{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENOWUMZPPFZG5AGUG4454B7GZO","short_pith_number":"pith:ENOWUMZP","schema_version":"1.0","canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","source":{"kind":"arxiv","id":"2503.05891","version":4},"attestation_state":"computed","paper":{"title":"MastermindEval: A Simple But Scalable Reasoning Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Fabio Barth, Jonas Golde, Patrick Haller","submitted_at":"2025-03-07T19:24:59Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have led to remarkable performance across a wide range of language understanding and mathematical tasks. As a result, increasing attention has been given to assessing the true reasoning capabilities of LLMs, driving research into commonsense, numerical, logical, and qualitative reasoning. However, with the rapid progress of reasoning-focused models such as OpenAI's o1 and DeepSeek's R1, there has been a growing demand for reasoning benchmarks that can keep pace with ongoing model developments. In this paper, we introduce MastermindEval, a sim"},"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":"2503.05891","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T19:24:59Z","cross_cats_sorted":[],"title_canon_sha256":"bb44f3bb23df00827d7741554b9db7c9f3a805c872da2f0d8d02acf0a2a223f9","abstract_canon_sha256":"a9e0e188740f7b780bddbf1537bf758ca85e8ed64fee7c5f4d30a114ba8167c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:32.627481Z","signature_b64":"2rOigBvoortsY/HsF2eOac8E0DMhGY816heiL7Mf30q7WcpLFOTxcwNkEg60++/kf6dH2qm6OArOeZ2hF0ALDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","last_reissued_at":"2026-07-05T10:30:32.626583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:32.626583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MastermindEval: A Simple But Scalable Reasoning Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Fabio Barth, Jonas Golde, Patrick Haller","submitted_at":"2025-03-07T19:24:59Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have led to remarkable performance across a wide range of language understanding and mathematical tasks. As a result, increasing attention has been given to assessing the true reasoning capabilities of LLMs, driving research into commonsense, numerical, logical, and qualitative reasoning. However, with the rapid progress of reasoning-focused models such as OpenAI's o1 and DeepSeek's R1, there has been a growing demand for reasoning benchmarks that can keep pace with ongoing model developments. In this paper, we introduce MastermindEval, a sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05891","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/2503.05891/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":"2503.05891","created_at":"2026-07-05T10:30:32.626714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05891v4","created_at":"2026-07-05T10:30:32.626714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05891","created_at":"2026-07-05T10:30:32.626714+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENOWUMZPPFZG","created_at":"2026-07-05T10:30:32.626714+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENOWUMZPPFZG5AGU","created_at":"2026-07-05T10:30:32.626714+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENOWUMZP","created_at":"2026-07-05T10:30:32.626714+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/ENOWUMZPPFZG5AGUG4454B7GZO","json":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO.json","graph_json":"https://pith.science/api/pith-number/ENOWUMZPPFZG5AGUG4454B7GZO/graph.json","events_json":"https://pith.science/api/pith-number/ENOWUMZPPFZG5AGUG4454B7GZO/events.json","paper":"https://pith.science/paper/ENOWUMZP"},"agent_actions":{"view_html":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO","download_json":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO.json","view_paper":"https://pith.science/paper/ENOWUMZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05891&json=true","fetch_graph":"https://pith.science/api/pith-number/ENOWUMZPPFZG5AGUG4454B7GZO/graph.json","fetch_events":"https://pith.science/api/pith-number/ENOWUMZPPFZG5AGUG4454B7GZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/action/storage_attestation","attest_author":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/action/author_attestation","sign_citation":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/action/citation_signature","submit_replication":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/action/replication_record"}},"created_at":"2026-07-05T10:30:32.626714+00:00","updated_at":"2026-07-05T10:30:32.626714+00:00"}