{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DFUTNGSM7FA7IAL3DDRPYX5Q2U","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":"b5fac4145ad108f00a99b1f2e4decc6a8dc6ab9fbb4ec261c31d4b015f5da852","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T09:34:43Z","title_canon_sha256":"91578eb3a35746ff44ba67a7bafef95c045ac9fe4001915b47824b09cc66d374"},"schema_version":"1.0","source":{"id":"2212.10114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10114","created_at":"2026-07-05T06:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10114v2","created_at":"2026-07-05T06:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10114","created_at":"2026-07-05T06:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"DFUTNGSM7FA7","created_at":"2026-07-05T06:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"DFUTNGSM7FA7IAL3","created_at":"2026-07-05T06:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"DFUTNGSM","created_at":"2026-07-05T06:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:09c6916200874eeca15444b98d8b11de9d68d10aff7b7cf25252516865bfa134","target":"graph","created_at":"2026-07-05T06:16:35Z","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/2212.10114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated solid zero-shot reasoning capabilities, which is reflected in their performance on the current test tasks. This calls for a more challenging benchmark requiring highly advanced reasoning ability to be solved. In this paper, we introduce such a benchmark, consisting of 191 long-form (1200 words on average) mystery narratives constructed as detective puzzles. Puzzles are sourced from the \"5 Minute Mystery\" platform and include a multiple-choice question for evaluation. Only 47% of humans solve a puzzle successfully on average, while the best human s","authors_text":"Maksym Del, Mark Fishel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T09:34:43Z","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10114","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":"sha256:281fe05156ed26f4af8f57c815c215a5f634d782f38bf162c0dfbc77909b061a","target":"record","created_at":"2026-07-05T06:16:35Z","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":"b5fac4145ad108f00a99b1f2e4decc6a8dc6ab9fbb4ec261c31d4b015f5da852","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T09:34:43Z","title_canon_sha256":"91578eb3a35746ff44ba67a7bafef95c045ac9fe4001915b47824b09cc66d374"},"schema_version":"1.0","source":{"id":"2212.10114","kind":"arxiv","version":2}},"canonical_sha256":"1969369a4cf941f4017b18e2fc5fb0d50027188ae54c76e9ff32a4ea7c28b434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1969369a4cf941f4017b18e2fc5fb0d50027188ae54c76e9ff32a4ea7c28b434","first_computed_at":"2026-07-05T06:16:35.858520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:35.858520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LXvI+Mznv5lp0jRUd9OnDi+pVu7K1hh9ZsqW97Ff0GkFVClcKY50whV0oTu9eAWiVsGhRlyb99fm22x8bDDlAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:35.859025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:281fe05156ed26f4af8f57c815c215a5f634d782f38bf162c0dfbc77909b061a","sha256:09c6916200874eeca15444b98d8b11de9d68d10aff7b7cf25252516865bfa134"],"state_sha256":"ccc8631efb9b0ad8e5efd6207ae73e7226afbd8445aec05d6f167cb64726e89d"}