{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.17905", "kind": "paper", "url": "https://arxiv.org/abs/2606.17905"}, {"id": "gh:0328zpx/chlogic", "kind": "repo", "url": "https://github.com/0328zpx/ChLogic"}], "authors": ["Peixian Zhou", "Yuxu Chen", "Chaorui Zhang", "Wei Han", "Bo Bai", "Xueyan Niu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.17905", "source_url": "https://arxiv.org/abs/2606.17905"}, "categories": ["General AI", "Reasoning", "Robustness", "Safety & Trustworthiness"], "description": {"en": "ChLogic is an English–Chinese aligned benchmark for evaluating logical reasoning robustness across surface realizations. It includes 3,000 general, 2,000 difficult, and 1,500 Chinese-only items derived from formal logical templates, with each aligned item pairing one English reference with five Chinese variants."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.17905", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.17905", "title": "ChLogic"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Sichuan University", "Sichuan University of Science and Engineering", "Huawei Technologies (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.17905", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.17905", "source_url": "https://openalex.org/W7165024533"}, "key": "claire-radar:2606.17905", "modality": null, "name": "ChLogic", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_chlogic_3b9dd8db", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "68d4f31a2eda19dd053ec41daa24271673aee581a20e45d6c9266beb1bb378cd", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.17905"}, "publisher": null, "released": "2026-06-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.17905", "source_url": "https://arxiv.org/abs/2606.17905"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-17905", "source": "claire_radar", "source_benchmark_id": "2606.17905", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/0328zpx/ChLogic", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 8, "hfPaperUrl": "https://huggingface.co/papers/2606.17905", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning", "Robustness"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d65f67ca676a6bafd2cc6a30259edab1bf36a755ab003b5a50f60c1c4e3b6182", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ChLogic is an English–Chinese aligned benchmark for evaluating logical reasoning robustness across surface realizations. It includes 3,000 general, 2,000 difficult, and 1,500 Chinese-only items derived from formal logical templates, with each aligned item pairing one English reference with five Chinese variants.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce ChLogic, an English--Chinese aligned benchmark that tests whether models preserve logical reasoning performance when the same latent logical structure is expressed in English and diverse Chinese surface realizations."}, "familyId": "bmf_760dd213a7b3", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/0328zpx/ChLogic", "url": "https://github.com/0328zpx/ChLogic"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/0328zpx/ChLogic", "url": "https://huggingface.co/papers/2606.17905"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/0328zpx/ChLogic", "url": "https://huggingface.co/api/papers/2606.17905"}], "scope": "benchmark_repo", "url": "https://github.com/0328zpx/ChLogic", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_chlogic_3b9dd8db", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/0328zpx/ChLogic", "data": null, "hfPaper": "https://huggingface.co/papers/2606.17905", "paper": "https://arxiv.org/abs/2606.17905", "pdf": "https://arxiv.org/pdf/2606.17905", "project": null, "report": "https://arxiv.org/abs/2606.17905"}, "metrics": [], "motivation": "Large language models perform increasingly well on standardized logical reasoning benchmarks, but whether this ability remains robust beyond English is unclear.", "name": "ChLogic", "oneLine": "ChLogic is an English–Chinese aligned benchmark for evaluating logical reasoning robustness across surface realizations. It includes 3,000 general, 2,000 difficult, and 1,500 Chinese-only items derived from formal logical templates, with each aligned item pairing one English reference with five Chinese variants.", "paperTitle": "ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.17905", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ChLogic team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/0328zpx/ChLogic"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-16", "source": {"authors": ["Peixian Zhou", "Yuxu Chen", "Chaorui Zhang", "Wei Han", "Bo Bai", "Xueyan Niu"], "categories": ["cs.CL"], "id": "2606.17905", "title": "ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.17905"}, "sourceUpdatedAt": "2026-06-16T13:28:57Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing logical reasoning benchmarks focus on English, so it is unclear whether models retain performance when the same logical structure is expressed in Chinese. ChLogic provides a cross-lingual stress test, helping identify language-specific gaps and translation artifacts that affect multilingual reasoning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
