{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PJRYCLCDTFLJHXTUOS7OPYWXZS","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":"c8a2c8eca62337abe822649d35ec12d2e49ed2061e34b16fa4889d3302ac77d7","cross_cats_sorted":["cs.CC","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T18:07:44Z","title_canon_sha256":"47b20b3411e6d99bbb3bd7ebd1875f27f90bdce43442a325f9728cc218bb3d13"},"schema_version":"1.0","source":{"id":"2312.14890","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14890","created_at":"2026-07-05T07:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14890v4","created_at":"2026-07-05T07:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14890","created_at":"2026-07-05T07:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"PJRYCLCDTFLJ","created_at":"2026-07-05T07:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"PJRYCLCDTFLJHXTU","created_at":"2026-07-05T07:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"PJRYCLCD","created_at":"2026-07-05T07:43:59Z"}],"graph_snapshots":[{"event_id":"sha256:b2268b7fd1fde2779f47c83e62599f6ba36b8d324767472d5494c3ebee35b395","target":"graph","created_at":"2026-07-05T07:43:59Z","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/2312.14890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Complex reasoning ability is one of the most important features of current LLMs, which has also been leveraged to play an integral role in complex decision-making tasks. Therefore, the investigation into the reasoning capabilities of Large Language Models (LLMs) is critical: numerous benchmarks have been established to assess the reasoning abilities of LLMs. However, current benchmarks are inadequate in offering a rigorous evaluation of the full extent of reasoning abilities that LLMs are capable of achieving. They are also prone to the risk of overfitting, as these benchmarks, being publicly ","authors_text":"Haoyang Ling, Lingyao Li, Lizhou Fan, Wenyue Hua, Yongfeng Zhang","cross_cats":["cs.CC","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T18:07:44Z","title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14890","kind":"arxiv","version":4},"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:e308f37f0cb617af3ec3af26e7ab89717287b39710c92061ce3fef718e749203","target":"record","created_at":"2026-07-05T07:43:59Z","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":"c8a2c8eca62337abe822649d35ec12d2e49ed2061e34b16fa4889d3302ac77d7","cross_cats_sorted":["cs.CC","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T18:07:44Z","title_canon_sha256":"47b20b3411e6d99bbb3bd7ebd1875f27f90bdce43442a325f9728cc218bb3d13"},"schema_version":"1.0","source":{"id":"2312.14890","kind":"arxiv","version":4}},"canonical_sha256":"7a63812c43995693de7474bee7e2d7ccacb5af95a1b0cfbe71e8aa6067470fb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a63812c43995693de7474bee7e2d7ccacb5af95a1b0cfbe71e8aa6067470fb2","first_computed_at":"2026-07-05T07:43:59.274745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:59.274745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mzQB/Hw9h4vZK7gnPlZ6nZOuDHIz1r5mYJ7qKKztlzIl0o3atsqCO1bvoEJHLcqOxDYlYz/jHXdfQFZlOR0UDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:59.275221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14890","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e308f37f0cb617af3ec3af26e7ab89717287b39710c92061ce3fef718e749203","sha256:b2268b7fd1fde2779f47c83e62599f6ba36b8d324767472d5494c3ebee35b395"],"state_sha256":"91fda69b9398823418fa97472372058c600cbf75e946a685f2b83f80d2680d0c"}