{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DG5LBOX6ER2J6M3QWXADERJU2K","short_pith_number":"pith:DG5LBOX6","schema_version":"1.0","canonical_sha256":"19bab0bafe24749f3370b5c0324534d29b3b904463af68af67e8102c272b2ab9","source":{"kind":"arxiv","id":"2006.11278","version":1},"attestation_state":"computed","paper":{"title":"The MCC-F1 curve: a performance evaluation technique for binary classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang Cao, Davide Chicco, Michael M. Hoffman","submitted_at":"2020-06-17T15:39:08Z","abstract_excerpt":"Many fields use the ROC curve and the PR curve as standard evaluations of binary classification methods. Analysis of ROC and PR, however, often gives misleading and inflated performance evaluations, especially with an imbalanced ground truth. Here, we demonstrate the problems with ROC and PR analysis through simulations, and propose the MCC-F1 curve to address these drawbacks. The MCC-F1 curve combines two informative single-threshold metrics, MCC and the F1 score. The MCC-F1 curve more clearly differentiates good and bad classifiers, even with imbalanced ground truths. We also introduce the M"},"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":"2006.11278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-17T15:39:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3745c88d924b38e61f3161c2321143750c060e79c70c33d224624b9318492bc","abstract_canon_sha256":"3e331d9ce2d93adb4451bb6727eb7bd62c5df3c3317d248697318fdd797da383"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:48.686599Z","signature_b64":"TnIddL9ECtoXfymBwezOhTK8jPxv8priyLX21KCfcGJ1iwhMkOEEmpJtb2K7+uEMGpVLiCj++oLuMyXZxx4EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19bab0bafe24749f3370b5c0324534d29b3b904463af68af67e8102c272b2ab9","last_reissued_at":"2026-07-05T01:11:48.686142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:48.686142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The MCC-F1 curve: a performance evaluation technique for binary classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang Cao, Davide Chicco, Michael M. Hoffman","submitted_at":"2020-06-17T15:39:08Z","abstract_excerpt":"Many fields use the ROC curve and the PR curve as standard evaluations of binary classification methods. Analysis of ROC and PR, however, often gives misleading and inflated performance evaluations, especially with an imbalanced ground truth. Here, we demonstrate the problems with ROC and PR analysis through simulations, and propose the MCC-F1 curve to address these drawbacks. The MCC-F1 curve combines two informative single-threshold metrics, MCC and the F1 score. The MCC-F1 curve more clearly differentiates good and bad classifiers, even with imbalanced ground truths. We also introduce the M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11278","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/2006.11278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.11278","created_at":"2026-07-05T01:11:48.686201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11278v1","created_at":"2026-07-05T01:11:48.686201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11278","created_at":"2026-07-05T01:11:48.686201+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG5LBOX6ER2J","created_at":"2026-07-05T01:11:48.686201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG5LBOX6ER2J6M3Q","created_at":"2026-07-05T01:11:48.686201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG5LBOX6","created_at":"2026-07-05T01:11:48.686201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13608","citing_title":"Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K","json":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K.json","graph_json":"https://pith.science/api/pith-number/DG5LBOX6ER2J6M3QWXADERJU2K/graph.json","events_json":"https://pith.science/api/pith-number/DG5LBOX6ER2J6M3QWXADERJU2K/events.json","paper":"https://pith.science/paper/DG5LBOX6"},"agent_actions":{"view_html":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K","download_json":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K.json","view_paper":"https://pith.science/paper/DG5LBOX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11278&json=true","fetch_graph":"https://pith.science/api/pith-number/DG5LBOX6ER2J6M3QWXADERJU2K/graph.json","fetch_events":"https://pith.science/api/pith-number/DG5LBOX6ER2J6M3QWXADERJU2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K/action/storage_attestation","attest_author":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K/action/author_attestation","sign_citation":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K/action/citation_signature","submit_replication":"https://pith.science/pith/DG5LBOX6ER2J6M3QWXADERJU2K/action/replication_record"}},"created_at":"2026-07-05T01:11:48.686201+00:00","updated_at":"2026-07-05T01:11:48.686201+00:00"}