{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AKM6LFRFKGMZXJTSO64VHFT74M","short_pith_number":"pith:AKM6LFRF","schema_version":"1.0","canonical_sha256":"0299e5962551999ba67277b953967fe32e5d5be8367aa54cafcd42c0eec4ed57","source":{"kind":"arxiv","id":"2102.12894","version":4},"attestation_state":"computed","paper":{"title":"Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andreas Hoetker, Ender Konukoglu, Ertunc Erdil, Olivio Donati, Sara Sangalli","submitted_at":"2021-02-21T09:49:36Z","abstract_excerpt":"Deep neural networks (DNNs) are notorious for making more mistakes for the classes that have substantially fewer samples than the others during training. Such class imbalance is ubiquitous in clinical applications and very crucial to handle because the classes with fewer samples most often correspond to critical cases (e.g., cancer) where misclassifications can have severe consequences. Not to miss such cases, binary classifiers need to be operated at high True Positive Rates (TPRs) by setting a higher threshold, but this comes at the cost of very high False Positive Rates (FPRs) for problems "},"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":"2102.12894","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T09:49:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b24952e823704004b92612a426bf2d0134fed7b5965f345d2fa412da448aefc8","abstract_canon_sha256":"6f7a2447a6dc38bd27ca60c0d540492409f75581b0f5cbdaedc9b64fa26a1065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:01.156883Z","signature_b64":"A8U2DmlVmCwGSIgRcVHLiXclkyembWtKg7PuAZku8r6XqAwcmYJDN+ABi0oSt4tTGbVRul3OT72UTd2CBnlJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0299e5962551999ba67277b953967fe32e5d5be8367aa54cafcd42c0eec4ed57","last_reissued_at":"2026-07-05T03:46:01.156451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:01.156451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andreas Hoetker, Ender Konukoglu, Ertunc Erdil, Olivio Donati, Sara Sangalli","submitted_at":"2021-02-21T09:49:36Z","abstract_excerpt":"Deep neural networks (DNNs) are notorious for making more mistakes for the classes that have substantially fewer samples than the others during training. Such class imbalance is ubiquitous in clinical applications and very crucial to handle because the classes with fewer samples most often correspond to critical cases (e.g., cancer) where misclassifications can have severe consequences. Not to miss such cases, binary classifiers need to be operated at high True Positive Rates (TPRs) by setting a higher threshold, but this comes at the cost of very high False Positive Rates (FPRs) for problems "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12894","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/2102.12894/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":"2102.12894","created_at":"2026-07-05T03:46:01.156508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12894v4","created_at":"2026-07-05T03:46:01.156508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12894","created_at":"2026-07-05T03:46:01.156508+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKM6LFRFKGMZ","created_at":"2026-07-05T03:46:01.156508+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKM6LFRFKGMZXJTS","created_at":"2026-07-05T03:46:01.156508+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKM6LFRF","created_at":"2026-07-05T03:46:01.156508+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/AKM6LFRFKGMZXJTSO64VHFT74M","json":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M.json","graph_json":"https://pith.science/api/pith-number/AKM6LFRFKGMZXJTSO64VHFT74M/graph.json","events_json":"https://pith.science/api/pith-number/AKM6LFRFKGMZXJTSO64VHFT74M/events.json","paper":"https://pith.science/paper/AKM6LFRF"},"agent_actions":{"view_html":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M","download_json":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M.json","view_paper":"https://pith.science/paper/AKM6LFRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12894&json=true","fetch_graph":"https://pith.science/api/pith-number/AKM6LFRFKGMZXJTSO64VHFT74M/graph.json","fetch_events":"https://pith.science/api/pith-number/AKM6LFRFKGMZXJTSO64VHFT74M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M/action/storage_attestation","attest_author":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M/action/author_attestation","sign_citation":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M/action/citation_signature","submit_replication":"https://pith.science/pith/AKM6LFRFKGMZXJTSO64VHFT74M/action/replication_record"}},"created_at":"2026-07-05T03:46:01.156508+00:00","updated_at":"2026-07-05T03:46:01.156508+00:00"}