{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IKSRN7BE4X2HHMFPQRXNZBHMVY","short_pith_number":"pith:IKSRN7BE","canonical_record":{"source":{"id":"2605.15488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T00:13:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"067881e92825bf93033dab7bc218f90e79b326bd86f4a131acd8c4ec129fbef1","abstract_canon_sha256":"7e69ed9d05660aa7b979dbe5e0a43094fc4f58e98ebe069cfc14e96288438093"},"schema_version":"1.0"},"canonical_sha256":"42a516fc24e5f473b0af846edc84ecae1051daabbef56e04f52c06444b2ceece","source":{"kind":"arxiv","id":"2605.15488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15488","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15488v1","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15488","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"IKSRN7BE4X2H","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"IKSRN7BE4X2HHMFP","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"IKSRN7BE","created_at":"2026-05-20T00:01:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IKSRN7BE4X2HHMFPQRXNZBHMVY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T00:13:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"067881e92825bf93033dab7bc218f90e79b326bd86f4a131acd8c4ec129fbef1","abstract_canon_sha256":"7e69ed9d05660aa7b979dbe5e0a43094fc4f58e98ebe069cfc14e96288438093"},"schema_version":"1.0"},"canonical_sha256":"42a516fc24e5f473b0af846edc84ecae1051daabbef56e04f52c06444b2ceece","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:01.241738Z","signature_b64":"X+lWTfFqeC1WmMKqfhfNQtBPy1doCkWuSaXPYz6jZcbrPJrxJoudNZiDj7h0oYrkqG9v+fr51J7og6YR4iYEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a516fc24e5f473b0af846edc84ecae1051daabbef56e04f52c06444b2ceece","last_reissued_at":"2026-05-20T00:01:01.240961Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:01.240961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15488","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nd6XlUuOAEh2xuzXPNZtfAlXMa+lSnBPPO4r5su7ccZZkfjqyGhGlPzqj0yJ/yihAzKUv4XX1Un20KFkiRehBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:32:13.316495Z"},"content_sha256":"5dae9ccfc7932a7c3fe490cacb76b644469f94d4e04a342c7a6e1553aca17c49","schema_version":"1.0","event_id":"sha256:5dae9ccfc7932a7c3fe490cacb76b644469f94d4e04a342c7a6e1553aca17c49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IKSRN7BE4X2HHMFPQRXNZBHMVY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Cooper, Rahul G. Krishnan, Russell Greiner, Shi-ang Qi, Vahid Balazadeh","submitted_at":"2026-05-15T00:13:04Z","abstract_excerpt":"Survival analysis provides a powerful statistical framework for modeling time-to-event outcomes in the presence of censoring. However, selecting an appropriate estimator from the many specialized survival approaches often requires substantial methodological and domain expertise. We introduce SurvivalPFN, a prior-data fitted network that amortizes Bayesian inference for censored observations through in-context learning. SurvivalPFN is pretrained on a diverse family of synthetic, identifiable, and right-censored data-generating processes, enabling it to amortize survival analysis in a single for"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In a large-scale benchmark spanning 61 datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That pretraining exclusively on a diverse family of synthetic, identifiable, and right-censored data-generating processes will produce a model whose in-context predictions generalize to the distribution of real-world censored datasets without task-specific retraining or hyperparameter tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SurvivalPFN amortizes Bayesian survival analysis for right-censored data by pretraining a prior-data fitted network on synthetic identifiable DGPs and then performing in-context inference, achieving competitive results on 61 real datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"40fffbc743ffdaea3a731a96507b3e1c90c9c58bd0d1e1287958e35e0da3af65"},"source":{"id":"2605.15488","kind":"arxiv","version":1},"verdict":{"id":"86e623c2-3468-4b44-b6b4-0403e7b98f69","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T14:15:41.115890Z","strongest_claim":"In a large-scale benchmark spanning 61 datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models.","one_line_summary":"SurvivalPFN amortizes Bayesian survival analysis for right-censored data by pretraining a prior-data fitted network on synthetic identifiable DGPs and then performing in-context inference, achieving competitive results on 61 real datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That pretraining exclusively on a diverse family of synthetic, identifiable, and right-censored data-generating processes will produce a model whose in-context predictions generalize to the distribution of real-world censored datasets without task-specific retraining or hyperparameter tuning.","pith_extraction_headline":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15488/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:57.320618Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.474458Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:27:26.946456Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.074211Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.401821Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.650697Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c20f5e8a0b1e2a79c70a29a236be0f030ed47b82962cfbe49a4a968f59df0786"},"references":{"count":130,"sample":[{"doi":"","year":2003,"title":"An introduction to mcmc for machine learning.Machine learning, 50(1):5–43, 2003","work_id":"8c380e1d-db26-4e03-a186-870fb8aadb0d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Causalpfn: Amortized causal effect estimation via in-context learning.arXiv preprint arXiv:2506.07918, 2025","work_id":"829f6a90-6097-4b5c-8cec-8025b6a9c21c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"In-context learning of temporal point processes with foundation inference models.arXiv preprint arXiv:2509.24762, 2025","work_id":"fe883dea-b8f9-4f1b-a8ae-3f30db1558a7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1998,"title":"Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach","work_id":"5f2e86dd-6d84-4646-aed4-b358693fab19","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1975,"title":"Analysis of survival data under the proportional hazards model.Interna- tional Statistical Review/Revue Internationale de Statistique, pages 45–57, 1975","work_id":"4a10fe55-d721-4f74-9b19-a0b325a9508a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":130,"snapshot_sha256":"e657b3d11565c6c844c51a999b5f66b9311424ff83dcc1d3266c7ba2b32dddfb","internal_anchors":5},"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"},"verdict_id":"86e623c2-3468-4b44-b6b4-0403e7b98f69"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0Xbtb97/4c+WyQ4rWr+jdDZXeGuzwyi12j4219d8tSR4ontClvBWDqDj/fF3xIupKnvTwWmnoKpU4YmaY3oCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:32:13.317838Z"},"content_sha256":"5575f66f13fbc04399f617bb9518ec9b342be5b4cd3917044472524d374dc034","schema_version":"1.0","event_id":"sha256:5575f66f13fbc04399f617bb9518ec9b342be5b4cd3917044472524d374dc034"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/bundle.json","state_url":"https://pith.science/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T23:32:13Z","links":{"resolver":"https://pith.science/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY","bundle":"https://pith.science/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/bundle.json","state":"https://pith.science/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKSRN7BE4X2HHMFPQRXNZBHMVY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IKSRN7BE4X2HHMFPQRXNZBHMVY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7e69ed9d05660aa7b979dbe5e0a43094fc4f58e98ebe069cfc14e96288438093","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T00:13:04Z","title_canon_sha256":"067881e92825bf93033dab7bc218f90e79b326bd86f4a131acd8c4ec129fbef1"},"schema_version":"1.0","source":{"id":"2605.15488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15488","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15488v1","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15488","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"IKSRN7BE4X2H","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"IKSRN7BE4X2HHMFP","created_at":"2026-05-20T00:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"IKSRN7BE","created_at":"2026-05-20T00:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:5575f66f13fbc04399f617bb9518ec9b342be5b4cd3917044472524d374dc034","target":"graph","created_at":"2026-05-20T00:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"In a large-scale benchmark spanning 61 datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That pretraining exclusively on a diverse family of synthetic, identifiable, and right-censored data-generating processes will produce a model whose in-context predictions generalize to the distribution of real-world censored datasets without task-specific retraining or hyperparameter tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SurvivalPFN amortizes Bayesian survival analysis for right-censored data by pretraining a prior-data fitted network on synthetic identifiable DGPs and then performing in-context inference, achieving competitive results on 61 real datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass."}],"snapshot_sha256":"40fffbc743ffdaea3a731a96507b3e1c90c9c58bd0d1e1287958e35e0da3af65"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:57.320618Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.474458Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:27:26.946456Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.074211Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.401821Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.650697Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15488/integrity.json","findings":[],"snapshot_sha256":"c20f5e8a0b1e2a79c70a29a236be0f030ed47b82962cfbe49a4a968f59df0786","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Survival analysis provides a powerful statistical framework for modeling time-to-event outcomes in the presence of censoring. However, selecting an appropriate estimator from the many specialized survival approaches often requires substantial methodological and domain expertise. We introduce SurvivalPFN, a prior-data fitted network that amortizes Bayesian inference for censored observations through in-context learning. SurvivalPFN is pretrained on a diverse family of synthetic, identifiable, and right-censored data-generating processes, enabling it to amortize survival analysis in a single for","authors_text":"Michael Cooper, Rahul G. Krishnan, Russell Greiner, Shi-ang Qi, Vahid Balazadeh","cross_cats":["stat.ML"],"headline":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T00:13:04Z","title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference"},"references":{"count":130,"internal_anchors":5,"resolved_work":130,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"An introduction to mcmc for machine learning.Machine learning, 50(1):5–43, 2003","work_id":"8c380e1d-db26-4e03-a186-870fb8aadb0d","year":2003},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Causalpfn: Amortized causal effect estimation via in-context learning.arXiv preprint arXiv:2506.07918, 2025","work_id":"829f6a90-6097-4b5c-8cec-8025b6a9c21c","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In-context learning of temporal point processes with foundation inference models.arXiv preprint arXiv:2509.24762, 2025","work_id":"fe883dea-b8f9-4f1b-a8ae-3f30db1558a7","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach","work_id":"5f2e86dd-6d84-4646-aed4-b358693fab19","year":1998},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Analysis of survival data under the proportional hazards model.Interna- tional Statistical Review/Revue Internationale de Statistique, pages 45–57, 1975","work_id":"4a10fe55-d721-4f74-9b19-a0b325a9508a","year":1975}],"snapshot_sha256":"e657b3d11565c6c844c51a999b5f66b9311424ff83dcc1d3266c7ba2b32dddfb"},"source":{"id":"2605.15488","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T14:15:41.115890Z","id":"86e623c2-3468-4b44-b6b4-0403e7b98f69","model_set":{"reader":"grok-4.3"},"one_line_summary":"SurvivalPFN amortizes Bayesian survival analysis for right-censored data by pretraining a prior-data fitted network on synthetic identifiable DGPs and then performing in-context inference, achieving competitive results on 61 real datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SurvivalPFN amortizes Bayesian survival inference so a single pretrained network produces calibrated time-to-event predictions for new datasets in one forward pass.","strongest_claim":"In a large-scale benchmark spanning 61 datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models.","weakest_assumption":"That pretraining exclusively on a diverse family of synthetic, identifiable, and right-censored data-generating processes will produce a model whose in-context predictions generalize to the distribution of real-world censored datasets without task-specific retraining or hyperparameter tuning."}},"verdict_id":"86e623c2-3468-4b44-b6b4-0403e7b98f69"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5dae9ccfc7932a7c3fe490cacb76b644469f94d4e04a342c7a6e1553aca17c49","target":"record","created_at":"2026-05-20T00:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7e69ed9d05660aa7b979dbe5e0a43094fc4f58e98ebe069cfc14e96288438093","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T00:13:04Z","title_canon_sha256":"067881e92825bf93033dab7bc218f90e79b326bd86f4a131acd8c4ec129fbef1"},"schema_version":"1.0","source":{"id":"2605.15488","kind":"arxiv","version":1}},"canonical_sha256":"42a516fc24e5f473b0af846edc84ecae1051daabbef56e04f52c06444b2ceece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42a516fc24e5f473b0af846edc84ecae1051daabbef56e04f52c06444b2ceece","first_computed_at":"2026-05-20T00:01:01.240961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:01.240961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X+lWTfFqeC1WmMKqfhfNQtBPy1doCkWuSaXPYz6jZcbrPJrxJoudNZiDj7h0oYrkqG9v+fr51J7og6YR4iYEDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:01.241738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dae9ccfc7932a7c3fe490cacb76b644469f94d4e04a342c7a6e1553aca17c49","sha256:5575f66f13fbc04399f617bb9518ec9b342be5b4cd3917044472524d374dc034"],"state_sha256":"b3f63e3023c73ffc6355633f528a2476dc1ba5fb9388a8cd82c31319435cba9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Jm1HQ8m5C2TgCBiooX7R/pdj3K4UelRrYWWtUAulv6hHWuAbLvFGawKEp+f5ZEEyvL2VhlvepqLEUCdJ3NMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:32:13.322922Z","bundle_sha256":"d6f7cd6f2f1068699905e5314043b88ee8d74df5fb0a5ad2b39f9017e82c6a5d"}}