{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FHNSN6WBQ2H6NSTALFSVM6DY6C","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":"11bfc0bac101c11a707a8342a6193d8ff49c7d401582a39aad503a7db50907f3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-26T14:08:17Z","title_canon_sha256":"8d024427088c758d846187e52b49a61469deb6c6df0caff6322547a75b73362c"},"schema_version":"1.0","source":{"id":"2502.19149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19149","created_at":"2026-07-05T10:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19149v1","created_at":"2026-07-05T10:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19149","created_at":"2026-07-05T10:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"FHNSN6WBQ2H6","created_at":"2026-07-05T10:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"FHNSN6WBQ2H6NSTA","created_at":"2026-07-05T10:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"FHNSN6WB","created_at":"2026-07-05T10:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:f496343ba99f5be8e6e6ccf510f6b7ec500957633491ed0083145e0169740d7b","target":"graph","created_at":"2026-07-05T10:20:27Z","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/2502.19149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing code generation benchmarks for Large Language Models (LLMs) such as HumanEval and MBPP are designed to study LLMs' end-to-end performance, where the benchmarks feed a problem description in natural language as input and examine the generated code in specific programming languages. However, the evaluation scores revealed in this way provide a little hint as to the bottleneck of the code generation -- whether LLMs are struggling with their problem-solving capability or language-coding capability. To answer this question, we construct PseudoEval, a multilingual code generation benchmark ","authors_text":"Hau Ching Lo, Jialun Cao, Jiarong Wu, Shing-Chi Cheung, Songqiang Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-26T14:08:17Z","title":"Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19149","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":"sha256:955105937048cef2dbf521133560c41dd7734ca874bc6d109fcbdec9f514ae18","target":"record","created_at":"2026-07-05T10:20:27Z","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":"11bfc0bac101c11a707a8342a6193d8ff49c7d401582a39aad503a7db50907f3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-26T14:08:17Z","title_canon_sha256":"8d024427088c758d846187e52b49a61469deb6c6df0caff6322547a75b73362c"},"schema_version":"1.0","source":{"id":"2502.19149","kind":"arxiv","version":1}},"canonical_sha256":"29db26fac1868fe6ca605965567878f0a5752558c7033a4ceaeaf8ab3c23944a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29db26fac1868fe6ca605965567878f0a5752558c7033a4ceaeaf8ab3c23944a","first_computed_at":"2026-07-05T10:20:27.759568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:27.759568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yhFrlZ9GOgQdTcNic2l5b9wXuNXEpk+Skh7Nn67cHNK4vwaC/xYqfD9wUgbz0gCgnvNjs8dcNy+Yf2UlP2rNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:27.760094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:955105937048cef2dbf521133560c41dd7734ca874bc6d109fcbdec9f514ae18","sha256:f496343ba99f5be8e6e6ccf510f6b7ec500957633491ed0083145e0169740d7b"],"state_sha256":"c715a3e82f82ac51a94aa713c25f4fd99e96bf61a18bcd00efa4bcdaff643189"}