{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.29632", "kind": "paper", "url": "https://arxiv.org/abs/2608.29632"}, {"id": "gh:kmsgk0/interactbench", "kind": "repo", "url": "https://github.com/kmsgk0/InteractBench"}], "authors": ["Jiaze Li", "Aocheng Shen", "Bing Liu", "Boyu Zhang", "Xiaoxuan Fan", "Qiankun Zhang", "Xianjun Deng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29632", "source_url": "https://arxiv.org/abs/2608.29632"}, "categories": ["Code & Software", "Code generation", "General AI", "cs.SE"], "description": {"en": "InteractBench evaluates LLM code generation on interactive competitive programming problems where solutions must query a judge to obtain hidden information under protocol constraints."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29632", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29632", "title": "InteractBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Huazhong University of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.29632", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.29632", "source_url": "https://openalex.org/W7204902238"}, "key": "claire-radar:2608.29632", "modality": null, "name": "InteractBench", "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": "true", "origin_record_id": "bm_interactbench_f60331ac", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "84e7b00311e042552be7f66cb06b37c8b7f7e97ee197f3295312ef2f70355e33", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.29632"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29632", "source_url": "https://arxiv.org/abs/2608.29632"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29632", "source": "claire_radar", "source_benchmark_id": "2608.29632", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/kmsgk0/InteractBench", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2608.29632", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Competitive programming and code generation benchmarks attract strong LLM evaluation interest, and the provided code and project page facilitate adoption.", "score": 75}, "capabilities": ["Code generation"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "3275bed36c9b1bfae15ddd56d4aca9829d73e2dc04f4eca6be44571b8a7d53dc", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce InteractBench, a benchmark comprising 322 high-quality interactive problems curated from Codeforces, AtCoder, IOI, and ICPC.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark provides an open-source evaluation harness with local interactors, supporting offline and reproducible scoring.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "InteractBench evaluates LLM code generation on interactive competitive programming problems where solutions must query a judge to obtain hidden information under protocol constraints.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce InteractBench, a benchmark comprising 322 high-quality interactive problems curated from Codeforces, AtCoder, IOI, and ICPC."}, "familyId": "bmf_59ef9e39fe17", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_interactbench_f60331ac", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": "https://github.com/kmsgk0/InteractBench", "data": null, "paper": "https://arxiv.org/abs/2608.29632", "pdf": "https://arxiv.org/pdf/2608.29632", "project": null, "report": "https://arxiv.org/abs/2608.29632"}, "metrics": [], "motivation": "Competitive programming is increasingly being used to evaluate the algorithmic reasoning capabilities of large language models (LLMs).", "name": "InteractBench", "oneLine": "InteractBench evaluates LLM code generation on interactive competitive programming problems where solutions must query a judge to obtain hidden information under protocol constraints.", "paperTitle": "InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ICML 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.29632", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ICML 2026", "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "publishers": [{"name": "Jiaze Li", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/kmsgk0/InteractBench"}], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.20647291500035556, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.2457137885628774, "value": 3}}, "confidence": "High", "coverage": 0.85, "rank": 109, "score": 26}, "method": "attention-ranking-v13", "rank": 109, "score": 26}, "90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.18868079669863877, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.2457137885628774, "value": 3}}, "confidence": "Medium", "coverage": 0.7, "rank": 250, "score": 29}, "method": "attention-ranking-v13", "rank": 250, "score": 29}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-30", "source": {"authors": ["Jiaze Li", "Aocheng Shen", "Bing Liu", "Boyu Zhang", "Xiaoxuan Fan", "Qiankun Zhang", "Xianjun Deng"], "categories": ["cs.SE", "cs.AI", "cs.CL"], "id": "2608.29632", "title": "InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29632"}, "sourceUpdatedAt": "2026-08-30T07:50:53Z", "topics": ["cs.SE"], "venueAttempts": [{"decisionRaw": "Accepted at ICML 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-02T05:21:06.631990Z", "rawValue": "Accepted at ICML 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.29632"}], "reviewStatus": "accepted", "venueName": "ICML 2026"}], "whyItMatters": "It addresses the gap in evaluating algorithmic reasoning under unrevealed information, a capability critical for real-world interactive tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
