{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q4U65UBJESKVG3PKG2ANUHCJGD","short_pith_number":"pith:Q4U65UBJ","schema_version":"1.0","canonical_sha256":"8729eed0292495536dea3680da1c4930f9663969b35c23cffb5f8a25399d9326","source":{"kind":"arxiv","id":"2212.04183","version":2},"attestation_state":"computed","paper":{"title":"Mind the Gap: Measuring Generalization Performance Across Multiple Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, Edward Bergman, Florian Pfisterer, Frank Hutter, Katharina Eggensperger, Matthias Feurer","submitted_at":"2022-12-08T10:53:56Z","abstract_excerpt":"Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To"},"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":"2212.04183","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-08T10:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"105e9631c3a7bd7d878b79bc313fd7a5fe99cb04aae4801685d8021ff5e3196b","abstract_canon_sha256":"2af9804495d3fb3338a0f18484871e01c7a6a28cc58f2b4ab8e6e38c873974ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:59.529452Z","signature_b64":"FBN+Nol7FbfBymnMzeL/cE49cS/Jmo8LTE6DhhtMS0zHgt3jLKun8YfEEmXjIAvTA0okzBKhGVfKds6ogWLfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8729eed0292495536dea3680da1c4930f9663969b35c23cffb5f8a25399d9326","last_reissued_at":"2026-07-05T07:49:59.529005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:59.529005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Gap: Measuring Generalization Performance Across Multiple Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, Edward Bergman, Florian Pfisterer, Frank Hutter, Katharina Eggensperger, Matthias Feurer","submitted_at":"2022-12-08T10:53:56Z","abstract_excerpt":"Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04183","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.04183/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":"2212.04183","created_at":"2026-07-05T07:49:59.529061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04183v2","created_at":"2026-07-05T07:49:59.529061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04183","created_at":"2026-07-05T07:49:59.529061+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4U65UBJESKV","created_at":"2026-07-05T07:49:59.529061+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4U65UBJESKVG3PK","created_at":"2026-07-05T07:49:59.529061+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4U65UBJ","created_at":"2026-07-05T07:49:59.529061+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/Q4U65UBJESKVG3PKG2ANUHCJGD","json":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD.json","graph_json":"https://pith.science/api/pith-number/Q4U65UBJESKVG3PKG2ANUHCJGD/graph.json","events_json":"https://pith.science/api/pith-number/Q4U65UBJESKVG3PKG2ANUHCJGD/events.json","paper":"https://pith.science/paper/Q4U65UBJ"},"agent_actions":{"view_html":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD","download_json":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD.json","view_paper":"https://pith.science/paper/Q4U65UBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04183&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4U65UBJESKVG3PKG2ANUHCJGD/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4U65UBJESKVG3PKG2ANUHCJGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD/action/storage_attestation","attest_author":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD/action/author_attestation","sign_citation":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD/action/citation_signature","submit_replication":"https://pith.science/pith/Q4U65UBJESKVG3PKG2ANUHCJGD/action/replication_record"}},"created_at":"2026-07-05T07:49:59.529061+00:00","updated_at":"2026-07-05T07:49:59.529061+00:00"}