{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PJRYCLCDTFLJHXTUOS7OPYWXZS","short_pith_number":"pith:PJRYCLCD","schema_version":"1.0","canonical_sha256":"7a63812c43995693de7474bee7e2d7ccacb5af95a1b0cfbe71e8aa6067470fb2","source":{"kind":"arxiv","id":"2312.14890","version":4},"attestation_state":"computed","paper":{"title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Haoyang Ling, Lingyao Li, Lizhou Fan, Wenyue Hua, Yongfeng Zhang","submitted_at":"2023-12-22T18:07:44Z","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 "},"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":"2312.14890","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T18:07:44Z","cross_cats_sorted":["cs.CC","cs.CL","cs.LG"],"title_canon_sha256":"47b20b3411e6d99bbb3bd7ebd1875f27f90bdce43442a325f9728cc218bb3d13","abstract_canon_sha256":"c8a2c8eca62337abe822649d35ec12d2e49ed2061e34b16fa4889d3302ac77d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:59.275221Z","signature_b64":"mzQB/Hw9h4vZK7gnPlZ6nZOuDHIz1r5mYJ7qKKztlzIl0o3atsqCO1bvoEJHLcqOxDYlYz/jHXdfQFZlOR0UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a63812c43995693de7474bee7e2d7ccacb5af95a1b0cfbe71e8aa6067470fb2","last_reissued_at":"2026-07-05T07:43:59.274745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:59.274745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Haoyang Ling, Lingyao Li, Lizhou Fan, Wenyue Hua, Yongfeng Zhang","submitted_at":"2023-12-22T18:07:44Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14890","kind":"arxiv","version":4},"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/2312.14890/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":"2312.14890","created_at":"2026-07-05T07:43:59.274798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14890v4","created_at":"2026-07-05T07:43:59.274798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14890","created_at":"2026-07-05T07:43:59.274798+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJRYCLCDTFLJ","created_at":"2026-07-05T07:43:59.274798+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJRYCLCDTFLJHXTU","created_at":"2026-07-05T07:43:59.274798+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJRYCLCD","created_at":"2026-07-05T07:43:59.274798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS","json":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS.json","graph_json":"https://pith.science/api/pith-number/PJRYCLCDTFLJHXTUOS7OPYWXZS/graph.json","events_json":"https://pith.science/api/pith-number/PJRYCLCDTFLJHXTUOS7OPYWXZS/events.json","paper":"https://pith.science/paper/PJRYCLCD"},"agent_actions":{"view_html":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS","download_json":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS.json","view_paper":"https://pith.science/paper/PJRYCLCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14890&json=true","fetch_graph":"https://pith.science/api/pith-number/PJRYCLCDTFLJHXTUOS7OPYWXZS/graph.json","fetch_events":"https://pith.science/api/pith-number/PJRYCLCDTFLJHXTUOS7OPYWXZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS/action/storage_attestation","attest_author":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS/action/author_attestation","sign_citation":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS/action/citation_signature","submit_replication":"https://pith.science/pith/PJRYCLCDTFLJHXTUOS7OPYWXZS/action/replication_record"}},"created_at":"2026-07-05T07:43:59.274798+00:00","updated_at":"2026-07-05T07:43:59.274798+00:00"}