{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3IC26KLM4SJXYBX4QAZRGHTJK6","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":"66712dd0cba3b19a596a1bf80be5cb42524c104c6e918b43c0ae7b97118c19dc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T01:07:59Z","title_canon_sha256":"4ea6e3e58b0102d03711e372df45b6366f16406ed55190983046ed99ccd60d44"},"schema_version":"1.0","source":{"id":"2508.17580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17580","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17580v1","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17580","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_12","alias_value":"3IC26KLM4SJX","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_16","alias_value":"3IC26KLM4SJXYBX4","created_at":"2026-07-05T11:58:44Z"},{"alias_kind":"pith_short_8","alias_value":"3IC26KLM","created_at":"2026-07-05T11:58:44Z"}],"graph_snapshots":[{"event_id":"sha256:b5c7dc9065605b525ccd93e9e48b0e6acacd7a63e012a0907696f767e389bfb0","target":"graph","created_at":"2026-07-05T11:58:44Z","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/2508.17580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks shape progress in AI research. A useful benchmark should be both difficult and realistic: questions should challenge frontier models while also reflecting real-world usage. Yet, current paradigms face a difficulty-realism tension: exam-style benchmarks are often made artificially difficult with limited real-world value, while benchmarks based on real user interaction often skew toward easy, high-frequency problems. In this work, we explore a radically different paradigm: assessing models on unsolved questions. Rather than a static benchmark scored once, we curate unsolved questions ","authors_text":"Andrew Y. Ng, Fan Nie, Huaxiu Yao, James Zou, Ken Ziyu Liu, Linjun Zhang, Niklas Muennighoff, Percy Liang, Rui Sun, Sanmi Koyejo, Weijia Shi, Wei Liu, Yejin Choi, Zihao Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T01:07:59Z","title":"UQ: Assessing Language Models on Unsolved Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17580","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":"sha256:716c348e6d6ded6bee472e0d9a47d0fdf5cc87c19548610f341ad57495142a67","target":"record","created_at":"2026-07-05T11:58:44Z","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":"66712dd0cba3b19a596a1bf80be5cb42524c104c6e918b43c0ae7b97118c19dc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T01:07:59Z","title_canon_sha256":"4ea6e3e58b0102d03711e372df45b6366f16406ed55190983046ed99ccd60d44"},"schema_version":"1.0","source":{"id":"2508.17580","kind":"arxiv","version":1}},"canonical_sha256":"da05af296ce4937c06fc8033131e6957a60bc094e830d6751bc46536403b8b97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da05af296ce4937c06fc8033131e6957a60bc094e830d6751bc46536403b8b97","first_computed_at":"2026-07-05T11:58:44.002089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:44.002089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qLLPdUblJk6ogHb76f1NAvs7i6bHVxmBJ7OpOqGZuCWhn61vHL9jLdnVvQThiQZ2czwvR0hAfJZh/Pyj9voBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:44.002550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:716c348e6d6ded6bee472e0d9a47d0fdf5cc87c19548610f341ad57495142a67","sha256:b5c7dc9065605b525ccd93e9e48b0e6acacd7a63e012a0907696f767e389bfb0"],"state_sha256":"8425d6135e980ecfb0abdec343e767a90b4cfd284834ea6093fef0208f500ffb"}