{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBAGG2DT3QPTFE7CPTVCZGH3UI","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":"8ae0ac4b55598dc50339a925645ebc68a9907fe617a5a1fc51c848bca56ffa19","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T19:31:03Z","title_canon_sha256":"bfbd8cfa4b5ca94e7ef2b1c4c3c2a3b604fca90c10d86bb7469d0e3fffbc19b4"},"schema_version":"1.0","source":{"id":"2409.02257","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02257","created_at":"2026-07-05T09:21:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02257v3","created_at":"2026-07-05T09:21:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02257","created_at":"2026-07-05T09:21:07Z"},{"alias_kind":"pith_short_12","alias_value":"RBAGG2DT3QPT","created_at":"2026-07-05T09:21:07Z"},{"alias_kind":"pith_short_16","alias_value":"RBAGG2DT3QPTFE7C","created_at":"2026-07-05T09:21:07Z"},{"alias_kind":"pith_short_8","alias_value":"RBAGG2DT","created_at":"2026-07-05T09:21:07Z"}],"graph_snapshots":[{"event_id":"sha256:93a0d8d795b0ddb4c7d4707da743e378e7db3e4d5bbeaf6c9ff370a70cb34a36","target":"graph","created_at":"2026-07-05T09:21:07Z","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/2409.02257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing benchmarks for large language models (LLMs) increasingly struggle to differentiate between top-performing models, underscoring the need for more challenging evaluation frameworks. We introduce MMLU-Pro+, an enhanced benchmark building upon MMLU-Pro to assess shortcut learning and higher-order reasoning in LLMs. By incorporating questions with multiple correct answers across diverse domains, MMLU-Pro+ tests LLMs' ability to engage in complex reasoning and resist simplistic problem-solving strategies. Our results show that MMLU-Pro+ maintains MMLU-Pro's difficulty while providing a more","authors_text":"Aliasgahr Khani, Amir Khasahmadi, Saeid Asgari Taghanaki","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T19:31:03Z","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02257","kind":"arxiv","version":3},"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":"sha256:5988e9eb5ac855b0b0c5b8e391677b3d739770a04e1d5df0421a9baf2bdbf5cb","target":"record","created_at":"2026-07-05T09:21:07Z","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":"8ae0ac4b55598dc50339a925645ebc68a9907fe617a5a1fc51c848bca56ffa19","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T19:31:03Z","title_canon_sha256":"bfbd8cfa4b5ca94e7ef2b1c4c3c2a3b604fca90c10d86bb7469d0e3fffbc19b4"},"schema_version":"1.0","source":{"id":"2409.02257","kind":"arxiv","version":3}},"canonical_sha256":"8840636873dc1f3293e27cea2c98fba2296f9e9544042a1388052416b761b8a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8840636873dc1f3293e27cea2c98fba2296f9e9544042a1388052416b761b8a1","first_computed_at":"2026-07-05T09:21:07.309585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:07.309585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OU9NbK2WhxdHISPLm1v+8vKSeTKnXu2u/oDdwfc3Wz6B1T6R7Ge99L4pky5j1pS3wPfpdYqh4qmwhH3aOa9nBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:07.310049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02257","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5988e9eb5ac855b0b0c5b8e391677b3d739770a04e1d5df0421a9baf2bdbf5cb","sha256:93a0d8d795b0ddb4c7d4707da743e378e7db3e4d5bbeaf6c9ff370a70cb34a36"],"state_sha256":"dc31ddd544d3a0bdf254dcc27991e2142f2ac535a96479280b02ab43e1218592"}