{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CG2JXTWANWBZAT24QZ6HCSUAWM","short_pith_number":"pith:CG2JXTWA","canonical_record":{"source":{"id":"2605.16571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-15T19:20:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"638ed385c6f94a2c0ba2e35319b9de78bc5b6af13b4f64758313aa96e7a07bef","abstract_canon_sha256":"081712ced6c9c77ce9b91731013d2ffe1bf5e6631443c9081b44507b1777f59a"},"schema_version":"1.0"},"canonical_sha256":"11b49bcec06d83904f5c867c714a80b3351f33f34e496061bba71ad72dc82f8f","source":{"kind":"arxiv","id":"2605.16571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16571","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16571v1","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16571","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"CG2JXTWANWBZ","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"CG2JXTWANWBZAT24","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"CG2JXTWA","created_at":"2026-05-20T00:02:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CG2JXTWANWBZAT24QZ6HCSUAWM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-15T19:20:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"638ed385c6f94a2c0ba2e35319b9de78bc5b6af13b4f64758313aa96e7a07bef","abstract_canon_sha256":"081712ced6c9c77ce9b91731013d2ffe1bf5e6631443c9081b44507b1777f59a"},"schema_version":"1.0"},"canonical_sha256":"11b49bcec06d83904f5c867c714a80b3351f33f34e496061bba71ad72dc82f8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:29.780336Z","signature_b64":"S/tNSK/druIwKldoOv4uNowe/2W+2sFNzOlD29f/9jW27MyT4GpEDriQbnYOyo0zh9nWH3YOMJS74hBz7f4CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11b49bcec06d83904f5c867c714a80b3351f33f34e496061bba71ad72dc82f8f","last_reissued_at":"2026-05-20T00:02:29.779411Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:29.779411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16571","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":"2026-05-20T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LrwSeAX3FEHPbqkpPRlr0COLoaPmXFL/BK8nyUTv4i3uKCrrT6Oc7xfQPG765Be4a4NTvbwgnk1RMLHPcFxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:21:16.846220Z"},"content_sha256":"745237cd3b08a22eabc89c18b0745d81318c527a1fa18a66205eea33f705ce57","schema_version":"1.0","event_id":"sha256:745237cd3b08a22eabc89c18b0745d81318c527a1fa18a66205eea33f705ce57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CG2JXTWANWBZAT24QZ6HCSUAWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Anchit Jain, Kevin Zhang, Stephen Bates","submitted_at":"2026-05-15T19:20:23Z","abstract_excerpt":"Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates the application of standard machine learning methods. Deep Cox models have emerged as a popular method for analyzing time-to-event data because they gracefully handle censoring and can be used with unstructured data such as clinical text reports, genomic sequences, and pathology images. However, their predicted survival probabilities are often poorly calibrated, thus limiting their practical utility. In this paper, we propose a novel post hoc cal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The isotonic calibration method for Deep Cox models achieves asymptotic calibration, possesses a double-robustness property, and preserves discriminative power on synthetic and real-world clinical data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That applying isotonic regression post-hoc to the model's predicted survival curves will not distort the underlying risk ordering or introduce new calibration issues under the specific censoring patterns present in the target datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Post-hoc isotonic regression calibration for deep Cox survival models that improves calibration with theoretical guarantees including double-robustness and asymptotic calibration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"65620a8f98319e4f7a4949862d2200dbbb3036e4fb86c1f607f5b92799511f10"},"source":{"id":"2605.16571","kind":"arxiv","version":1},"verdict":{"id":"1bafe29c-d8a6-4b2e-bed2-4b26b04297dc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:55:27.994381Z","strongest_claim":"The isotonic calibration method for Deep Cox models achieves asymptotic calibration, possesses a double-robustness property, and preserves discriminative power on synthetic and real-world clinical data.","one_line_summary":"Post-hoc isotonic regression calibration for deep Cox survival models that improves calibration with theoretical guarantees including double-robustness and asymptotic calibration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That applying isotonic regression post-hoc to the model's predicted survival curves will not distort the underlying risk ordering or introduce new calibration issues under the specific censoring patterns present in the target datasets.","pith_extraction_headline":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16571/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T21:02:55.954640Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.344828Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.867057Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.619847Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"93156de18571dc3b2296a98f712db8b83eafd4335d3e2a47fb101a1a7f764f86"},"references":{"count":93,"sample":[{"doi":"","year":2007,"title":"Farid E. Ahmed, Paul W. V os, and Don Holbert. Modeling survival in colon cancer: a method- ological review.Molecular Cancer, 6, 2007","work_id":"10df94de-0012-4e0c-bbd5-a8c2545cff8a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Jishan Ahmed and Robert C. Green II. Leveraging survival analysis in cost-aware deepnet for efficient hard drive failure prediction.Neural Computing and Applications, 37, 2025","work_id":"0637ca8f-8334-42d1-863c-c405f715c6d1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Publicly available clinical BERT embeddings","work_id":"2fa87aba-be62-4434-a9e0-680484bf3ab3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"Assael, Carlo Castellani, Marisol Barao Ocampo, Patrizia Iansa, Andrea Callegaro, and Maria Grazia Valsecchi","work_id":"71f64c0d-f4e4-4be8-bf96-b6de757283a9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Shah, and Andrew Y","work_id":"2b00a53c-f6d8-40b7-b6d2-9239e8fc6665","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":93,"snapshot_sha256":"08dfcaab24bc131f281195bda425b8a9b54028ab82b34fabee53beff6c208fa2","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8bf5e232c46ad1a8c5305fcf390f77ae5ca3de43685c16a9c490718d11c56bce"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1bafe29c-d8a6-4b2e-bed2-4b26b04297dc"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3Z2KPwJ4HxI9+hu2JcjYMO1QqO3+qVYGGJAQ8D60B3rd0xGbdi8Tv2D/psaZ45vcvqNEcA5NRtzgrSaDzqBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:21:16.846903Z"},"content_sha256":"3b45949cb54718e9cdfef3078543656c7e7ea45b771cc54978a7563a723c0059","schema_version":"1.0","event_id":"sha256:3b45949cb54718e9cdfef3078543656c7e7ea45b771cc54978a7563a723c0059"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/bundle.json","state_url":"https://pith.science/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/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":"2026-06-03T14:21:16Z","links":{"resolver":"https://pith.science/pith/CG2JXTWANWBZAT24QZ6HCSUAWM","bundle":"https://pith.science/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/bundle.json","state":"https://pith.science/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CG2JXTWANWBZAT24QZ6HCSUAWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CG2JXTWANWBZAT24QZ6HCSUAWM","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":"081712ced6c9c77ce9b91731013d2ffe1bf5e6631443c9081b44507b1777f59a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-15T19:20:23Z","title_canon_sha256":"638ed385c6f94a2c0ba2e35319b9de78bc5b6af13b4f64758313aa96e7a07bef"},"schema_version":"1.0","source":{"id":"2605.16571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16571","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16571v1","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16571","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"CG2JXTWANWBZ","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"CG2JXTWANWBZAT24","created_at":"2026-05-20T00:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"CG2JXTWA","created_at":"2026-05-20T00:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:3b45949cb54718e9cdfef3078543656c7e7ea45b771cc54978a7563a723c0059","target":"graph","created_at":"2026-05-20T00:02:29Z","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":"The isotonic calibration method for Deep Cox models achieves asymptotic calibration, possesses a double-robustness property, and preserves discriminative power on synthetic and real-world clinical data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That applying isotonic regression post-hoc to the model's predicted survival curves will not distort the underlying risk ordering or introduce new calibration issues under the specific censoring patterns present in the target datasets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Post-hoc isotonic regression calibration for deep Cox survival models that improves calibration with theoretical guarantees including double-robustness and asymptotic calibration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance."}],"snapshot_sha256":"65620a8f98319e4f7a4949862d2200dbbb3036e4fb86c1f607f5b92799511f10"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8bf5e232c46ad1a8c5305fcf390f77ae5ca3de43685c16a9c490718d11c56bce"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:02:55.954640Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.344828Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.867057Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.619847Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16571/integrity.json","findings":[],"snapshot_sha256":"93156de18571dc3b2296a98f712db8b83eafd4335d3e2a47fb101a1a7f764f86","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates the application of standard machine learning methods. Deep Cox models have emerged as a popular method for analyzing time-to-event data because they gracefully handle censoring and can be used with unstructured data such as clinical text reports, genomic sequences, and pathology images. However, their predicted survival probabilities are often poorly calibrated, thus limiting their practical utility. In this paper, we propose a novel post hoc cal","authors_text":"Anchit Jain, Kevin Zhang, Stephen Bates","cross_cats":["cs.AI","cs.LG"],"headline":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-15T19:20:23Z","title":"Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models"},"references":{"count":93,"internal_anchors":0,"resolved_work":93,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Farid E. Ahmed, Paul W. V os, and Don Holbert. Modeling survival in colon cancer: a method- ological review.Molecular Cancer, 6, 2007","work_id":"10df94de-0012-4e0c-bbd5-a8c2545cff8a","year":2007},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Jishan Ahmed and Robert C. Green II. Leveraging survival analysis in cost-aware deepnet for efficient hard drive failure prediction.Neural Computing and Applications, 37, 2025","work_id":"0637ca8f-8334-42d1-863c-c405f715c6d1","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Publicly available clinical BERT embeddings","work_id":"2fa87aba-be62-4434-a9e0-680484bf3ab3","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Assael, Carlo Castellani, Marisol Barao Ocampo, Patrizia Iansa, Andrea Callegaro, and Maria Grazia Valsecchi","work_id":"71f64c0d-f4e4-4be8-bf96-b6de757283a9","year":2002},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Shah, and Andrew Y","work_id":"2b00a53c-f6d8-40b7-b6d2-9239e8fc6665","year":2020}],"snapshot_sha256":"08dfcaab24bc131f281195bda425b8a9b54028ab82b34fabee53beff6c208fa2"},"source":{"id":"2605.16571","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:55:27.994381Z","id":"1bafe29c-d8a6-4b2e-bed2-4b26b04297dc","model_set":{"reader":"grok-4.3"},"one_line_summary":"Post-hoc isotonic regression calibration for deep Cox survival models that improves calibration with theoretical guarantees including double-robustness and asymptotic calibration.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Isotonic regression applied after a Deep Cox model calibrates survival probabilities while preserving ranking performance.","strongest_claim":"The isotonic calibration method for Deep Cox models achieves asymptotic calibration, possesses a double-robustness property, and preserves discriminative power on synthetic and real-world clinical data.","weakest_assumption":"That applying isotonic regression post-hoc to the model's predicted survival curves will not distort the underlying risk ordering or introduce new calibration issues under the specific censoring patterns present in the target datasets."}},"verdict_id":"1bafe29c-d8a6-4b2e-bed2-4b26b04297dc"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:745237cd3b08a22eabc89c18b0745d81318c527a1fa18a66205eea33f705ce57","target":"record","created_at":"2026-05-20T00:02:29Z","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":"081712ced6c9c77ce9b91731013d2ffe1bf5e6631443c9081b44507b1777f59a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-15T19:20:23Z","title_canon_sha256":"638ed385c6f94a2c0ba2e35319b9de78bc5b6af13b4f64758313aa96e7a07bef"},"schema_version":"1.0","source":{"id":"2605.16571","kind":"arxiv","version":1}},"canonical_sha256":"11b49bcec06d83904f5c867c714a80b3351f33f34e496061bba71ad72dc82f8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11b49bcec06d83904f5c867c714a80b3351f33f34e496061bba71ad72dc82f8f","first_computed_at":"2026-05-20T00:02:29.779411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:29.779411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S/tNSK/druIwKldoOv4uNowe/2W+2sFNzOlD29f/9jW27MyT4GpEDriQbnYOyo0zh9nWH3YOMJS74hBz7f4CCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:29.780336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:745237cd3b08a22eabc89c18b0745d81318c527a1fa18a66205eea33f705ce57","sha256:3b45949cb54718e9cdfef3078543656c7e7ea45b771cc54978a7563a723c0059"],"state_sha256":"e22b6828bafb1c35a86bc19fac13b87baa4f26bc0a6f38ac3252d2a945e481d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ay371rKCJgiRDg3vKIjMW0VBKOBEncNr1dk6KxO+e9zr8zLEdPj5MOVbhokJ6M654li125ykF2i+DyFLvzraAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T14:21:16.849728Z","bundle_sha256":"96267dba09a79fbaea984f3d887d8890a1e95597841df4732480ca1815b55b33"}}