{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VQRRIDUCWNGVKWHS5YXEX6HGB7","short_pith_number":"pith:VQRRIDUC","schema_version":"1.0","canonical_sha256":"ac23140e82b34d5558f2ee2e4bf8e60fe660c4e1587af8d7aa61f1e93d7074a5","source":{"kind":"arxiv","id":"1902.04639","version":2},"attestation_state":"computed","paper":{"title":"A Tunable Loss Function for Binary Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lalitha Sankar, Mario Diaz, Peter Kairouz, Tyler Sypherd","submitted_at":"2019-02-12T21:15:33Z","abstract_excerpt":"We present $\\alpha$-loss, $\\alpha \\in [1,\\infty]$, a tunable loss function for binary classification that bridges log-loss ($\\alpha=1$) and $0$-$1$ loss ($\\alpha = \\infty$). We prove that $\\alpha$-loss has an equivalent margin-based form and is classification-calibrated, two desirable properties for a good surrogate loss function for the ideal yet intractable $0$-$1$ loss. For logistic regression-based classification, we provide an upper bound on the difference between the empirical and expected risk at the empirical risk minimizers for $\\alpha$-loss by exploiting its Lipschitzianity along wit"},"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":"1902.04639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T21:15:33Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"a2492fd29565a6f4e82e4a4e3d17f224b083dd949d0707a945ad56cc198e9374","abstract_canon_sha256":"9d6f1c9e7d7e1e59bc4d0fde065a7167a46fb60fd751164799462ddd09cc976d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:50.325254Z","signature_b64":"Io/DNE1yhvrV0b/m5QVCKJWyqB9RWkP68cBOD0q00mqKy3yV9/t1mz39rX5xaCKqtIsh8Y4IIqfl9Nzfy5NuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac23140e82b34d5558f2ee2e4bf8e60fe660c4e1587af8d7aa61f1e93d7074a5","last_reissued_at":"2026-05-17T23:50:50.324477Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:50.324477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tunable Loss Function for Binary Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lalitha Sankar, Mario Diaz, Peter Kairouz, Tyler Sypherd","submitted_at":"2019-02-12T21:15:33Z","abstract_excerpt":"We present $\\alpha$-loss, $\\alpha \\in [1,\\infty]$, a tunable loss function for binary classification that bridges log-loss ($\\alpha=1$) and $0$-$1$ loss ($\\alpha = \\infty$). We prove that $\\alpha$-loss has an equivalent margin-based form and is classification-calibrated, two desirable properties for a good surrogate loss function for the ideal yet intractable $0$-$1$ loss. For logistic regression-based classification, we provide an upper bound on the difference between the empirical and expected risk at the empirical risk minimizers for $\\alpha$-loss by exploiting its Lipschitzianity along wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04639","kind":"arxiv","version":2},"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":"1902.04639","created_at":"2026-05-17T23:50:50.324617+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04639v2","created_at":"2026-05-17T23:50:50.324617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04639","created_at":"2026-05-17T23:50:50.324617+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQRRIDUCWNGV","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQRRIDUCWNGVKWHS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQRRIDUC","created_at":"2026-05-18T12:33:30.264802+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/VQRRIDUCWNGVKWHS5YXEX6HGB7","json":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7.json","graph_json":"https://pith.science/api/pith-number/VQRRIDUCWNGVKWHS5YXEX6HGB7/graph.json","events_json":"https://pith.science/api/pith-number/VQRRIDUCWNGVKWHS5YXEX6HGB7/events.json","paper":"https://pith.science/paper/VQRRIDUC"},"agent_actions":{"view_html":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7","download_json":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7.json","view_paper":"https://pith.science/paper/VQRRIDUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04639&json=true","fetch_graph":"https://pith.science/api/pith-number/VQRRIDUCWNGVKWHS5YXEX6HGB7/graph.json","fetch_events":"https://pith.science/api/pith-number/VQRRIDUCWNGVKWHS5YXEX6HGB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7/action/storage_attestation","attest_author":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7/action/author_attestation","sign_citation":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7/action/citation_signature","submit_replication":"https://pith.science/pith/VQRRIDUCWNGVKWHS5YXEX6HGB7/action/replication_record"}},"created_at":"2026-05-17T23:50:50.324617+00:00","updated_at":"2026-05-17T23:50:50.324617+00:00"}