{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5BSY4PO36V7ASFVKXUDKSBQ4BX","short_pith_number":"pith:5BSY4PO3","schema_version":"1.0","canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","source":{"kind":"arxiv","id":"2506.03399","version":1},"attestation_state":"computed","paper":{"title":"Sampling Preferences Yields Simple Trustworthiness Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Sean Steinle","submitted_at":"2025-06-03T21:14:35Z","abstract_excerpt":"With the onset of large language models (LLMs), the performance of artificial intelligence (AI) models is becoming increasingly multi-dimensional. Accordingly, there have been several large, multi-dimensional evaluation frameworks put forward to evaluate LLMs. Though these frameworks are much more realistic than previous attempts which only used a single score like accuracy, multi-dimensional evaluations can complicate decision-making since there is no obvious way to select an optimal model. This work introduces preference sampling, a method to extract a scalar trustworthiness score from multi"},"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":"2506.03399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-06-03T21:14:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"918e1cdca8dcf48dbc69f937c17b7120c0b402c2508894b5c9e280fdb160b672","abstract_canon_sha256":"89cc849e9cd595686a1a97eb683af041fb51298558a1728855f1b92a840fa4be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:26.931615Z","signature_b64":"iImLGWTX2CsYT1mw2pUsH2DMoUs/01ToYLE4SOYNR5CCbpi85jwzyC86Ro0s0AQpXIv8bEtfHhFY+Ov/gdyhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","last_reissued_at":"2026-07-05T11:15:26.931167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:26.931167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling Preferences Yields Simple Trustworthiness Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Sean Steinle","submitted_at":"2025-06-03T21:14:35Z","abstract_excerpt":"With the onset of large language models (LLMs), the performance of artificial intelligence (AI) models is becoming increasingly multi-dimensional. Accordingly, there have been several large, multi-dimensional evaluation frameworks put forward to evaluate LLMs. Though these frameworks are much more realistic than previous attempts which only used a single score like accuracy, multi-dimensional evaluations can complicate decision-making since there is no obvious way to select an optimal model. This work introduces preference sampling, a method to extract a scalar trustworthiness score from multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03399","kind":"arxiv","version":1},"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/2506.03399/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":"2506.03399","created_at":"2026-07-05T11:15:26.931219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03399v1","created_at":"2026-07-05T11:15:26.931219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03399","created_at":"2026-07-05T11:15:26.931219+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BSY4PO36V7A","created_at":"2026-07-05T11:15:26.931219+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BSY4PO36V7ASFVK","created_at":"2026-07-05T11:15:26.931219+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BSY4PO3","created_at":"2026-07-05T11:15:26.931219+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/5BSY4PO36V7ASFVKXUDKSBQ4BX","json":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX.json","graph_json":"https://pith.science/api/pith-number/5BSY4PO36V7ASFVKXUDKSBQ4BX/graph.json","events_json":"https://pith.science/api/pith-number/5BSY4PO36V7ASFVKXUDKSBQ4BX/events.json","paper":"https://pith.science/paper/5BSY4PO3"},"agent_actions":{"view_html":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX","download_json":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX.json","view_paper":"https://pith.science/paper/5BSY4PO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03399&json=true","fetch_graph":"https://pith.science/api/pith-number/5BSY4PO36V7ASFVKXUDKSBQ4BX/graph.json","fetch_events":"https://pith.science/api/pith-number/5BSY4PO36V7ASFVKXUDKSBQ4BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/action/storage_attestation","attest_author":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/action/author_attestation","sign_citation":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/action/citation_signature","submit_replication":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/action/replication_record"}},"created_at":"2026-07-05T11:15:26.931219+00:00","updated_at":"2026-07-05T11:15:26.931219+00:00"}