{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OHRCXXQJNCX7MO4JN2OAV3RPDI","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":"e1a1fb1c0d21619c9cfe35754b3ca12597d6f996aa9029ec996d87a85b194034","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T15:41:51Z","title_canon_sha256":"7cd21c6df1b48f04cd3347ae4de820a3c5a53b408f9abd4bae7bb80c353cf54b"},"schema_version":"1.0","source":{"id":"2502.16268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16268","created_at":"2026-07-05T10:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16268v1","created_at":"2026-07-05T10:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16268","created_at":"2026-07-05T10:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"OHRCXXQJNCX7","created_at":"2026-07-05T10:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"OHRCXXQJNCX7MO4J","created_at":"2026-07-05T10:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"OHRCXXQJ","created_at":"2026-07-05T10:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:d86c1f200dfcbc28f234826c00d241f542181a884d23f672ef1df34533d427fe","target":"graph","created_at":"2026-07-05T10:18:24Z","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/2502.16268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challenges, we introduce ThinkBench, a novel evaluation framework designed to evaluate LLMs' reasoning capability robustly. ThinkBench proposes a dynamic data generation method for constructing out-of-distribution (OOD) datasets and offers an OOD dataset that contains 2,912 samples drawn from reasoning tasks. ThinkBench unifies the evaluation of reasoning models and non-reasoning models. We evaluate 16 LLMs and 4 PRMs under ","authors_text":"Jun Wang, Kun Shao, Leyang Cui, Linyi Yang, Qingcheng Zeng, Shuang Chen, Shulin Huang, Weinan Zhang, Yan Song, Ying Wen, Yue Zhang, Ziyu Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T15:41:51Z","title":"ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16268","kind":"arxiv","version":1},"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:dcd1588bb988643e8ce075e2dc6ccad110dcb0f46330870ab65b17fba44b9ca1","target":"record","created_at":"2026-07-05T10:18:24Z","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":"e1a1fb1c0d21619c9cfe35754b3ca12597d6f996aa9029ec996d87a85b194034","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-22T15:41:51Z","title_canon_sha256":"7cd21c6df1b48f04cd3347ae4de820a3c5a53b408f9abd4bae7bb80c353cf54b"},"schema_version":"1.0","source":{"id":"2502.16268","kind":"arxiv","version":1}},"canonical_sha256":"71e22bde0968aff63b896e9c0aee2f1a0f536f45943012c306b329088e26addf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71e22bde0968aff63b896e9c0aee2f1a0f536f45943012c306b329088e26addf","first_computed_at":"2026-07-05T10:18:24.006083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:24.006083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QRz8JeTewpVZkPC57Xy5FteF5IkiFSIMhNpeffO/Lk08ysesoA04n8J8CbVpA4qR+Ljn5WhmwSAZ0JyZ8MjTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:24.006577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcd1588bb988643e8ce075e2dc6ccad110dcb0f46330870ab65b17fba44b9ca1","sha256:d86c1f200dfcbc28f234826c00d241f542181a884d23f672ef1df34533d427fe"],"state_sha256":"e72d8184c60305c5663ed22c33caecba9e38793bb83dfcb3d4b5ad675be42183"}