{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:U6SKTFMI7KMJSV42YQGPOP6TSS","short_pith_number":"pith:U6SKTFMI","canonical_record":{"source":{"id":"1602.06989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d697418de04964d073951b2912821403332131d12dd6ba68496cd5b5f8abab91","abstract_canon_sha256":"26f7658f9ad959dcd61e8b29c7cb1c4f0394f52391f77cc3bdd6058635500ea2"},"schema_version":"1.0"},"canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","source":{"kind":"arxiv","id":"1602.06989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06989","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06989v1","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06989","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"U6SKTFMI7KMJ","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U6SKTFMI7KMJSV42","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U6SKTFMI","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:U6SKTFMI7KMJSV42YQGPOP6TSS","target":"record","payload":{"canonical_record":{"source":{"id":"1602.06989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d697418de04964d073951b2912821403332131d12dd6ba68496cd5b5f8abab91","abstract_canon_sha256":"26f7658f9ad959dcd61e8b29c7cb1c4f0394f52391f77cc3bdd6058635500ea2"},"schema_version":"1.0"},"canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:07.473733Z","signature_b64":"fNqDTGJZtNFoxgO6vem7wCwsB0AddVXhEw3OD+lP1G/2bbZ+WSNViHLRxvTXOqO5SohlQ820ie1gPsLtLikXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","last_reissued_at":"2026-05-18T01:20:07.473175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:07.473175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.06989","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":"2026-05-18T01:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfVQ9l4W6JdhZcKakPV5RW5Nh33bolrpOOdj67FEJVWqf0MF2AqXj4KbWTlyNazrgHga0tJGhmimrv79HcPFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:32:45.731982Z"},"content_sha256":"81ecd4537da1776e3abf2f3b612cf1b162ff8bcbbbf9c86a902de8d92fcaecd3","schema_version":"1.0","event_id":"sha256:81ecd4537da1776e3abf2f3b612cf1b162ff8bcbbbf9c86a902de8d92fcaecd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:U6SKTFMI7KMJSV42YQGPOP6TSS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recovering the number of clusters in data sets with noise features using feature rescaling factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christian Hennig, Renato Cordeiro de Amorim","submitted_at":"2016-02-22T22:40:00Z","abstract_excerpt":"In this paper we introduce three methods for re-scaling data sets aiming at improving the likelihood of clustering validity indexes to return the true number of spherical Gaussian clusters with additional noise features. Our method obtains feature re-scaling factors taking into account the structure of a given data set and the intuitive idea that different features may have different degrees of relevance at different clusters.\n  We experiment with the Silhouette (using squared Euclidean, Manhattan, and the p$^{th}$ power of the Minkowski distance), Dunn's, Calinski-Harabasz and Hartigan indexe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06989","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":""},"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":"2026-05-18T01:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/WpbwtrVPZ+/uj5XZuGfQNNlAPjTm7s7IUqhF3jSjZapRaZUs6G7GksRhK1BvegScefMT9yC8EUBdh/r8/fOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:32:45.732396Z"},"content_sha256":"fa1d90a483b85c2050ef8f66935b4a48e17abf39f7d63cbba4a649ae60e275bb","schema_version":"1.0","event_id":"sha256:fa1d90a483b85c2050ef8f66935b4a48e17abf39f7d63cbba4a649ae60e275bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/bundle.json","state_url":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/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":"2026-06-08T13:32:45Z","links":{"resolver":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS","bundle":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/bundle.json","state":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:U6SKTFMI7KMJSV42YQGPOP6TSS","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":"26f7658f9ad959dcd61e8b29c7cb1c4f0394f52391f77cc3bdd6058635500ea2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","title_canon_sha256":"d697418de04964d073951b2912821403332131d12dd6ba68496cd5b5f8abab91"},"schema_version":"1.0","source":{"id":"1602.06989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06989","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06989v1","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06989","created_at":"2026-05-18T01:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"U6SKTFMI7KMJ","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U6SKTFMI7KMJSV42","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U6SKTFMI","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:fa1d90a483b85c2050ef8f66935b4a48e17abf39f7d63cbba4a649ae60e275bb","target":"graph","created_at":"2026-05-18T01:20:07Z","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"},"paper":{"abstract_excerpt":"In this paper we introduce three methods for re-scaling data sets aiming at improving the likelihood of clustering validity indexes to return the true number of spherical Gaussian clusters with additional noise features. Our method obtains feature re-scaling factors taking into account the structure of a given data set and the intuitive idea that different features may have different degrees of relevance at different clusters.\n  We experiment with the Silhouette (using squared Euclidean, Manhattan, and the p$^{th}$ power of the Minkowski distance), Dunn's, Calinski-Harabasz and Hartigan indexe","authors_text":"Christian Hennig, Renato Cordeiro de Amorim","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","title":"Recovering the number of clusters in data sets with noise features using feature rescaling factors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06989","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":"sha256:81ecd4537da1776e3abf2f3b612cf1b162ff8bcbbbf9c86a902de8d92fcaecd3","target":"record","created_at":"2026-05-18T01:20:07Z","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":"26f7658f9ad959dcd61e8b29c7cb1c4f0394f52391f77cc3bdd6058635500ea2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","title_canon_sha256":"d697418de04964d073951b2912821403332131d12dd6ba68496cd5b5f8abab91"},"schema_version":"1.0","source":{"id":"1602.06989","kind":"arxiv","version":1}},"canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","first_computed_at":"2026-05-18T01:20:07.473175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:07.473175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNqDTGJZtNFoxgO6vem7wCwsB0AddVXhEw3OD+lP1G/2bbZ+WSNViHLRxvTXOqO5SohlQ820ie1gPsLtLikXCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:07.473733Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.06989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81ecd4537da1776e3abf2f3b612cf1b162ff8bcbbbf9c86a902de8d92fcaecd3","sha256:fa1d90a483b85c2050ef8f66935b4a48e17abf39f7d63cbba4a649ae60e275bb"],"state_sha256":"4b65fe583fab9bd6454eaec0837848230bf40cb729aee39b5bf0c9763b663b6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtPfdulNrf8lCD5CTBMiBFkCzEepNCm+gzgJwHiwG2ooDay3/P/bEnYCfZIK/4ryDFJ6wXFv5G+oDuWa2RWnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T13:32:45.734458Z","bundle_sha256":"750c39a187b282a6de887e4b31928c4c8a24aa94260b7e3aaf0ffc9b23d7e067"}}