{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2SCG5PZG27A47AZGRBCKZPQ2TR","short_pith_number":"pith:2SCG5PZG","schema_version":"1.0","canonical_sha256":"d4846ebf26d7c1cf83268844acbe1a9c482ec21d691d2d8b07aefd37de33f0b9","source":{"kind":"arxiv","id":"2410.18991","version":2},"attestation_state":"computed","paper":{"title":"TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Konstantin Hebenstreit, Matthias Samwald, Nathalie Maria Kirch","submitted_at":"2024-10-10T15:06:12Z","abstract_excerpt":"We present the TRIAGE Benchmark, a novel machine ethics (ME) benchmark that tests LLMs' ability to make ethical decisions during mass casualty incidents. It uses real-world ethical dilemmas with clear solutions designed by medical professionals, offering a more realistic alternative to annotation-based benchmarks. TRIAGE incorporates various prompting styles to evaluate model performance across different contexts. Most models consistently outperformed random guessing, suggesting LLMs may support decision-making in triage scenarios. Neutral or factual scenario formulations led to the best perfo"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.18991","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-10T15:06:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b18522d17287bb9d119e41b431a40aba808ad975d157182807988ca42b89f69c","abstract_canon_sha256":"4d0b3c79290c1ea72d9dcc58a8220f8dd6c2fc59648742d6eabf8cf417c0a7e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:23.028925Z","signature_b64":"bI1yysqrQcyeyo0nDwa3zgXL9nZEqAvv4Qqt4+1UxCO0V2Jef8RwHx3iupLMxRcCXbPID9ULYt7O2ltEZm/qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4846ebf26d7c1cf83268844acbe1a9c482ec21d691d2d8b07aefd37de33f0b9","last_reissued_at":"2026-07-05T09:30:23.028460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:23.028460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Konstantin Hebenstreit, Matthias Samwald, Nathalie Maria Kirch","submitted_at":"2024-10-10T15:06:12Z","abstract_excerpt":"We present the TRIAGE Benchmark, a novel machine ethics (ME) benchmark that tests LLMs' ability to make ethical decisions during mass casualty incidents. It uses real-world ethical dilemmas with clear solutions designed by medical professionals, offering a more realistic alternative to annotation-based benchmarks. TRIAGE incorporates various prompting styles to evaluate model performance across different contexts. Most models consistently outperformed random guessing, suggesting LLMs may support decision-making in triage scenarios. Neutral or factual scenario formulations led to the best perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18991","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.18991/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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":"2410.18991","created_at":"2026-07-05T09:30:23.028514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18991v2","created_at":"2026-07-05T09:30:23.028514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18991","created_at":"2026-07-05T09:30:23.028514+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SCG5PZG27A4","created_at":"2026-07-05T09:30:23.028514+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SCG5PZG27A47AZG","created_at":"2026-07-05T09:30:23.028514+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SCG5PZG","created_at":"2026-07-05T09:30:23.028514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02788","citing_title":"Moral Responsibility or Obedience: What Do We Want from AI?","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR","json":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR.json","graph_json":"https://pith.science/api/pith-number/2SCG5PZG27A47AZGRBCKZPQ2TR/graph.json","events_json":"https://pith.science/api/pith-number/2SCG5PZG27A47AZGRBCKZPQ2TR/events.json","paper":"https://pith.science/paper/2SCG5PZG"},"agent_actions":{"view_html":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR","download_json":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR.json","view_paper":"https://pith.science/paper/2SCG5PZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18991&json=true","fetch_graph":"https://pith.science/api/pith-number/2SCG5PZG27A47AZGRBCKZPQ2TR/graph.json","fetch_events":"https://pith.science/api/pith-number/2SCG5PZG27A47AZGRBCKZPQ2TR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR/action/storage_attestation","attest_author":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR/action/author_attestation","sign_citation":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR/action/citation_signature","submit_replication":"https://pith.science/pith/2SCG5PZG27A47AZGRBCKZPQ2TR/action/replication_record"}},"created_at":"2026-07-05T09:30:23.028514+00:00","updated_at":"2026-07-05T09:30:23.028514+00:00"}