{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:VBMEPX26MPC73NPCZXAED3NTEQ","short_pith_number":"pith:VBMEPX26","schema_version":"1.0","canonical_sha256":"a85847df5e63c5fdb5e2cdc041edb32434697631c4ba6d68f1f0abed90bd7318","source":{"kind":"arxiv","id":"1103.4767","version":1},"attestation_state":"computed","paper":{"title":"A comparison of Gap statistic definitions with and without logarithm function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ME","authors_text":"Karl-Hans Englmeier, Mojgan Mohajer, Volker J. Schmid","submitted_at":"2011-03-24T13:51:46Z","abstract_excerpt":"The Gap statistic is a standard method for determining the number of clusters in a set of data. The Gap statistic standardizes the graph of $\\log(W_{k})$, where $W_{k}$ is the within-cluster dispersion, by comparing it to its expectation under an appropriate null reference distribution of the data. We suggest to use $W_{k}$ instead of $\\log(W_{k})$, and to compare it to the expectation of $W_{k}$ under a null reference distribution. In fact, whenever a number fulfills the original Gap statistic inequality, this number also fulfills the inequality of a Gap statistic using $W_{k}$, but not \\text"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1103.4767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-03-24T13:51:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d01c85759fc1ffa11a9b428171d0ce8946dcc6496aa20d9ca9470e7a518aa05a","abstract_canon_sha256":"15951d9ab938da21da7bd5ebce856000582e06c87f7e67c961e7fe57c31f20a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:26:00.894849Z","signature_b64":"tO+jVQoFLo0JuRW1tEzsvbq4YAaQZBX7rKd1WQL7li2HiJIlnlMphoE2Pfd6YNE2zeyjFY8PMaSMEofRHAW8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85847df5e63c5fdb5e2cdc041edb32434697631c4ba6d68f1f0abed90bd7318","last_reissued_at":"2026-05-18T04:26:00.894263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:26:00.894263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparison of Gap statistic definitions with and without logarithm function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ME","authors_text":"Karl-Hans Englmeier, Mojgan Mohajer, Volker J. Schmid","submitted_at":"2011-03-24T13:51:46Z","abstract_excerpt":"The Gap statistic is a standard method for determining the number of clusters in a set of data. The Gap statistic standardizes the graph of $\\log(W_{k})$, where $W_{k}$ is the within-cluster dispersion, by comparing it to its expectation under an appropriate null reference distribution of the data. We suggest to use $W_{k}$ instead of $\\log(W_{k})$, and to compare it to the expectation of $W_{k}$ under a null reference distribution. In fact, whenever a number fulfills the original Gap statistic inequality, this number also fulfills the inequality of a Gap statistic using $W_{k}$, but not \\text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.4767","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1103.4767","created_at":"2026-05-18T04:26:00.894377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1103.4767v1","created_at":"2026-05-18T04:26:00.894377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.4767","created_at":"2026-05-18T04:26:00.894377+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBMEPX26MPC7","created_at":"2026-05-18T12:26:42.757692+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBMEPX26MPC73NPC","created_at":"2026-05-18T12:26:42.757692+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBMEPX26","created_at":"2026-05-18T12:26:42.757692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ","json":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ.json","graph_json":"https://pith.science/api/pith-number/VBMEPX26MPC73NPCZXAED3NTEQ/graph.json","events_json":"https://pith.science/api/pith-number/VBMEPX26MPC73NPCZXAED3NTEQ/events.json","paper":"https://pith.science/paper/VBMEPX26"},"agent_actions":{"view_html":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ","download_json":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ.json","view_paper":"https://pith.science/paper/VBMEPX26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1103.4767&json=true","fetch_graph":"https://pith.science/api/pith-number/VBMEPX26MPC73NPCZXAED3NTEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VBMEPX26MPC73NPCZXAED3NTEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ/action/storage_attestation","attest_author":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ/action/author_attestation","sign_citation":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ/action/citation_signature","submit_replication":"https://pith.science/pith/VBMEPX26MPC73NPCZXAED3NTEQ/action/replication_record"}},"created_at":"2026-05-18T04:26:00.894377+00:00","updated_at":"2026-05-18T04:26:00.894377+00:00"}