{"paper":{"title":"A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"QSurv approximates cumulative hazards via Gauss-Legendre quadrature to enable scalable nonparametric continuous-time survival modeling in deep networks.","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chaeyeon Lee, Hyungrok Do, Sehwan Kim","submitted_at":"2026-05-15T17:25:17Z","abstract_excerpt":"Flexible continuous-time survival modeling is critical for capturing complex time-varying hazard dynamics in high-dimensional data; however, training such models remains challenging due to the intractable integral required for likelihood estimation. We introduce QSurv, a scalable deep learning framework that enables nonparametric continuous-time modeling without relying on time discretization or restrictive distributional assumptions. We propose a training objective based on Gauss-Legendre numerical quadrature, which approximates the cumulative hazard with high-order accuracy while facilitatin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce QSurv, a scalable deep learning framework that enables nonparametric continuous-time modeling without relying on time discretization or restrictive distributional assumptions. We propose a training objective based on Gauss-Legendre numerical quadrature, which approximates the cumulative hazard with high-order accuracy while facilitating efficient end-to-end training via standard backpropagation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Gauss-Legendre numerical quadrature approximates the cumulative hazard with high-order accuracy while facilitating efficient end-to-end training via standard backpropagation, without introducing bias that would affect model learning or predictions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"QSurv uses Gauss-Legendre numerical quadrature and time-conditioned low-rank adaptation to enable scalable nonparametric continuous-time survival modeling with theoretical error bounds.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"QSurv approximates cumulative hazards via Gauss-Legendre quadrature to enable scalable nonparametric continuous-time survival modeling in deep networks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1f0052f30f7a6b9aec6bf93378d38956ea8560fc6257aa38a9a789ed23f299c"},"source":{"id":"2605.16208","kind":"arxiv","version":1},"verdict":{"id":"0c287a98-1272-481a-9082-20a90cf895c5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:32:24.818777Z","strongest_claim":"We introduce QSurv, a scalable deep learning framework that enables nonparametric continuous-time modeling without relying on time discretization or restrictive distributional assumptions. We propose a training objective based on Gauss-Legendre numerical quadrature, which approximates the cumulative hazard with high-order accuracy while facilitating efficient end-to-end training via standard backpropagation.","one_line_summary":"QSurv uses Gauss-Legendre numerical quadrature and time-conditioned low-rank adaptation to enable scalable nonparametric continuous-time survival modeling with theoretical error bounds.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Gauss-Legendre numerical quadrature approximates the cumulative hazard with high-order accuracy while facilitating efficient end-to-end training via standard backpropagation, without introducing bias that would affect model learning or predictions.","pith_extraction_headline":"QSurv approximates cumulative hazards via Gauss-Legendre quadrature to enable scalable nonparametric continuous-time survival modeling in deep networks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16208/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:18.882842Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:40:54.186056Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T17:49:44.677479Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T17:49:44.167410Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:24.836290Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:34.822203Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T17:22:07.046037Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.396728Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1de87a0724f6311998c1aa539e7c6fad34c5a949f7ae60d77fd4012c60bfe049"},"references":{"count":48,"sample":[{"doi":"","year":2020,"title":"A. Avati, T. Duan, S. Zhou, K. Jung, N. H. Shah, and A. Y . Ng. Countdown regression: Sharp and calibrated survival predictions. In R. P. Adams and V . Gogate, editors,Proceedings of The 35th Uncertai","work_id":"e12a8b64-849b-4f9e-9b08-fcb5115939b7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. Farahani, and C. Davatzikos. Advancing the cancer genome atlas glioma mri collections with expert segmentation ","work_id":"9b77188c-7557-41ec-ab9a-37488abeb662","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"arXiv preprint arXiv:1811.02629 (2018)","work_id":"1605e84f-e9eb-47fa-8083-67dd5daedf5c","ref_index":3,"cited_arxiv_id":"1811.02629","is_internal_anchor":true},{"doi":"10.1007/978-3-030-47426-3_53","year":2020,"title":"A. Bennis, S. Mouysset, and M. Serrurier. Estimation of conditional mixture weibull distribution with right censored data using neural network for time-to-event analysis. InAdvances in Knowledge Disco","work_id":"c917e70e-871a-4e83-9c08-6ec2300250ab","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"N. E. Breslow and N. Chatterjee. Design and analysis of two-phase studies with binary outcome applied to wilms tumour prognosis.Journal of the Royal Statistical Society: Series C (Applied Statistics),","work_id":"ca9eb33f-a2a0-49f5-83f7-d7bcbaa79737","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"c1b74b07cb59aeb30d675348c6e1f5b328ad7691e4b7c05fa8f10d35f07527d2","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2b735800ac29e2d1e8ad082daa29e64665a4d874c9c25f76c6ad53627cd99c6d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}