{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IMNJUJD2DH3Q26D4XAP7OG2YV2","short_pith_number":"pith:IMNJUJD2","schema_version":"1.0","canonical_sha256":"431a9a247a19f70d787cb81ff71b58aea165c38cb2824b9df4913ffc631cf61e","source":{"kind":"arxiv","id":"2605.12895","version":1},"attestation_state":"computed","paper":{"title":"RISED: A Pre-Deployment Safety Evaluation Framework for Clinical AI Decision-Support Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity.","cross_cats":["cs.AI","cs.CY","stat.AP"],"primary_cat":"cs.LG","authors_text":"Rohith Reddy Bellibatlu","submitted_at":"2026-05-13T02:17:13Z","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 "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.12895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:17:13Z","cross_cats_sorted":["cs.AI","cs.CY","stat.AP"],"title_canon_sha256":"01eb52e45017d5f010feb471d12fc689fb86138f1eb20fde6c547827f7fb6972","abstract_canon_sha256":"4dcdb24f9865de63c0692f1d2cc763523a99f8d6a4f182168e5d46bdfebcfe98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:10.862550Z","signature_b64":"IQswA/YWBsjwPRlt1C03ByUV0rN+iENEPZQQK3KpEwBmFPk3BnlKyxP0HoNeOFSHU37mH7ke0vqj3cL+CvvyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"431a9a247a19f70d787cb81ff71b58aea165c38cb2824b9df4913ffc631cf61e","last_reissued_at":"2026-05-18T03:09:10.861765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:10.861765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RISED: A Pre-Deployment Safety Evaluation Framework for Clinical AI Decision-Support Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity.","cross_cats":["cs.AI","cs.CY","stat.AP"],"primary_cat":"cs.LG","authors_text":"Rohith Reddy Bellibatlu","submitted_at":"2026-05-13T02:17:13Z","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 "},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"40024834475abee06200c61a1fba006570cb8387589939b4d1abaf9e5be2acf3"},"source":{"id":"2605.12895","kind":"arxiv","version":1},"verdict":{"id":"bef42c7b-3f83-4c07-9247-75ff3c92a55f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:09:19.495359Z","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.","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","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.","pith_extraction_headline":"Clinical AI models that pass standard accuracy tests can fail on input stability and threshold sensitivity."},"references":{"count":105,"sample":[{"doi":"","year":null,"title":"and Torkamani, Ali and Dias, Raquel and Gianfrancesco, Milena and Arnaout, Rima and Kohane, Isaac S","work_id":"f0895a9b-4adb-4c6c-a04f-339328cc7e53","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Porras, Antonio R","work_id":"0f1f71b2-07f9-4ecc-a9ba-bb60ba4e31b4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Calvert, Melanie J","work_id":"5e8b5a88-2d28-4f3a-a5e5-23969f6014d0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Denniston, Alastair K","work_id":"fd2a7a32-7c79-4c7e-a2a0-8186385a7928","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of the American Statistical Association , year =","work_id":"acc72481-3709-44d8-9ed8-4ab9f814ce86","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":105,"snapshot_sha256":"54728d5b38602b16403c9cb6d4206edbbbf8e5d0892a8493f1c6e803c57ce0ee","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":"2605.12895","created_at":"2026-05-18T03:09:10.861896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12895v1","created_at":"2026-05-18T03:09:10.861896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12895","created_at":"2026-05-18T03:09:10.861896+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMNJUJD2DH3Q","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMNJUJD2DH3Q26D4","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMNJUJD2","created_at":"2026-05-18T12:33:37.589309+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/IMNJUJD2DH3Q26D4XAP7OG2YV2","json":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2.json","graph_json":"https://pith.science/api/pith-number/IMNJUJD2DH3Q26D4XAP7OG2YV2/graph.json","events_json":"https://pith.science/api/pith-number/IMNJUJD2DH3Q26D4XAP7OG2YV2/events.json","paper":"https://pith.science/paper/IMNJUJD2"},"agent_actions":{"view_html":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2","download_json":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2.json","view_paper":"https://pith.science/paper/IMNJUJD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12895&json=true","fetch_graph":"https://pith.science/api/pith-number/IMNJUJD2DH3Q26D4XAP7OG2YV2/graph.json","fetch_events":"https://pith.science/api/pith-number/IMNJUJD2DH3Q26D4XAP7OG2YV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2/action/storage_attestation","attest_author":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2/action/author_attestation","sign_citation":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2/action/citation_signature","submit_replication":"https://pith.science/pith/IMNJUJD2DH3Q26D4XAP7OG2YV2/action/replication_record"}},"created_at":"2026-05-18T03:09:10.861896+00:00","updated_at":"2026-05-18T03:09:10.861896+00:00"}