{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXNRL2QCDSTJ2OSXBOAWFS22QD","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":"3d053dbda36284148cb7f524d40d5f680d3f17bff82034b3b931d8dc3013d7c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T18:47:28Z","title_canon_sha256":"55a4409cb432fb95441bd2ea2de6e2732ecb55b83435255640a4056ae0e19829"},"schema_version":"1.0","source":{"id":"2406.08587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08587","created_at":"2026-07-05T10:21:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08587v2","created_at":"2026-07-05T10:21:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08587","created_at":"2026-07-05T10:21:20Z"},{"alias_kind":"pith_short_12","alias_value":"LXNRL2QCDSTJ","created_at":"2026-07-05T10:21:20Z"},{"alias_kind":"pith_short_16","alias_value":"LXNRL2QCDSTJ2OSX","created_at":"2026-07-05T10:21:20Z"},{"alias_kind":"pith_short_8","alias_value":"LXNRL2QC","created_at":"2026-07-05T10:21:20Z"}],"graph_snapshots":[{"event_id":"sha256:de8c53e39ae4003f23f6ad14a497771415f6528d3c10db47d33f13ab15406b89","target":"graph","created_at":"2026-07-05T10:21:20Z","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/2406.08587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated significant potential in advancing various fields of research and society. However, the current community of LLMs overly focuses on benchmarks for analyzing specific foundational skills (e.g. mathematics and code generation), neglecting an all-round evaluation of the computer science field. To bridge this gap, we introduce CS-Bench, the first multilingual (English, Chinese, French, German) benchmark dedicated to evaluating the performance of LLMs in computer science. CS-Bench comprises approximately 10K meticulously curated test samples, covering ","authors_text":"Bin Liang, Dayuan Fu, Guanting Dong, Huangxuan Wu, Jianing Yu, Muxi Diao, Qiuna Tan, Runqi Qiao, Weihao Zeng, Weiran Xu, Xiaoshuai Song, Yejie Wang, Yujia Fu, Zhengyang Wang, Zhexu Wang, Zhuoma Gongque","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T18:47:28Z","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08587","kind":"arxiv","version":2},"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":"sha256:5afb9f877a293af0663d4e31c03f33b4cff3c47ce62c1ccf7f602f06bee05851","target":"record","created_at":"2026-07-05T10:21:20Z","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":"3d053dbda36284148cb7f524d40d5f680d3f17bff82034b3b931d8dc3013d7c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T18:47:28Z","title_canon_sha256":"55a4409cb432fb95441bd2ea2de6e2732ecb55b83435255640a4056ae0e19829"},"schema_version":"1.0","source":{"id":"2406.08587","kind":"arxiv","version":2}},"canonical_sha256":"5ddb15ea021ca69d3a570b8162cb5a80c01704e3c1094a331213e66ac291536a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ddb15ea021ca69d3a570b8162cb5a80c01704e3c1094a331213e66ac291536a","first_computed_at":"2026-07-05T10:21:20.712543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:20.712543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OVpoPTIWOuwwqYy1HgdaXadz3urapsScUnYpiSOfR0GPTqO3eXHFTbyTvAoCd2akbjL3ZXXH3NCOLyx24SzMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:20.713039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5afb9f877a293af0663d4e31c03f33b4cff3c47ce62c1ccf7f602f06bee05851","sha256:de8c53e39ae4003f23f6ad14a497771415f6528d3c10db47d33f13ab15406b89"],"state_sha256":"0f3ba4bdda4373a800de0a4c16bc53a115d6cb51fa9927827acbdbad58836601"}