{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ENOWUMZPPFZG5AGUG4454B7GZO","short_pith_number":"pith:ENOWUMZP","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"},"canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","source":{"kind":"arxiv","id":"2503.05891","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05891","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05891v4","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05891","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"ENOWUMZPPFZG","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"ENOWUMZPPFZG5AGU","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"ENOWUMZP","created_at":"2026-07-05T10:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ENOWUMZPPFZG5AGUG4454B7GZO","target":"record","payload":{"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"},"canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","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"},"source_kind":"arxiv","source_id":"2503.05891","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NU8h1Kk/uOrAN2Ax+Tp3sFp/2zM4PrPQkFCHyPxIRr6fB0ILjgzEyaDVDAl1czbZRFvUFnlZ/Tz1hZ2gi5uYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:15:40.463814Z"},"content_sha256":"19947dcd8d79dbb7ab9ef439b3f92b3109082328fcf21565c11ac888aff4aa8c","schema_version":"1.0","event_id":"sha256:19947dcd8d79dbb7ab9ef439b3f92b3109082328fcf21565c11ac888aff4aa8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ENOWUMZPPFZG5AGUG4454B7GZO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrV2d+wkijLmE7Khr7JzpQjNibu2HuP/YRycFzcnqSIkEMfMY1dOGmNDsrjLG+i7gFumQ28Wj7c/qUioHUADAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:15:40.464190Z"},"content_sha256":"6ff683ce5bccbc8879a7a4acdf66d51fca1ad4515a29cc6505ee68502fd2791c","schema_version":"1.0","event_id":"sha256:6ff683ce5bccbc8879a7a4acdf66d51fca1ad4515a29cc6505ee68502fd2791c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/bundle.json","state_url":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENOWUMZPPFZG5AGUG4454B7GZO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T07:15:40Z","links":{"resolver":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO","bundle":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/bundle.json","state":"https://pith.science/pith/ENOWUMZPPFZG5AGUG4454B7GZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENOWUMZPPFZG5AGUG4454B7GZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ENOWUMZPPFZG5AGUG4454B7GZO","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":"a9e0e188740f7b780bddbf1537bf758ca85e8ed64fee7c5f4d30a114ba8167c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T19:24:59Z","title_canon_sha256":"bb44f3bb23df00827d7741554b9db7c9f3a805c872da2f0d8d02acf0a2a223f9"},"schema_version":"1.0","source":{"id":"2503.05891","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05891","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05891v4","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05891","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"ENOWUMZPPFZG","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"ENOWUMZPPFZG5AGU","created_at":"2026-07-05T10:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"ENOWUMZP","created_at":"2026-07-05T10:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:6ff683ce5bccbc8879a7a4acdf66d51fca1ad4515a29cc6505ee68502fd2791c","target":"graph","created_at":"2026-07-05T10:30:32Z","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/2503.05891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Akbik, Fabio Barth, Jonas Golde, Patrick Haller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T19:24:59Z","title":"MastermindEval: A Simple But Scalable Reasoning Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05891","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":"sha256:19947dcd8d79dbb7ab9ef439b3f92b3109082328fcf21565c11ac888aff4aa8c","target":"record","created_at":"2026-07-05T10:30:32Z","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":"a9e0e188740f7b780bddbf1537bf758ca85e8ed64fee7c5f4d30a114ba8167c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T19:24:59Z","title_canon_sha256":"bb44f3bb23df00827d7741554b9db7c9f3a805c872da2f0d8d02acf0a2a223f9"},"schema_version":"1.0","source":{"id":"2503.05891","kind":"arxiv","version":4}},"canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"235d6a332f79726e80d43739de07e6cb9e42ac5f95fa2fd6e7756f452da9433d","first_computed_at":"2026-07-05T10:30:32.626583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:32.626583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rOigBvoortsY/HsF2eOac8E0DMhGY816heiL7Mf30q7WcpLFOTxcwNkEg60++/kf6dH2qm6OArOeZ2hF0ALDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:32.627481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05891","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19947dcd8d79dbb7ab9ef439b3f92b3109082328fcf21565c11ac888aff4aa8c","sha256:6ff683ce5bccbc8879a7a4acdf66d51fca1ad4515a29cc6505ee68502fd2791c"],"state_sha256":"d522c027f3ca24b8001ff50ef29dbdd3251b5e0f809b743b7466f8554c804542"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"42hI5uojGTuvP7mr4owCtCGvBKODzuR0xnmXXB6tPIKrgW0nIIwNYEqSzplqdFNysWP3klAsW/lN4Ms72JtgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:15:40.466829Z","bundle_sha256":"7270d1b5ea34217378a25a8506822bda2c6bbd8ec5aa1132003443de76f5dd2d"}}