{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VJQA6Y47FFKIOQ26GXWNJKXHQD","short_pith_number":"pith:VJQA6Y47","schema_version":"1.0","canonical_sha256":"aa600f639f295487435e35ecd4aae780eee8f1327d22d0256cd78e177d36c4ab","source":{"kind":"arxiv","id":"2411.14486","version":1},"attestation_state":"computed","paper":{"title":"The Impossible Test: A 2024 Unsolvable Dataset and A Chance for an AGI Quiz","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Noever, Forrest McKee","submitted_at":"2024-11-20T04:12:29Z","abstract_excerpt":"This research introduces a novel evaluation framework designed to assess large language models' (LLMs) ability to acknowledge uncertainty on 675 fundamentally unsolvable problems. Using a curated dataset of graduate-level grand challenge questions with intentionally unknowable answers, we evaluated twelve state-of-the-art LLMs, including both open and closed-source models, on their propensity to admit ignorance rather than generate plausible but incorrect responses. The best models scored in 62-68% accuracy ranges for admitting the problem solution was unknown in fields ranging from biology to"},"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":"2411.14486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T04:12:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"113b85e80152cf14ab8de334ac4277061f96409c93762f9a13f9a598558bad13","abstract_canon_sha256":"520352f0dfbb1b96e6a26ae825ddb56ac06c1060180b9f054fa64e25a0344ec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:51.942954Z","signature_b64":"BFFUtb6FdLfMrhDApC8p+GXI47FmKjitO7q2weAAthPpwZDkpPpjsLC8ljB6QCSx/NnLkXDFOS7sKz26hV+FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa600f639f295487435e35ecd4aae780eee8f1327d22d0256cd78e177d36c4ab","last_reissued_at":"2026-07-05T09:38:51.942539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:51.942539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Impossible Test: A 2024 Unsolvable Dataset and A Chance for an AGI Quiz","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Noever, Forrest McKee","submitted_at":"2024-11-20T04:12:29Z","abstract_excerpt":"This research introduces a novel evaluation framework designed to assess large language models' (LLMs) ability to acknowledge uncertainty on 675 fundamentally unsolvable problems. Using a curated dataset of graduate-level grand challenge questions with intentionally unknowable answers, we evaluated twelve state-of-the-art LLMs, including both open and closed-source models, on their propensity to admit ignorance rather than generate plausible but incorrect responses. The best models scored in 62-68% accuracy ranges for admitting the problem solution was unknown in fields ranging from biology to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14486","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/2411.14486/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":"2411.14486","created_at":"2026-07-05T09:38:51.942588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14486v1","created_at":"2026-07-05T09:38:51.942588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14486","created_at":"2026-07-05T09:38:51.942588+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJQA6Y47FFKI","created_at":"2026-07-05T09:38:51.942588+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJQA6Y47FFKIOQ26","created_at":"2026-07-05T09:38:51.942588+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJQA6Y47","created_at":"2026-07-05T09:38:51.942588+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/VJQA6Y47FFKIOQ26GXWNJKXHQD","json":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD.json","graph_json":"https://pith.science/api/pith-number/VJQA6Y47FFKIOQ26GXWNJKXHQD/graph.json","events_json":"https://pith.science/api/pith-number/VJQA6Y47FFKIOQ26GXWNJKXHQD/events.json","paper":"https://pith.science/paper/VJQA6Y47"},"agent_actions":{"view_html":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD","download_json":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD.json","view_paper":"https://pith.science/paper/VJQA6Y47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14486&json=true","fetch_graph":"https://pith.science/api/pith-number/VJQA6Y47FFKIOQ26GXWNJKXHQD/graph.json","fetch_events":"https://pith.science/api/pith-number/VJQA6Y47FFKIOQ26GXWNJKXHQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD/action/storage_attestation","attest_author":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD/action/author_attestation","sign_citation":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD/action/citation_signature","submit_replication":"https://pith.science/pith/VJQA6Y47FFKIOQ26GXWNJKXHQD/action/replication_record"}},"created_at":"2026-07-05T09:38:51.942588+00:00","updated_at":"2026-07-05T09:38:51.942588+00:00"}