{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMNJUJD2DH3Q26D4XAP7OG2YV2","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":"4dcdb24f9865de63c0692f1d2cc763523a99f8d6a4f182168e5d46bdfebcfe98","cross_cats_sorted":["cs.AI","cs.CY","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:17:13Z","title_canon_sha256":"01eb52e45017d5f010feb471d12fc689fb86138f1eb20fde6c547827f7fb6972"},"schema_version":"1.0","source":{"id":"2605.12895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12895","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12895v1","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12895","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"IMNJUJD2DH3Q","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IMNJUJD2DH3Q26D4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IMNJUJD2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2024a49bbeadc3f1fc286f3bfca245fb6a5a0d98d0bfa5030cc1eed7c093b92a","target":"graph","created_at":"2026-05-18T03:09:10Z","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":"A classifier satisfying conventional high-discrimination benchmarks can simultaneously fail input-encoding stability and threshold-shift sensitivity checks, while subgroup AUC parity remains statistically inconclusive, pointing to deployment risks that aggregate evaluation alone cannot detect."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the five chosen dimensions and their operationalized sub-criteria with pre-specified thresholds adequately capture the primary pre-deployment risks for clinical AI systems across diverse datasets and use cases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RISED is a structured pre-deployment safety framework that flags failures in clinical AI systems across reliability, inclusivity, sensitivity, equity, and deployability using pre-specified criteria and statistical corrections, even when aggregate accuracy looks strong."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity."}],"snapshot_sha256":"40024834475abee06200c61a1fba006570cb8387589939b4d1abaf9e5be2acf3"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Aggregate accuracy metrics dominate the evaluation of clinical AI decision-support systems but do not detect deployment-phase failures of input reliability, subgroup equity, threshold sensitivity, or operational feasibility. We propose the RISED Framework: a five-dimension pre-deployment evaluation covering Reliability, Inclusivity, Sensitivity, Equity, and Deployability, in which each dimension is operationalized through formal sub-criteria, pre-specified pass/fail thresholds, and bias-corrected accelerated (BCa) bootstrap 95% confidence intervals combined under a Holm-Bonferroni family-wise ","authors_text":"Rohith Reddy Bellibatlu","cross_cats":["cs.AI","cs.CY","stat.AP"],"headline":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:17:13Z","title":"RISED: A Pre-Deployment Safety Evaluation Framework for Clinical AI Decision-Support Systems"},"references":{"count":105,"internal_anchors":0,"resolved_work":105,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"and Torkamani, Ali and Dias, Raquel and Gianfrancesco, Milena and Arnaout, Rima and Kohane, Isaac S","work_id":"f0895a9b-4adb-4c6c-a04f-339328cc7e53","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"and Porras, Antonio R","work_id":"0f1f71b2-07f9-4ecc-a9ba-bb60ba4e31b4","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"and Calvert, Melanie J","work_id":"5e8b5a88-2d28-4f3a-a5e5-23969f6014d0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"and Denniston, Alastair K","work_id":"fd2a7a32-7c79-4c7e-a2a0-8186385a7928","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Journal of the American Statistical Association , year =","work_id":"acc72481-3709-44d8-9ed8-4ab9f814ce86","year":null}],"snapshot_sha256":"54728d5b38602b16403c9cb6d4206edbbbf8e5d0892a8493f1c6e803c57ce0ee"},"source":{"id":"2605.12895","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:09:19.495359Z","id":"bef42c7b-3f83-4c07-9247-75ff3c92a55f","model_set":{"reader":"grok-4.3"},"one_line_summary":"RISED is a structured pre-deployment safety framework that flags failures in clinical AI systems across reliability, inclusivity, sensitivity, equity, and deployability using pre-specified criteria and statistical corrections, even when aggregate accuracy looks strong.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity.","strongest_claim":"A classifier satisfying conventional high-discrimination benchmarks can simultaneously fail input-encoding stability and threshold-shift sensitivity checks, while subgroup AUC parity remains statistically inconclusive, pointing to deployment risks that aggregate evaluation alone cannot detect.","weakest_assumption":"That the five chosen dimensions and their operationalized sub-criteria with pre-specified thresholds adequately capture the primary pre-deployment risks for clinical AI systems across diverse datasets and use cases."}},"verdict_id":"bef42c7b-3f83-4c07-9247-75ff3c92a55f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:935ffdc94189ddc712fc774ff13542b2e12ca1f1c9152bd89cc76d5f9ec5c470","target":"record","created_at":"2026-05-18T03:09:10Z","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":"4dcdb24f9865de63c0692f1d2cc763523a99f8d6a4f182168e5d46bdfebcfe98","cross_cats_sorted":["cs.AI","cs.CY","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:17:13Z","title_canon_sha256":"01eb52e45017d5f010feb471d12fc689fb86138f1eb20fde6c547827f7fb6972"},"schema_version":"1.0","source":{"id":"2605.12895","kind":"arxiv","version":1}},"canonical_sha256":"431a9a247a19f70d787cb81ff71b58aea165c38cb2824b9df4913ffc631cf61e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"431a9a247a19f70d787cb81ff71b58aea165c38cb2824b9df4913ffc631cf61e","first_computed_at":"2026-05-18T03:09:10.861765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:10.861765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQswA/YWBsjwPRlt1C03ByUV0rN+iENEPZQQK3KpEwBmFPk3BnlKyxP0HoNeOFSHU37mH7ke0vqj3cL+CvvyCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:10.862550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:935ffdc94189ddc712fc774ff13542b2e12ca1f1c9152bd89cc76d5f9ec5c470","sha256:2024a49bbeadc3f1fc286f3bfca245fb6a5a0d98d0bfa5030cc1eed7c093b92a"],"state_sha256":"d52639d211fa165a4179eae0f61a99246258298a992d1a4b891a6b96af5b863f"}