{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZVLCF6HQBQ2TLZORPQDWXGFTIT","short_pith_number":"pith:ZVLCF6HQ","schema_version":"1.0","canonical_sha256":"cd5622f8f00c3535e5d17c076b98b344e8b944f219013ee36c04b5da2b11dfae","source":{"kind":"arxiv","id":"2606.08945","version":1},"attestation_state":"computed","paper":{"title":"From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Blanca Gallego, Louisa Jorm, Nicholas I-Hsien Kuo","submitted_at":"2026-06-08T02:47:05Z","abstract_excerpt":"We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large language model. We propose a text-based survival modelling pipeline in which structured clinical covariates are converted into text prompts and a Qwen-based large language model is fine-tuned to generate patient-specific survival risk using Cox model predictions as a training target. Across GBSG2, ACTG320, and WHAS500, the model achieves competitive held-out discrimination and calibration despite being trained as a text-generation task rather than"},"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":"2606.08945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T02:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"fe1de4db7e6cb4ea0d394d9dfe6917770e20fc3d69cbd8e39015a5aae8f2c4d4","abstract_canon_sha256":"60118ae93c9da6b732ee7fcd452eb4407e756f93ec08e10cc8c85af041880cfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:49.261220Z","signature_b64":"A+ThwSLQsUhcq/V3ITXDJdKtRE7wfkc6+RDevEBLaMk4kUjQoQKoK01KrpDL+14k8ywARf4P5Yo8WSwP+5EJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd5622f8f00c3535e5d17c076b98b344e8b944f219013ee36c04b5da2b11dfae","last_reissued_at":"2026-06-09T02:07:49.260387Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:49.260387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Blanca Gallego, Louisa Jorm, Nicholas I-Hsien Kuo","submitted_at":"2026-06-08T02:47:05Z","abstract_excerpt":"We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large language model. We propose a text-based survival modelling pipeline in which structured clinical covariates are converted into text prompts and a Qwen-based large language model is fine-tuned to generate patient-specific survival risk using Cox model predictions as a training target. Across GBSG2, ACTG320, and WHAS500, the model achieves competitive held-out discrimination and calibration despite being trained as a text-generation task rather than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08945","kind":"arxiv","version":1},"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/2606.08945/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":"2606.08945","created_at":"2026-06-09T02:07:49.260529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08945v1","created_at":"2026-06-09T02:07:49.260529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08945","created_at":"2026-06-09T02:07:49.260529+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVLCF6HQBQ2T","created_at":"2026-06-09T02:07:49.260529+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVLCF6HQBQ2TLZOR","created_at":"2026-06-09T02:07:49.260529+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVLCF6HQ","created_at":"2026-06-09T02:07:49.260529+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/ZVLCF6HQBQ2TLZORPQDWXGFTIT","json":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT.json","graph_json":"https://pith.science/api/pith-number/ZVLCF6HQBQ2TLZORPQDWXGFTIT/graph.json","events_json":"https://pith.science/api/pith-number/ZVLCF6HQBQ2TLZORPQDWXGFTIT/events.json","paper":"https://pith.science/paper/ZVLCF6HQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT","download_json":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT.json","view_paper":"https://pith.science/paper/ZVLCF6HQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08945&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVLCF6HQBQ2TLZORPQDWXGFTIT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVLCF6HQBQ2TLZORPQDWXGFTIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT/action/storage_attestation","attest_author":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT/action/author_attestation","sign_citation":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT/action/citation_signature","submit_replication":"https://pith.science/pith/ZVLCF6HQBQ2TLZORPQDWXGFTIT/action/replication_record"}},"created_at":"2026-06-09T02:07:49.260529+00:00","updated_at":"2026-06-09T02:07:49.260529+00:00"}