{"record": {"aliases": [], "artifacts": [{"id": "gh:supreethbare/decision-model-bench", "kind": "repo", "url": "https://github.com/supreethbare/decision-model-bench"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "The repository compares typed decision models on several enterprise tasks, but it is a one-off harness without a formal benchmark name or clear external submission mechanism."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/supreethbare/decision-model-bench", "source": "claire_radar", "source_url": "https://github.com/supreethbare/decision-model-bench", "title": "decision-model-bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:supreethbare/decision-model-bench", "modality": null, "name": "decision-model-bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "false", "origin_record_id": "bm_decision-model-bench_23575868", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "c86a6bfe31aea8a1609ccda36cfc1f63d03d2b350ae83f98aa1f8fb7de5d2e72", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-27T10:09:07.308450Z", "source_url": "https://github.com/supreethbare/decision-model-bench"}, "publisher": null, "released": "2026-09-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:supreethbare/decision-model-bench", "source_url": "https://github.com/supreethbare/decision-model-bench"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-supreethbare-decision-model-bench", "source": "claire_radar", "source_benchmark_id": "github:supreethbare/decision-model-bench", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/supreethbare/decision-model-bench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "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": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The enterprise task focus and multiple model comparisons may draw some interest, but the lack of benchmark framing limits broad appeal.", "score": 30}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-27T10:09:07.308450Z", "inputHash": "993576fc99ea9f9879cac1c2c777c1a3f9e940ea9cee6dc7050f92e9a353c2f2", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# decision-model-bench Benchmark harness comparing **typed decision models** on four enterprise tasks, with per-case predictions committed as evidence.", "canonicalNameSource": "official_readme", "decisionReason": "The project appears to be a comparison experiment with fixed datasets and models, not a benchmark with a reusable scoring contract.", "evaluationEvidence": {"reuse": "```sh python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt ./bench/fetch_raw.sh # download the public datasets into bench/raw/ python bench/build_datasets.py # rebuild bench/data/ (seed 42; should match what's committed) ```", "scoring": "**Accuracy** - exact match against the gold label. A declined answer counts as wrong.", "task": "Benchmark harness comparing **typed decision models** on four enterprise tasks, with per-case predictions committed as evidence."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-27T10:09:07.308450Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "The repository compares typed decision models on several enterprise tasks, but it is a one-off harness without a formal benchmark name or clear external submission mechanism.", "discoverySources": [{"id": "github:supreethbare/decision-model-bench", "type": "github", "url": "https://github.com/supreethbare/decision-model-bench"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "decision-model-bench Benchmarking typed decision models (Jev, Open-Jev, Needle 3) as a routing layer in front of LLMs benchmark calibration classification intent-classification llm structured-output tool-calling # decision-model-bench Benchmark harness comparing **typed decision models** on four enterprise tasks, with per-case predictions committed as evidence."}, "familyId": "bmf_28fb9b6e64a0", "firstSeenAt": "2026-09-24", "heat": null, "id": "bm_decision-model-bench_23575868", "indexedAt": "2026-09-24T06:25:40.629929Z", "industrySectors": [], "links": {"code": "https://github.com/supreethbare/decision-model-bench"}, "metrics": [], "motivation": "decision-model-bench Benchmarking typed decision models (Jev, Open-Jev, Needle 3) as a routing layer in front of LLMs benchmark calibration classification intent-classification llm structured-output tool-calling # decision-model-bench Benchmark harness comparing **typed decision models** on four enterprise tasks, with per-case predictions committed as evidence.", "name": "decision-model-bench", "oneLine": "The repository compares typed decision models on several enterprise tasks, but it is a one-off harness without a formal benchmark name or clear external submission mechanism.", "paperTitle": "decision-model-bench", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/supreethbare/decision-model-bench", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-24T06:25:40.629929Z"}, "publications": [], "ranking": {"30d": {"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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 149, "score": 23}, "method": "attention-ranking-v13", "rank": 149, "score": 23}, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 413, "score": 23}, "method": "attention-ranking-v13", "rank": 413, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-23", "source": {"authors": ["supreethbare"], "categories": [], "id": "github:supreethbare/decision-model-bench", "publicSignals": {"githubStars": 0}, "title": "decision-model-bench", "type": "github", "url": "https://github.com/supreethbare/decision-model-bench"}, "sourceUpdatedAt": "2026-09-24T04:47:46Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It could inform decisions about using typed decision models as routing layers, but the lack of a stable, shared evaluation protocol reduces its benchmark value."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
