{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3RMZBBWNSCAI2FKV7FYEQM3SNB","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":"280978558d4cf3cebcc1a2d3a7ba94f2fe15f632cd6dae9ab7f71dabbdb21e05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-23T11:43:00Z","title_canon_sha256":"28cb97089ddad76ce55ec3fe27677151a980c172756b8f86c7b83c48f628c68e"},"schema_version":"1.0","source":{"id":"2408.13001","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13001","created_at":"2026-07-05T11:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13001v2","created_at":"2026-07-05T11:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13001","created_at":"2026-07-05T11:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"3RMZBBWNSCAI","created_at":"2026-07-05T11:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"3RMZBBWNSCAI2FKV","created_at":"2026-07-05T11:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"3RMZBBWN","created_at":"2026-07-05T11:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:3780793faef76fb258df3ec7b6869ea21b1866da2314c4c5595a292c936fc6aa","target":"graph","created_at":"2026-07-05T11:04:18Z","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/2408.13001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code benchmarks such as HumanEval are widely adopted to evaluate Large Language Models' (LLMs) coding capabilities. However, there is an unignorable programming language bias in existing code benchmarks -- over 95% code generation benchmarks are dominated by Python, leaving the LLMs' capabilities in other programming languages such as Java and C/C++ unknown. Moreover, coding task bias is also crucial. Most benchmarks focus on code generation capability, while benchmarks for code reasoning (given input, reasoning output; and given output, reasoning input), an essential coding capability, are in","authors_text":"Ben He, Hongyu Lin, Jialun Cao, Le Sun, Ming Wen, Ruiyang Xu, Shing-Chi Cheung, Xianpei Han, Yaojie Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-23T11:43:00Z","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13001","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:e9e5d508f7c0de610947d139a02ba3c276c6227f8ba63eaf2f499a128528a3a5","target":"record","created_at":"2026-07-05T11:04:18Z","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":"280978558d4cf3cebcc1a2d3a7ba94f2fe15f632cd6dae9ab7f71dabbdb21e05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-23T11:43:00Z","title_canon_sha256":"28cb97089ddad76ce55ec3fe27677151a980c172756b8f86c7b83c48f628c68e"},"schema_version":"1.0","source":{"id":"2408.13001","kind":"arxiv","version":2}},"canonical_sha256":"dc599086cd90808d1555f970483372686b35747649a8ea878fb6193782afa961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc599086cd90808d1555f970483372686b35747649a8ea878fb6193782afa961","first_computed_at":"2026-07-05T11:04:18.360265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:18.360265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loyR7WDHHA5YPvfwKsIusEHekjP1qq1IF2nkBB087pRO38bidONGGziFENJAIOcigWBWC3bpNHcGbDSwXt+hCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:18.360817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13001","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9e5d508f7c0de610947d139a02ba3c276c6227f8ba63eaf2f499a128528a3a5","sha256:3780793faef76fb258df3ec7b6869ea21b1866da2314c4c5595a292c936fc6aa"],"state_sha256":"52dc426a50e91e62d17266e05af3a3336cdf0496ed5a742fb3250f29388f5409"}