{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KS2K77ZJCRA7BPNSD4VXEMKSKT","short_pith_number":"pith:KS2K77ZJ","canonical_record":{"source":{"id":"2303.14301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T23:45:27Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"f50a562923fe041f31739b66e1f608859909e9fa77ef9b77a9bff6d70255ed76","abstract_canon_sha256":"50e99ed2d89b695c592c8e42bb38f7fdcb234621c7d4053785abdb72f036c442"},"schema_version":"1.0"},"canonical_sha256":"54b4afff291441f0bdb21f2b72315254caa23b789b0784b270e05cae6656fa64","source":{"kind":"arxiv","id":"2303.14301","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14301","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14301v4","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14301","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"KS2K77ZJCRA7","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"KS2K77ZJCRA7BPNS","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"KS2K77ZJ","created_at":"2026-07-05T10:15:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KS2K77ZJCRA7BPNSD4VXEMKSKT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.14301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T23:45:27Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"f50a562923fe041f31739b66e1f608859909e9fa77ef9b77a9bff6d70255ed76","abstract_canon_sha256":"50e99ed2d89b695c592c8e42bb38f7fdcb234621c7d4053785abdb72f036c442"},"schema_version":"1.0"},"canonical_sha256":"54b4afff291441f0bdb21f2b72315254caa23b789b0784b270e05cae6656fa64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:41.248751Z","signature_b64":"5eGmq20YnLiKu4hygeyEN7SlxKoMOzxw5cGA59ecFCd0r3oS0MXK3XcoORJqQZCuluNCONu9AaADkqmfguxDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b4afff291441f0bdb21f2b72315254caa23b789b0784b270e05cae6656fa64","last_reissued_at":"2026-07-05T10:15:41.248212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:41.248212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.14301","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbWTedFhZ9JXUzvcx7VIvTWCjSXyeDMeiSc4M9KcApkkeTB0duE95x+tpcdy1h9pFg9ywliiVNnhTT1cSkPKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:54:44.028370Z"},"content_sha256":"206df5d2424b7a39975e3a6784a3f2c0ba6a9c0932ec0e83f99309968043e543","schema_version":"1.0","event_id":"sha256:206df5d2424b7a39975e3a6784a3f2c0ba6a9c0932ec0e83f99309968043e543"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KS2K77ZJCRA7BPNSD4VXEMKSKT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language-Based Synthetic Data Generation for Cluster Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael J. Zellinger, Peter B\\\"uhlmann","submitted_at":"2023-03-24T23:45:27Z","abstract_excerpt":"Cluster analysis relies on effective benchmarks for evaluating and comparing different algorithms. Simulation studies on synthetic data are popular because important features of the data sets, such as the overlap between clusters, or the variation in cluster shapes, can be effectively varied. Unfortunately, creating evaluation scenarios is often laborious, as practitioners must translate higher-level scenario descriptions like \"clusters with very different shapes\" into lower-level geometric parameters such as cluster centers, covariance matrices, etc. To make benchmarks more convenient and inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14301","kind":"arxiv","version":4},"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/2303.14301/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":"2026-07-05T10:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWNrbtYFMDzFYa6XjVduNBCtiYp9y7Eyo4mQbWEhG5dLJ2dYY4x8T8aK3VQBLucxF81nZsC8gbLT15ftWK9ACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:54:44.029007Z"},"content_sha256":"a0b7cf705fb3aebed33d3439a983f6f14358dee534ea56dd63bbf6218cb8b931","schema_version":"1.0","event_id":"sha256:a0b7cf705fb3aebed33d3439a983f6f14358dee534ea56dd63bbf6218cb8b931"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/bundle.json","state_url":"https://pith.science/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/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":"2026-08-15T16:54:44Z","links":{"resolver":"https://pith.science/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT","bundle":"https://pith.science/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/bundle.json","state":"https://pith.science/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KS2K77ZJCRA7BPNSD4VXEMKSKT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KS2K77ZJCRA7BPNSD4VXEMKSKT","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":"50e99ed2d89b695c592c8e42bb38f7fdcb234621c7d4053785abdb72f036c442","cross_cats_sorted":["stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T23:45:27Z","title_canon_sha256":"f50a562923fe041f31739b66e1f608859909e9fa77ef9b77a9bff6d70255ed76"},"schema_version":"1.0","source":{"id":"2303.14301","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14301","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14301v4","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14301","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"KS2K77ZJCRA7","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"KS2K77ZJCRA7BPNS","created_at":"2026-07-05T10:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"KS2K77ZJ","created_at":"2026-07-05T10:15:41Z"}],"graph_snapshots":[{"event_id":"sha256:a0b7cf705fb3aebed33d3439a983f6f14358dee534ea56dd63bbf6218cb8b931","target":"graph","created_at":"2026-07-05T10:15:41Z","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/2303.14301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cluster analysis relies on effective benchmarks for evaluating and comparing different algorithms. Simulation studies on synthetic data are popular because important features of the data sets, such as the overlap between clusters, or the variation in cluster shapes, can be effectively varied. Unfortunately, creating evaluation scenarios is often laborious, as practitioners must translate higher-level scenario descriptions like \"clusters with very different shapes\" into lower-level geometric parameters such as cluster centers, covariance matrices, etc. To make benchmarks more convenient and inf","authors_text":"Michael J. Zellinger, Peter B\\\"uhlmann","cross_cats":["stat.CO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T23:45:27Z","title":"Natural Language-Based Synthetic Data Generation for Cluster Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14301","kind":"arxiv","version":4},"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":"sha256:206df5d2424b7a39975e3a6784a3f2c0ba6a9c0932ec0e83f99309968043e543","target":"record","created_at":"2026-07-05T10:15:41Z","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":"50e99ed2d89b695c592c8e42bb38f7fdcb234621c7d4053785abdb72f036c442","cross_cats_sorted":["stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T23:45:27Z","title_canon_sha256":"f50a562923fe041f31739b66e1f608859909e9fa77ef9b77a9bff6d70255ed76"},"schema_version":"1.0","source":{"id":"2303.14301","kind":"arxiv","version":4}},"canonical_sha256":"54b4afff291441f0bdb21f2b72315254caa23b789b0784b270e05cae6656fa64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54b4afff291441f0bdb21f2b72315254caa23b789b0784b270e05cae6656fa64","first_computed_at":"2026-07-05T10:15:41.248212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:41.248212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5eGmq20YnLiKu4hygeyEN7SlxKoMOzxw5cGA59ecFCd0r3oS0MXK3XcoORJqQZCuluNCONu9AaADkqmfguxDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:41.248751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14301","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:206df5d2424b7a39975e3a6784a3f2c0ba6a9c0932ec0e83f99309968043e543","sha256:a0b7cf705fb3aebed33d3439a983f6f14358dee534ea56dd63bbf6218cb8b931"],"state_sha256":"ce515695ccb0ebc912e687eafb486590508715bfe8f6d3dccdf3cf38cbb85251"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2pOu7x+EtppcIGwLmFORJb7SzKGsdJbI8KAmw4qN/535B7avN3f5TTUvFBGOCCabsasnBAatUKQ9UC+H6KeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:54:44.033243Z","bundle_sha256":"3d32ce2fb2bc5978ea8221f0ace48197cebc3c44dd1a5be0684499e03eb186c8"}}