{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z7SANF66S4LHOZH6JIPYJ5YGLY","short_pith_number":"pith:Z7SANF66","schema_version":"1.0","canonical_sha256":"cfe40697de97167764fe4a1f84f7065e2d71d21f3b7d687957c497f7027109eb","source":{"kind":"arxiv","id":"2212.05260","version":3},"attestation_state":"computed","paper":{"title":"Examining marginal properness in the external validation of survival models with squared and logarithmic losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.TH"],"primary_cat":"math.ST","authors_text":"Andreas Bender, John Zobolas, Lukas Burk, Philipp Kopper, Raphael Sonabend, Riccardo Be Bin","submitted_at":"2022-12-10T10:34:35Z","abstract_excerpt":"Scoring rules promote rational and honest decision-making, which is important for model evaluation and becoming increasingly important for automated procedures such as `AutoML'. In this paper we survey common squared and logarithmic scoring rules for survival analysis, with a focus on their theoretical and empirical properness. We introduce a marginal definition of properness and show that both the Integrated Survival Brier Score (ISBS) and the Right-Censored Log-Likelihood (RCLL) are theoretically improper under this definition. We also investigate a new class of losses that may inform future"},"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":"2212.05260","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2022-12-10T10:34:35Z","cross_cats_sorted":["cs.LG","stat.AP","stat.TH"],"title_canon_sha256":"1c1f316f4a40f589c2ca7f42ee1bd10a35164fab8ff027e44fd68d083617f601","abstract_canon_sha256":"46e16e15b5878e88b0580b17158e4b366b319480bcb8999ed29a504484fc8d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:04.802047Z","signature_b64":"NZHnvxqfHN4fYYK2+cxMADJ4N/Ml6Rayq0BuCxiwF/BvZjXBMDyCDy3LR6bGKn+BZV6Kbfp64f7u74JQ/5CBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfe40697de97167764fe4a1f84f7065e2d71d21f3b7d687957c497f7027109eb","last_reissued_at":"2026-07-05T11:13:04.801486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:04.801486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Examining marginal properness in the external validation of survival models with squared and logarithmic losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.TH"],"primary_cat":"math.ST","authors_text":"Andreas Bender, John Zobolas, Lukas Burk, Philipp Kopper, Raphael Sonabend, Riccardo Be Bin","submitted_at":"2022-12-10T10:34:35Z","abstract_excerpt":"Scoring rules promote rational and honest decision-making, which is important for model evaluation and becoming increasingly important for automated procedures such as `AutoML'. In this paper we survey common squared and logarithmic scoring rules for survival analysis, with a focus on their theoretical and empirical properness. We introduce a marginal definition of properness and show that both the Integrated Survival Brier Score (ISBS) and the Right-Censored Log-Likelihood (RCLL) are theoretically improper under this definition. We also investigate a new class of losses that may inform future"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05260","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/2212.05260/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":"2212.05260","created_at":"2026-07-05T11:13:04.801550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05260v3","created_at":"2026-07-05T11:13:04.801550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05260","created_at":"2026-07-05T11:13:04.801550+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7SANF66S4LH","created_at":"2026-07-05T11:13:04.801550+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7SANF66S4LHOZH6","created_at":"2026-07-05T11:13:04.801550+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7SANF66","created_at":"2026-07-05T11:13:04.801550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2406.04098","citing_title":"A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data","ref_index":95,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY","json":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY.json","graph_json":"https://pith.science/api/pith-number/Z7SANF66S4LHOZH6JIPYJ5YGLY/graph.json","events_json":"https://pith.science/api/pith-number/Z7SANF66S4LHOZH6JIPYJ5YGLY/events.json","paper":"https://pith.science/paper/Z7SANF66"},"agent_actions":{"view_html":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY","download_json":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY.json","view_paper":"https://pith.science/paper/Z7SANF66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05260&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7SANF66S4LHOZH6JIPYJ5YGLY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7SANF66S4LHOZH6JIPYJ5YGLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY/action/storage_attestation","attest_author":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY/action/author_attestation","sign_citation":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY/action/citation_signature","submit_replication":"https://pith.science/pith/Z7SANF66S4LHOZH6JIPYJ5YGLY/action/replication_record"}},"created_at":"2026-07-05T11:13:04.801550+00:00","updated_at":"2026-07-05T11:13:04.801550+00:00"}