{"record": {"aliases": [], "artifacts": [{"id": "gh:cl1110goo-afk/oraclephys", "kind": "repo", "url": "https://github.com/cl1110goo-afk/oraclephys"}], "categories": ["Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "Evaluates LLM ranking of stories by inter-story drift and identification of the governing story for multi-story 2-D steel frames, with scoring by top-1 accuracy and Spearman correlation against oracle truth."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/cl1110goo-afk/oraclephys", "source": "claire_radar", "source_url": "https://github.com/cl1110goo-afk/oraclephys", "title": "OraclePhys"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:cl1110goo-afk/oraclephys", "modality": null, "name": "OraclePhys", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "true", "origin_record_id": "bm_oraclephys_04a2c150", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "7d04505b8f684d67bd48e384c75ff3d55a577ceee8ac3bc4a832c079c26e1f57", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://github.com/cl1110goo-afk/oraclephys"}, "publisher": null, "released": "2026-08-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:cl1110goo-afk/oraclephys", "source_url": "https://github.com/cl1110goo-afk/oraclephys"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-cl1110goo-afk-oraclephys", "source": "claire_radar", "source_benchmark_id": "github:cl1110goo-afk/oraclephys", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T16:48:55.714492Z", "githubRepo": "https://github.com/cl1110goo-afk/oraclephys", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-08-25T16:48:55.714492Z", "signalStatus": {"githubStars": {"observedAt": "2026-08-25T16:48:55.714492Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Niche structural mechanics domain limits broad interest, but a public GitHub release with evaluation code and an arXiv paper supports moderate attention.", "score": 42}, "capabilities": [], "confidence": "Medium", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "e17bd57cc6a73e934d5b3b84df3ce4d751ebec1c65bcdaeb14d5bf7987afca33", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "# OraclePhys An end-to-end instrument — **benchmark, dataset, training pipeline**", "canonicalNameSource": "official_readme", "decisionReason": "The GitHub repository provides a self-contained static benchmark with JSON prompts and oracle truth, evaluation code, and documented metrics.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates LLM ranking of stories by inter-story drift and identification of the governing story for multi-story 2-D steel frames, with scoring by top-1 accuracy and Spearman correlation against oracle truth.", "discoverySources": [{"id": "github:cl1110goo-afk/oraclephys", "type": "github", "url": "https://github.com/cl1110goo-afk/oraclephys"}], "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "oraclephys Benchmark, datasets and code for arXiv:2608.17162 benchmark finetuning llm reinforcement-learning structural-engineering # OraclePhys An end-to-end instrument — **benchmark, dataset, training pipeline** — for studying what fine-tuning objectives install in LLMs."}, "familyId": "bmf_467dce972bf6", "firstSeenAt": "2026-08-24", "heat": null, "id": "bm_oraclephys_04a2c150", "indexedAt": "2026-08-24T07:04:32.475961Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/cl1110goo-afk/oraclephys", "project": "https://arxiv.org/abs/2608.17162"}, "metrics": [], "motivation": "oraclephys Benchmark, datasets and code for arXiv:2608.17162 benchmark finetuning llm reinforcement-learning structural-engineering # OraclePhys An end-to-end instrument — **benchmark, dataset, training pipeline** — for studying what fine-tuning objectives install in LLMs.", "name": "OraclePhys", "oneLine": "Evaluates LLM ranking of stories by inter-story drift and identification of the governing story for multi-story 2-D steel frames, with scoring by top-1 accuracy and Spearman correlation against oracle truth.", "paperTitle": "oraclephys", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/cl1110goo-afk/oraclephys", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-24T07:04:32.475961Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": 0.462406015037594, "value": 1}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 73, "score": 48}, "method": "attention-ranking-v11", "rank": 73, "score": 48}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": 0.29526462395543174, "value": 1}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 266, "score": 39}, "method": "attention-ranking-v11", "rank": 266, "score": 39}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-23", "source": {"authors": ["cl1110goo-afk"], "categories": [], "id": "github:cl1110goo-afk/oraclephys", "title": "oraclephys", "type": "github", "url": "https://github.com/cl1110goo-afk/oraclephys"}, "sourceUpdatedAt": "2026-08-23T04:59:51Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides exact finite-element ground truth for structural mechanics, enabling controlled comparison of fine-tuning objectives without human labels or LLM judging."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
