{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E2UNEZUM43GRBHOW2YG7F7X5GS","short_pith_number":"pith:E2UNEZUM","schema_version":"1.0","canonical_sha256":"26a8d2668ce6cd109dd6d60df2fefd34bde4c7daf72e9c1e980740c69296635a","source":{"kind":"arxiv","id":"2310.07132","version":3},"attestation_state":"computed","paper":{"title":"Risk Aware Benchmarking of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","q-fin.RM","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Apoorva Nitsure, Brian Belgodere, Igor Melnyk, Jerret Ross, Jiri Navratil, Kristjan Greenewald, Mattia Rigotti, Mikhail Yurochkin, Youssef Mroueh","submitted_at":"2023-10-11T02:08:37Z","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"},"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":"2310.07132","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T02:08:37Z","cross_cats_sorted":["math.ST","q-fin.RM","stat.ML","stat.TH"],"title_canon_sha256":"5e73ed42608d76305cf86f6f120f73bb83228a1beb03fc2b1c25e3365f108e94","abstract_canon_sha256":"621c78e33f6d8a421f0b37efbfa28362e2ef12d8d2004916b35638f4df22d0b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:17.920013Z","signature_b64":"Viu0O2vutgA+k1pn8MiGGuSnAWHFeTdoU2SI+AOC1RUhnf4Ew4MC6sMar95GE2JHeHKq6d4wT/qO85lYA2oeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a8d2668ce6cd109dd6d60df2fefd34bde4c7daf72e9c1e980740c69296635a","last_reissued_at":"2026-07-05T08:29:17.919561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:17.919561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk Aware Benchmarking of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","q-fin.RM","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Apoorva Nitsure, Brian Belgodere, Igor Melnyk, Jerret Ross, Jiri Navratil, Kristjan Greenewald, Mattia Rigotti, Mikhail Yurochkin, Youssef Mroueh","submitted_at":"2023-10-11T02:08:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07132","kind":"arxiv","version":3},"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/2310.07132/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":"2310.07132","created_at":"2026-07-05T08:29:17.919615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07132v3","created_at":"2026-07-05T08:29:17.919615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07132","created_at":"2026-07-05T08:29:17.919615+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2UNEZUM43GR","created_at":"2026-07-05T08:29:17.919615+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2UNEZUM43GRBHOW","created_at":"2026-07-05T08:29:17.919615+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2UNEZUM","created_at":"2026-07-05T08:29:17.919615+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/E2UNEZUM43GRBHOW2YG7F7X5GS","json":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS.json","graph_json":"https://pith.science/api/pith-number/E2UNEZUM43GRBHOW2YG7F7X5GS/graph.json","events_json":"https://pith.science/api/pith-number/E2UNEZUM43GRBHOW2YG7F7X5GS/events.json","paper":"https://pith.science/paper/E2UNEZUM"},"agent_actions":{"view_html":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS","download_json":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS.json","view_paper":"https://pith.science/paper/E2UNEZUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07132&json=true","fetch_graph":"https://pith.science/api/pith-number/E2UNEZUM43GRBHOW2YG7F7X5GS/graph.json","fetch_events":"https://pith.science/api/pith-number/E2UNEZUM43GRBHOW2YG7F7X5GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS/action/storage_attestation","attest_author":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS/action/author_attestation","sign_citation":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS/action/citation_signature","submit_replication":"https://pith.science/pith/E2UNEZUM43GRBHOW2YG7F7X5GS/action/replication_record"}},"created_at":"2026-07-05T08:29:17.919615+00:00","updated_at":"2026-07-05T08:29:17.919615+00:00"}