{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWHTIFD5J3Q637RBERR4KBF22Y","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":"7f40baa18b298126f5a1b5606e29eb0a26d5dd3ff1affb06048210dfb09c66df","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-25T01:42:45Z","title_canon_sha256":"7ca50bd66f52312e26c4ef252efbcaa0f8e861df021a0e491722a0e9264ff838"},"schema_version":"1.0","source":{"id":"2607.22984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22984","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22984v1","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22984","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"OWHTIFD5J3Q6","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"OWHTIFD5J3Q637RB","created_at":"2026-07-28T00:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"OWHTIFD5","created_at":"2026-07-28T00:22:06Z"}],"graph_snapshots":[{"event_id":"sha256:b13177d28ffee6fed37f607e30deec393e0357eb2c54d4bd0c27fec58427240f","target":"graph","created_at":"2026-07-28T00:22:06Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.22984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models for clinical prediction tasks, such as in-hospital mortality and sepsis onset, routinely achieve high AUROC scores. However, AUROC measures ranking performance rather than clinical sensibility. A model may rank patients correctly overall while predicting a lower mortality risk when a patient's SOFA score worsens, contradicting established medical knowledge.\n  This paper proposes applying metamorphic testing (MT) to clinical machine learning models to evaluate behavioral correctness without requiring ground-truth labels for individual predictions. We design a catalog of ","authors_text":"Bo Chen, Feiyu E, Jie JW Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-25T01:42:45Z","title":"Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22984","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd747da150b6a24f251175d97e6c5cefb04f1b0134a520e061eaf8d783fbe343","target":"record","created_at":"2026-07-28T00:22:06Z","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":"7f40baa18b298126f5a1b5606e29eb0a26d5dd3ff1affb06048210dfb09c66df","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-25T01:42:45Z","title_canon_sha256":"7ca50bd66f52312e26c4ef252efbcaa0f8e861df021a0e491722a0e9264ff838"},"schema_version":"1.0","source":{"id":"2607.22984","kind":"arxiv","version":1}},"canonical_sha256":"758f34147d4ee1edfe212463c504bad626117a1ab4efcf08bcd08925598c2928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"758f34147d4ee1edfe212463c504bad626117a1ab4efcf08bcd08925598c2928","first_computed_at":"2026-07-28T00:22:06.048586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:22:06.048586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sxKSy6WY2yd7UXp1xahdjaij4N7mg+s95K0nDO2dEq4WX8qsidL2oNLIqzbFzLpowckBVQ6h1Uym1bNwRL/VAg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:22:06.049482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd747da150b6a24f251175d97e6c5cefb04f1b0134a520e061eaf8d783fbe343","sha256:b13177d28ffee6fed37f607e30deec393e0357eb2c54d4bd0c27fec58427240f"],"state_sha256":"301a1092e90ae71ce90960ffb2cf60039fb20b34ec1ae7f2cdfe207d3e300a16"}