{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B2KXGKPQ2T5VC4LVRPAFVSECTL","short_pith_number":"pith:B2KXGKPQ","schema_version":"1.0","canonical_sha256":"0e957329f0d4fb5171758bc05ac8829ae98987525e2580fd98c47baf6bed001e","source":{"kind":"arxiv","id":"2204.05205","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Machine Learning Model Evaluation in Pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Aaditya Prakash, Dinkar Juyal, Harsha Pokkalla, Shreya Chakraborty, Syed Ashar Javed, Zahil Shanis","submitted_at":"2022-04-11T15:49:12Z","abstract_excerpt":"Machine Learning has been applied to pathology images in research and clinical practice with promising outcomes. However, standard ML models often lack the rigorous evaluation required for clinical decisions. Machine learning techniques for natural images are ill-equipped to deal with pathology images that are significantly large and noisy, require expensive labeling, are hard to interpret, and are susceptible to spurious correlations. We propose a set of practical guidelines for ML evaluation in pathology that address the above concerns. The paper includes measures for setting up the evaluati"},"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":"2204.05205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2022-04-11T15:49:12Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d67adc480ba07fd1d1dc20c60cf75f9223595ad94f076ca18513023bd17cd1b7","abstract_canon_sha256":"13ae2fab0ad31aa6bdbe46832f8953ba245b37f2d44599856c02d5b86ce7df49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:15.799111Z","signature_b64":"yG0EOVXi3Cx2VWXUSZ1hxFxhLa9+LHjrq9gOgSVpjzjv3yEW1xQL9K/HAKfD+jWi5Ffd1oNxT0ny+qaujQihAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e957329f0d4fb5171758bc05ac8829ae98987525e2580fd98c47baf6bed001e","last_reissued_at":"2026-07-05T04:15:15.798602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:15.798602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Machine Learning Model Evaluation in Pathology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Aaditya Prakash, Dinkar Juyal, Harsha Pokkalla, Shreya Chakraborty, Syed Ashar Javed, Zahil Shanis","submitted_at":"2022-04-11T15:49:12Z","abstract_excerpt":"Machine Learning has been applied to pathology images in research and clinical practice with promising outcomes. However, standard ML models often lack the rigorous evaluation required for clinical decisions. Machine learning techniques for natural images are ill-equipped to deal with pathology images that are significantly large and noisy, require expensive labeling, are hard to interpret, and are susceptible to spurious correlations. We propose a set of practical guidelines for ML evaluation in pathology that address the above concerns. The paper includes measures for setting up the evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05205","kind":"arxiv","version":3},"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/2204.05205/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":"2204.05205","created_at":"2026-07-05T04:15:15.798664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05205v3","created_at":"2026-07-05T04:15:15.798664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05205","created_at":"2026-07-05T04:15:15.798664+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2KXGKPQ2T5V","created_at":"2026-07-05T04:15:15.798664+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2KXGKPQ2T5VC4LV","created_at":"2026-07-05T04:15:15.798664+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2KXGKPQ","created_at":"2026-07-05T04:15:15.798664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09809","citing_title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL","json":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL.json","graph_json":"https://pith.science/api/pith-number/B2KXGKPQ2T5VC4LVRPAFVSECTL/graph.json","events_json":"https://pith.science/api/pith-number/B2KXGKPQ2T5VC4LVRPAFVSECTL/events.json","paper":"https://pith.science/paper/B2KXGKPQ"},"agent_actions":{"view_html":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL","download_json":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL.json","view_paper":"https://pith.science/paper/B2KXGKPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05205&json=true","fetch_graph":"https://pith.science/api/pith-number/B2KXGKPQ2T5VC4LVRPAFVSECTL/graph.json","fetch_events":"https://pith.science/api/pith-number/B2KXGKPQ2T5VC4LVRPAFVSECTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL/action/storage_attestation","attest_author":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL/action/author_attestation","sign_citation":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL/action/citation_signature","submit_replication":"https://pith.science/pith/B2KXGKPQ2T5VC4LVRPAFVSECTL/action/replication_record"}},"created_at":"2026-07-05T04:15:15.798664+00:00","updated_at":"2026-07-05T04:15:15.798664+00:00"}