{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.07038", "kind": "paper", "url": "https://arxiv.org/abs/2608.07038"}], "authors": ["Xiuwei Shang", "Li Hu", "Xiao Jiang", "Jieke Shi", "Junda He", "Zhou Yang", "Shaoyin Cheng", "Guoqiang Chen", "Weiming Zhang", "David Lo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07038", "source_url": "https://arxiv.org/abs/2608.07038"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "BinJudgeBench evaluates LLM-as-a-Judge for human-oriented binary reverse engineering, covering function name recovery, code summarization, and decompilation optimization, with correlation to human judgment as the metric."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07038", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07038", "title": "BinJudgeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.07038", "modality": null, "name": "BinJudgeBench", "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_binjudgebench_a8dd4ae5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "54ec78b1d2f6b415ef29c349dde8ad5d127f684375f56dabe52cbf99fa3607a7", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.07038"}, "publisher": null, "released": "2026-08-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07038", "source_url": "https://arxiv.org/abs/2608.07038"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07038", "source": "claire_radar", "source_benchmark_id": "2608.07038", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.07038", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "4b4ab63edcb579c568a05f86c94df18cc102240ad5090bbf7dac85476beb9f54", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BinJudgeBench evaluates LLM-as-a-Judge for human-oriented binary reverse engineering, covering function name recovery, code summarization, and decompilation optimization, with correlation to human judgment as the metric.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce BinJudgeBench, the first expert-annotated, reference-free evaluation benchmark based on multi-dimensional human judgment, where LLM-as-a-Judge achieves an average correlation of 63.20\\% with human judgment, outperforming traditional automated metrics at 35.04\\%."}, "familyId": "bmf_03c435b933bf", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_binjudgebench_a8dd4ae5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.07038", "paper": "https://arxiv.org/abs/2608.07038", "pdf": "https://arxiv.org/pdf/2608.07038", "project": null, "report": "https://arxiv.org/abs/2608.07038"}, "metrics": [], "motivation": "Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing the cognitive burden of reverse analysis and improving efficiency.", "name": "BinJudgeBench", "oneLine": "BinJudgeBench evaluates LLM-as-a-Judge for human-oriented binary reverse engineering, covering function name recovery, code summarization, and decompilation optimization, with correlation to human judgment as the metric.", "paperTitle": "Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.07038", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-07", "source": {"authors": ["Xiuwei Shang", "Li Hu", "Xiao Jiang", "Jieke Shi", "Junda He", "Zhou Yang", "Shaoyin Cheng", "Guoqiang Chen", "Weiming Zhang", "David Lo"], "categories": ["cs.SE", "cs.AI", "cs.CR"], "id": "2608.07038", "title": "Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07038"}, "sourceUpdatedAt": "2026-08-07T09:48:25Z", "topics": ["cs.SE"], "venueAttempts": [{"decisionRaw": "Accepted by the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.07038"}], "reviewStatus": "accepted", "venueName": "41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)"}], "whyItMatters": "Addresses the challenge of scalable evaluation for HOBRE, providing a reference-free alternative that correlates with human judgment better than traditional metrics."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
