{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.00355", "kind": "paper", "url": "https://arxiv.org/abs/2608.00355"}, {"id": "gh:harvenstar/curveshift", "kind": "repo", "url": "https://github.com/harvenstar/CurveShift"}], "authors": ["Hanwen Xing", "Pengyun Wang", "BingXu Meng", "Kumail Alhamoud", "Xiang Li", "Jicheng Wang", "Xin Yu", "Xinyang Han", "Xiaomin Li", "Philip Torr", "Yuexing Hao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.00355", "source_url": "https://arxiv.org/abs/2608.00355"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "CurveShift analyzes progress on LiveCodeBench, releasing a difficulty panel of 66 models and 1,055 problems."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.00355", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.00355", "title": "LiveCodeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Southern California", "University of Chicago", "Massachusetts Institute of Technology", "Harvard University", "Stanford University", "University of California, Davis", "Pennsylvania State University", "University of California, Berkeley", "University of Oxford"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.00355", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.00355", "source_url": "https://openalex.org/W7172412367"}, "key": "claire-radar:2608.00355", "modality": null, "name": "LiveCodeBench", "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_livecodebench_fa145f1d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ec7194d821fe278f0bc5c300c8faa89cec801b286a791d8abd62e77eef1abe02", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.00355"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.00355", "source_url": "https://arxiv.org/abs/2608.00355"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-00355", "source": "claire_radar", "source_benchmark_id": "2608.00355", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/harvenstar/CurveShift", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.00355", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "ae80d13489ec097ddf97a43759b4f16ca26250966a72f9a4e69162f9ad4704d9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CurveShift analyzes progress on LiveCodeBench, releasing a difficulty panel of 66 models and 1,055 problems.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We release the LiveCodeBench Difficulty Panel (66 dated models x 1,055 problems) and our analysis code."}, "familyId": "bmf_b33aa0adf0e0", "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/harvenstar/CurveShift", "url": "https://github.com/harvenstar/CurveShift"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/harvenstar/CurveShift", "url": "https://huggingface.co/papers/2608.00355"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/harvenstar/CurveShift", "url": "https://arxiv.org/abs/2608.00355"}], "scope": "project_repo", "url": "https://github.com/harvenstar/CurveShift", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_livecodebench_fa145f1d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/harvenstar/CurveShift", "data": null, "hfPaper": "https://huggingface.co/papers/2608.00355", "paper": "https://arxiv.org/abs/2608.00355", "pdf": "https://arxiv.org/pdf/2608.00355", "project": null, "report": "https://arxiv.org/abs/2608.00355"}, "metrics": [], "motivation": "Progress in large language models is often summarized using a single scalar measure, such as a time horizon, a latent ability estimate, or an aggregate benchmark score.", "name": "LiveCodeBench", "oneLine": "CurveShift analyzes progress on LiveCodeBench, releasing a difficulty panel of 66 models and 1,055 problems.", "paperTitle": "CurveShift: Is Agent Progress Scalar? Separating Level from Shape", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.00355", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 343, "score": 28}, "method": "attention-ranking-v13", "rank": 343, "score": 28}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-31", "source": {"authors": ["Hanwen Xing", "Pengyun Wang", "BingXu Meng", "Kumail Alhamoud", "Xiang Li", "Jicheng Wang", "Xin Yu", "Xinyang Han", "Xiaomin Li", "Philip Torr", "Yuexing Hao"], "categories": ["cs.CL", "cs.LG"], "id": "2608.00355", "title": "CurveShift: Is Agent Progress Scalar? Separating Level from Shape", "type": "arxiv", "url": "https://arxiv.org/abs/2608.00355"}, "sourceUpdatedAt": "2026-07-31T23:58:25Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Provides insights into whether progress is scalar or shaped by task difficulty, but does not define a new evaluation benchmark."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
