{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5BSY4PO36V7ASFVKXUDKSBQ4BX","short_pith_number":"pith:5BSY4PO3","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"},"canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","source":{"kind":"arxiv","id":"2506.03399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03399","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03399v1","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03399","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"5BSY4PO36V7A","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"5BSY4PO36V7ASFVK","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"5BSY4PO3","created_at":"2026-07-05T11:15:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5BSY4PO36V7ASFVKXUDKSBQ4BX","target":"record","payload":{"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"},"canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","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"},"source_kind":"arxiv","source_id":"2506.03399","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rg5ZLPxpr/CaCzbm253FC6MCZ/CIyNaSzfE8UitGWZR96t+S2cDEPksIsod4+EymvLCj+l+FcCU0uTjbtBcdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T21:46:30.874229Z"},"content_sha256":"11e9bfea1e9081dd97b61e0194d10b4dce5eaeef6f75c153aadff488b8e60965","schema_version":"1.0","event_id":"sha256:11e9bfea1e9081dd97b61e0194d10b4dce5eaeef6f75c153aadff488b8e60965"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5BSY4PO36V7ASFVKXUDKSBQ4BX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wiLqEO7oTyJSzGDAA34zBj3HFOYizGC447qb6EOx6i5UYUFHvPE7+mZ/Jrv4xOKtUdf5G679bynf7QmzDScAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T21:46:30.874644Z"},"content_sha256":"e33a2738a7df3f19088c8aced03b16d8dda8dbb0f384bdf369f27e530ec8e4d2","schema_version":"1.0","event_id":"sha256:e33a2738a7df3f19088c8aced03b16d8dda8dbb0f384bdf369f27e530ec8e4d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/bundle.json","state_url":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T21:46:30Z","links":{"resolver":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX","bundle":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/bundle.json","state":"https://pith.science/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BSY4PO36V7ASFVKXUDKSBQ4BX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5BSY4PO36V7ASFVKXUDKSBQ4BX","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":"89cc849e9cd595686a1a97eb683af041fb51298558a1728855f1b92a840fa4be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-06-03T21:14:35Z","title_canon_sha256":"918e1cdca8dcf48dbc69f937c17b7120c0b402c2508894b5c9e280fdb160b672"},"schema_version":"1.0","source":{"id":"2506.03399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03399","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03399v1","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03399","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"5BSY4PO36V7A","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"5BSY4PO36V7ASFVK","created_at":"2026-07-05T11:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"5BSY4PO3","created_at":"2026-07-05T11:15:26Z"}],"graph_snapshots":[{"event_id":"sha256:e33a2738a7df3f19088c8aced03b16d8dda8dbb0f384bdf369f27e530ec8e4d2","target":"graph","created_at":"2026-07-05T11:15:26Z","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/2506.03399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Sean Steinle","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-06-03T21:14:35Z","title":"Sampling Preferences Yields Simple Trustworthiness Scores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03399","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":"sha256:11e9bfea1e9081dd97b61e0194d10b4dce5eaeef6f75c153aadff488b8e60965","target":"record","created_at":"2026-07-05T11:15:26Z","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":"89cc849e9cd595686a1a97eb683af041fb51298558a1728855f1b92a840fa4be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-06-03T21:14:35Z","title_canon_sha256":"918e1cdca8dcf48dbc69f937c17b7120c0b402c2508894b5c9e280fdb160b672"},"schema_version":"1.0","source":{"id":"2506.03399","kind":"arxiv","version":1}},"canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8658e3ddbf57e0916aabd06a9061c0dfcd7e4fc0730870228208e747646554a","first_computed_at":"2026-07-05T11:15:26.931167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:26.931167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iImLGWTX2CsYT1mw2pUsH2DMoUs/01ToYLE4SOYNR5CCbpi85jwzyC86Ro0s0AQpXIv8bEtfHhFY+Ov/gdyhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:26.931615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11e9bfea1e9081dd97b61e0194d10b4dce5eaeef6f75c153aadff488b8e60965","sha256:e33a2738a7df3f19088c8aced03b16d8dda8dbb0f384bdf369f27e530ec8e4d2"],"state_sha256":"b0c07bc69718669c7869ec194ad647724311ec50c9efc05a14728f77a4decf77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TRNWZshSrqMucrrCAX85yIILe5un4sZMFeGYGUL/qIDEC2p6eF33tZDd6Pz1ydu8OEYTreVm7C+/08bvHlI5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T21:46:30.877205Z","bundle_sha256":"f1267193bb830b5e15000fde634741ae28b44bdaf9e2c22753f99f32c118e921"}}