schema_version":"1.0"},"canonical_sha256":"2800442cabdf5b037a9095991597b86d4cec9ce8e5ecdcce8c8e4f351edf8012","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:58.166756Z","signature_b64":"HgYPIeyeR1IGki1miz/erjvlY2Lm7ptSNiEnfb0yMFZZ5enLlVIPAlF2xjQgVxzZHI8yW52sCOk2iQAhEApeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2800442cabdf5b037a9095991597b86d4cec9ce8e5ecdcce8c8e4f351edf8012","last_reissued_at":"2026-07-05T00:38:58.166264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:58.166264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.02701","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":"2026-07-05T00:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNldYseVdK7clEkWAYvoLkyrLWAIPP+7G0N/Xm+iOf5tANyysRAgFTuA0vKolUncqbd4lfWTPjQa8BocnfgKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T11:25:17.992205Z"},"content_sha256":"a8095267a221be6ac8742142e8f3cde93cd615fd47fba7ec04e5dcb101c9897a","schema_version":"1.0","event_id":"sha256:a8095267a221be6ac8742142e8f3cde93cd615fd47fba7ec04e5dcb101c9897a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FAAEILFL35NQG6UQSWMRLF5YNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A novel initialisation based on hospital-resident assignment for the k-modes algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Henry Wilde, Jonathan Gillard, Vincent Knight","submitted_at":"2020-02-07T10:20:49Z","abstract_excerpt":"This paper presents a new way of selecting an initial solution for the k-modes algorithm that allows for a notion of mathematical fairness and a leverage of the data that the common initialisations from literature do not. The method, which utilises the Hospital-Resident Assignment Problem to find the set of initial cluster centroids, is compared with the current initialisations on both benchmark datasets and a body of newly generated artificial datasets. Based on this analysis, the proposed method is shown to outperform the other initialisations in the majority of cases, especially when the nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02701","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/2002.02701/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":"2026-07-05T00:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cc2dsN+lCQlsBu8W81RR0vlGbaQGdNHkrnep2jZECHZJidW1zetaoqLhoz7HWNmGMClc/C9Es3du9q0XZZztBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T11:25:17.992599Z"},"content_sha256":"c8007a458944972e20aa8be1eae8938723bad2cad2ea4eeb315c7a104571defb","schema_version":"1.0","event_id":"sha256:c8007a458944972e20aa8be1eae8938723bad2cad2ea4eeb315c7a104571defb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAAEILFL35NQG6UQSWMRLF5YNV/bundle.json","state_url":"https://pith.science/pith/FAAEILFL35NQG6UQSWMRLF5YNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAAEILFL35NQG6UQSWMRLF5YNV/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":"2026-07-18T11:25:17Z","links":{"resolver":"https://pith.science/pith/FAAEILFL35NQG6UQSWMRLF5YNV","bundle":"https://pith.science/pith/FAAEILFL35NQG6UQSWMRLF5YNV/bundle.json","state":"https://pith.science/pith/FAAEILFL35NQG6UQSWMRLF5YNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAAEILFL35NQG6UQSWMRLF5YNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FAAEILFL35NQG6UQSWMRLF5YNV","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":"89cdbde4bc5355531f7d162dfd857771338a849e3c4be82ceba9e1c203859543","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T10:20:49Z","title_canon_sha256":"265b9aab005e7723e139a5fb28f12a09e51f9cdb7532d81b70438cd00a467c0a"},"schema_version":"1.0","source":{"id":"2002.02701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02701","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02701v1","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02701","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"FAAEILFL35NQ","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"FAAEILFL35NQG6UQ","created_at":"2026-07-05T00:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"FAAEILFL","created_at":"2026-07-05T00:38:58Z"}],"graph_snapshots":[{"event_id":"sha256:c8007a458944972e20aa8be1eae8938723bad2cad2ea4eeb315c7a104571defb","target":"graph","created_at":"2026-07-05T00:38:58Z","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/2002.02701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a new way of selecting an initial solution for the k-modes algorithm that allows for a notion of mathematical fairness and a leverage of the data that the common initialisations from literature do not. The method, which utilises the Hospital-Resident Assignment Problem to find the set of initial cluster centroids, is compared with the current initialisations on both benchmark datasets and a body of newly generated artificial datasets. Based on this analysis, the proposed method is shown to outperform the other initialisations in the majority of cases, especially when the nu","authors_text":"Henry Wilde, Jonathan Gillard, Vincent Knight","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T10:20:49Z","title":"A novel initialisation based on hospital-resident assignment for the k-modes algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02701","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:a8095267a221be6ac8742142e8f3cde93cd615fd47fba7ec04e5dcb101c9897a","target":"record","created_at":"2026-07-05T00:38:58Z","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":"89cdbde4bc5355531f7d162dfd857771338a849e3c4be82ceba9e1c203859543","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T10:20:49Z","title_canon_sha256":"265b9aab005e7723e139a5fb28f12a09e51f9cdb7532d81b70438cd00a467c0a"},"schema_version":"1.0","source":{"id":"2002.02701","kind":"arxiv","version":1}},"canonical_sha256":"2800442cabdf5b037a9095991597b86d4cec9ce8e5ecdcce8c8e4f351edf8012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2800442cabdf5b037a9095991597b86d4cec9ce8e5ecdcce8c8e4f351edf8012","first_computed_at":"2026-07-05T00:38:58.166264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:58.166264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgYPIeyeR1IGki1miz/erjvlY2Lm7ptSNiEnfb0yMFZZ5enLlVIPAlF2xjQgVxzZHI8yW52sCOk2iQAhEApeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:58.166756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.02701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8095267a221be6ac8742142e8f3cde93cd615fd47fba7ec04e5dcb101c9897a","sha256:c8007a458944972e20aa8be1eae8938723bad2cad2ea4eeb315c7a104571defb"],"state_sha256":"2e2c161f4bbdc73c98eb88d65031f33c5177ab51479f9080d45339b7d2525425"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRikTD4Fx5xB8aIcF5xQJYFYGXhYRkjitfghtPNOd7HDGylM3Dg41oLfjxXnaVEVNwyXgZmRZm9J+Fb4PVFhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T11:25:17.994742Z","bundle_sha256":"38ea20673355176ae0e986aae5efba5508a2a0d11e3d694da5247ff64c7fb02f"}}