{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E2UNEZUM43GRBHOW2YG7F7X5GS","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":"621c78e33f6d8a421f0b37efbfa28362e2ef12d8d2004916b35638f4df22d0b8","cross_cats_sorted":["math.ST","q-fin.RM","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T02:08:37Z","title_canon_sha256":"5e73ed42608d76305cf86f6f120f73bb83228a1beb03fc2b1c25e3365f108e94"},"schema_version":"1.0","source":{"id":"2310.07132","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07132","created_at":"2026-07-05T08:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07132v3","created_at":"2026-07-05T08:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07132","created_at":"2026-07-05T08:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"E2UNEZUM43GR","created_at":"2026-07-05T08:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"E2UNEZUM43GRBHOW","created_at":"2026-07-05T08:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"E2UNEZUM","created_at":"2026-07-05T08:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:53019c369fdcd60f6f3a38e1560a36df1de6244846634d65bc6835061fe15bab","target":"graph","created_at":"2026-07-05T08:29:17Z","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/2310.07132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a distributional framework for benchmarking socio-technical risks of foundation models with quantified statistical significance. Our approach hinges on a new statistical relative testing based on first and second order stochastic dominance of real random variables. We show that the second order statistics in this test are linked to mean-risk models commonly used in econometrics and mathematical finance to balance risk and utility when choosing between alternatives. Using this framework, we formally develop a risk-aware approach for foundation model selection given guardrails quantif","authors_text":"Apoorva Nitsure, Brian Belgodere, Igor Melnyk, Jerret Ross, Jiri Navratil, Kristjan Greenewald, Mattia Rigotti, Mikhail Yurochkin, Youssef Mroueh","cross_cats":["math.ST","q-fin.RM","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T02:08:37Z","title":"Risk Aware Benchmarking of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07132","kind":"arxiv","version":3},"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:afb1d9b9d3d0920e5788ba268e730abac0db3f475a4158c7e86c94c08427eb1f","target":"record","created_at":"2026-07-05T08:29:17Z","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":"621c78e33f6d8a421f0b37efbfa28362e2ef12d8d2004916b35638f4df22d0b8","cross_cats_sorted":["math.ST","q-fin.RM","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T02:08:37Z","title_canon_sha256":"5e73ed42608d76305cf86f6f120f73bb83228a1beb03fc2b1c25e3365f108e94"},"schema_version":"1.0","source":{"id":"2310.07132","kind":"arxiv","version":3}},"canonical_sha256":"26a8d2668ce6cd109dd6d60df2fefd34bde4c7daf72e9c1e980740c69296635a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26a8d2668ce6cd109dd6d60df2fefd34bde4c7daf72e9c1e980740c69296635a","first_computed_at":"2026-07-05T08:29:17.919561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:17.919561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Viu0O2vutgA+k1pn8MiGGuSnAWHFeTdoU2SI+AOC1RUhnf4Ew4MC6sMar95GE2JHeHKq6d4wT/qO85lYA2oeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:17.920013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07132","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afb1d9b9d3d0920e5788ba268e730abac0db3f475a4158c7e86c94c08427eb1f","sha256:53019c369fdcd60f6f3a38e1560a36df1de6244846634d65bc6835061fe15bab"],"state_sha256":"0d37083ae0439016e6d6b3fa55897e24b8a886b60d835c24ca3584e2a44868e6"}