{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S6QZIOVA7ZI24EONBW4676SPM3","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":"2be5f3e5e01698ba747edd330f7a2409a7096df4f9a0e6bea683d76d9430becf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T17:59:44Z","title_canon_sha256":"d13109efdd6d5fffa06672505a60fcdfe2abe6a897e49eb2ce870651ed66197f"},"schema_version":"1.0","source":{"id":"2510.18941","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.18941","created_at":"2026-05-20T00:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2510.18941v2","created_at":"2026-05-20T00:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18941","created_at":"2026-05-20T00:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"S6QZIOVA7ZI2","created_at":"2026-05-20T00:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"S6QZIOVA7ZI24EON","created_at":"2026-05-20T00:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"S6QZIOVA","created_at":"2026-05-20T00:02:57Z"}],"graph_snapshots":[{"event_id":"sha256:6c74461cb02f0734bb797f43b174f6a23f3b52b74965ae973deb3966fc15b5bd","target":"graph","created_at":"2026-05-20T00:02:57Z","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/2510.18941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and short-form question-answering. However, many real-world applications require evaluating LLMs in processing professional documents, synthesizing information, and generating comprehensive reports in response to user queries. We introduce ProfBench: a set of over 7000 response-criterion pairs as evaluated by human-experts with professional knowledge across Physics PhD, Chemistry PhD, Finance MBA and Consulting MBA. We bu","authors_text":"Ellie Evans, Jaehun Jung, Jan Kautz, Jiaqi Zeng, Pavlo Molchanov, Shizhe Diao, Ximing Lu, Yejin Choi, Yi Dong, Zhilin Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T17:59:44Z","title":"ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18941","kind":"arxiv","version":2},"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":"sha256:382380481d15ed21bc17b091c2a248b5b55005193650492288f8c188d9e1e2b5","target":"record","created_at":"2026-05-20T00:02:57Z","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":"2be5f3e5e01698ba747edd330f7a2409a7096df4f9a0e6bea683d76d9430becf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-21T17:59:44Z","title_canon_sha256":"d13109efdd6d5fffa06672505a60fcdfe2abe6a897e49eb2ce870651ed66197f"},"schema_version":"1.0","source":{"id":"2510.18941","kind":"arxiv","version":2}},"canonical_sha256":"97a1943aa0fe51ae11cd0db9effa4f66da36b78f57444e09382cbdb205ba3c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a1943aa0fe51ae11cd0db9effa4f66da36b78f57444e09382cbdb205ba3c20","first_computed_at":"2026-05-20T00:02:57.682917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:57.682917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhiXLLpNy5n1pKPKQblqApWn/jYHdDkb07qcaSwcbDHAhTwlTJRvk0L8iawsKBpxVbhOHGuFZEXgTFq8uhqlDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:57.683812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.18941","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:382380481d15ed21bc17b091c2a248b5b55005193650492288f8c188d9e1e2b5","sha256:6c74461cb02f0734bb797f43b174f6a23f3b52b74965ae973deb3966fc15b5bd"],"state_sha256":"6d56c3c8780c317f0eb4bb951b43cfe16e20549445c243242f0087f9f3d75b48"}