{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OBLJTUBJ6WDZIJ55HBVFK6LI3Q","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":"06fb92bde0d65ace5fcd0af29c50d21086dedc4a7aee7adc5e89fcf6bc1c224a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T00:59:16Z","title_canon_sha256":"85645a7da71b23847084b55b8b40b33e6a451879a71dce5f4817f7b397da4132"},"schema_version":"1.0","source":{"id":"2506.04535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04535","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04535v1","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04535","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"OBLJTUBJ6WDZ","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_16","alias_value":"OBLJTUBJ6WDZIJ55","created_at":"2026-07-05T11:16:16Z"},{"alias_kind":"pith_short_8","alias_value":"OBLJTUBJ","created_at":"2026-07-05T11:16:16Z"}],"graph_snapshots":[{"event_id":"sha256:49845bd5908c8ef3f072c952d3ac5611e3068fe37606b69bf238d97786fbc509","target":"graph","created_at":"2026-07-05T11:16:16Z","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/2506.04535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose that benchmarking LLMs on questions which have no reasonable answer actually isn't as silly as it sounds. We also present a benchmark that allows such testing and a method to modify the existing datasets, and discover that existing models demonstrate a performance far from the perfect on such questions. Our code and data artifacts are available at https://github.com/L3G5/impossible-bench","authors_text":"K. O. T. Erziev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T00:59:16Z","title":"BSBench: will your LLM find the largest prime number?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04535","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":"sha256:53fb4442c1128459c67b52183c0e72fc68466eff4f1a5bcb569fbd06e459d3c3","target":"record","created_at":"2026-07-05T11:16:16Z","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":"06fb92bde0d65ace5fcd0af29c50d21086dedc4a7aee7adc5e89fcf6bc1c224a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T00:59:16Z","title_canon_sha256":"85645a7da71b23847084b55b8b40b33e6a451879a71dce5f4817f7b397da4132"},"schema_version":"1.0","source":{"id":"2506.04535","kind":"arxiv","version":1}},"canonical_sha256":"705699d029f5879427bd386a557968dc02c2a8ccb14a881fcc35eadca34a1f03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"705699d029f5879427bd386a557968dc02c2a8ccb14a881fcc35eadca34a1f03","first_computed_at":"2026-07-05T11:16:16.227762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:16.227762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlOormZ/fRKvqPCH6cfjaY8lImFZCdW+FldWptkZ1zFoDCUlmHBBeiNHhKcFaAmhy/4gSxue/CJrNJlhvPNsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:16.228129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53fb4442c1128459c67b52183c0e72fc68466eff4f1a5bcb569fbd06e459d3c3","sha256:49845bd5908c8ef3f072c952d3ac5611e3068fe37606b69bf238d97786fbc509"],"state_sha256":"a6d0cd807f037f3a0a3e81457ab9dc6bfa4aabf18430cff3b9dcaebb713d1a77"}