{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TCJ7R5XBIPXG4ZPABAU5B646GO","short_pith_number":"pith:TCJ7R5XB","schema_version":"1.0","canonical_sha256":"9893f8f6e143ee6e65e00829d0fb9e338110f455330680b3c5ddae682228c056","source":{"kind":"arxiv","id":"2501.14705","version":1},"attestation_state":"computed","paper":{"title":"The Karp Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Conner Olsen, Daniel Reichman, Eamon Worden, Mason DiCicco, Neil Heffernan, Nikhil Gangaram","submitted_at":"2025-01-24T18:30:19Z","abstract_excerpt":"Understanding the mathematical reasoning capabilities of Large Language Models (LLMs) is a central topic in the study of artificial intelligence. This new domain necessitates the creation of datasets of reasoning tasks for both training and benchmarking the performance of LLMs. To this end, we introduce the Karp dataset: The first dataset composed of detailed proofs of NP-completeness reductions. The reductions vary in difficulty, ranging from simple exercises of undergraduate courses to more challenging reductions from academic papers. We compare the performance of state-of-the-art models on "},"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":"2501.14705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T18:30:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4587c34fb4c2686f8d89b61b18bd9ba21fe1b9c9e6e6c8e2d9ed83ae9dbfe29a","abstract_canon_sha256":"bff58522ed2d7c5246ee6faad36051fe3fa17dd72c00ad2b5d11f7a9f1b9c041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:04.508652Z","signature_b64":"mjeIha30kQJ1mncZuRzGjQ6B8CD46UXzIvIKvfQHlANClUu1guRu2/b9BWpXuL425bVZlkGTi6+SEkapXLZDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9893f8f6e143ee6e65e00829d0fb9e338110f455330680b3c5ddae682228c056","last_reissued_at":"2026-07-05T10:05:04.508094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:04.508094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Karp Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Conner Olsen, Daniel Reichman, Eamon Worden, Mason DiCicco, Neil Heffernan, Nikhil Gangaram","submitted_at":"2025-01-24T18:30:19Z","abstract_excerpt":"Understanding the mathematical reasoning capabilities of Large Language Models (LLMs) is a central topic in the study of artificial intelligence. This new domain necessitates the creation of datasets of reasoning tasks for both training and benchmarking the performance of LLMs. To this end, we introduce the Karp dataset: The first dataset composed of detailed proofs of NP-completeness reductions. The reductions vary in difficulty, ranging from simple exercises of undergraduate courses to more challenging reductions from academic papers. We compare the performance of state-of-the-art models on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14705","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/2501.14705/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":"2501.14705","created_at":"2026-07-05T10:05:04.508154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14705v1","created_at":"2026-07-05T10:05:04.508154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14705","created_at":"2026-07-05T10:05:04.508154+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCJ7R5XBIPXG","created_at":"2026-07-05T10:05:04.508154+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCJ7R5XBIPXG4ZPA","created_at":"2026-07-05T10:05:04.508154+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCJ7R5XB","created_at":"2026-07-05T10:05:04.508154+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/TCJ7R5XBIPXG4ZPABAU5B646GO","json":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO.json","graph_json":"https://pith.science/api/pith-number/TCJ7R5XBIPXG4ZPABAU5B646GO/graph.json","events_json":"https://pith.science/api/pith-number/TCJ7R5XBIPXG4ZPABAU5B646GO/events.json","paper":"https://pith.science/paper/TCJ7R5XB"},"agent_actions":{"view_html":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO","download_json":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO.json","view_paper":"https://pith.science/paper/TCJ7R5XB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14705&json=true","fetch_graph":"https://pith.science/api/pith-number/TCJ7R5XBIPXG4ZPABAU5B646GO/graph.json","fetch_events":"https://pith.science/api/pith-number/TCJ7R5XBIPXG4ZPABAU5B646GO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO/action/storage_attestation","attest_author":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO/action/author_attestation","sign_citation":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO/action/citation_signature","submit_replication":"https://pith.science/pith/TCJ7R5XBIPXG4ZPABAU5B646GO/action/replication_record"}},"created_at":"2026-07-05T10:05:04.508154+00:00","updated_at":"2026-07-05T10:05:04.508154+00:00"}