{"record": {"aliases": [], "artifacts": [{"id": "hf:djalexj/amo-bench-p", "kind": "dataset", "url": "https://huggingface.co/datasets/djalexj/amo-bench-p"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "AMO-Bench-P is a 39-problem subset of AMO-Bench with parser-graded answers (numbers, sets, variables), excluding description-type answers that require an LLM judge."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://huggingface.co/datasets/djalexj/amo-bench-p", "source": "claire_radar", "source_url": "https://huggingface.co/datasets/djalexj/amo-bench-p", "title": "amo-bench-p"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:huggingface:djalexj/amo-bench-p", "modality": null, "name": "amo-bench-p", "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": "false", "origin_record_id": "bm_amo-bench-p_ed92afee", "origin_source": "huggingface", "recognition_confidence": "0.4", "record_sha256": "23481dff9aa55e5f848f393a4d2d09228599a4329f493480848bc41cbfd738f2", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T15:38:21.596820Z", "source_url": "https://huggingface.co/datasets/djalexj/amo-bench-p"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:huggingface:djalexj/amo-bench-p", "source_url": "https://huggingface.co/datasets/djalexj/amo-bench-p"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-huggingface-djalexj-amo-bench-p", "source": "claire_radar", "source_benchmark_id": "huggingface:djalexj/amo-bench-p", "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/meituan-longcat/AMO-Bench", "githubScope": "benchmark_repo", "githubStars": 171, "hfDailySubmittedAt": null, "hfDataset": "djalexj/amo-bench-p", "hfDatasetDownloads": 192, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T16:23:14.196185Z", "inputHash": "d827db214411517347295e54427ba23c9e5f3552a5d101ead733339606f22ccd", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T15:38:21.596820Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "AMO-Bench-P is a 39-problem subset of AMO-Bench with parser-graded answers (numbers, sets, variables), excluding description-type answers that require an LLM judge.", "discoverySources": [{"id": "huggingface:djalexj/amo-bench-p", "type": "huggingface", "url": "https://huggingface.co/datasets/djalexj/amo-bench-p"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via huggingface", "benchmark term in abstract", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "AMO-Bench-P This is the 39-problem, parser-graded subset of meituan-longcat/AMO-Bench."}, "familyId": "bmf_bc43e071f49e", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_amo-bench-p_ed92afee", "indexedAt": "2026-08-23T06:55:51.988821Z", "industrySectors": [], "links": {"data": "https://huggingface.co/datasets/djalexj/amo-bench-p", "paper": "https://huggingface.co/datasets/djalexj/amo-bench-p", "report": "https://huggingface.co/datasets/djalexj/amo-bench-p"}, "metrics": [], "motivation": "AMO-Bench-P This is the 39-problem, parser-graded subset of meituan-longcat/AMO-Bench.", "name": "amo-bench-p", "oneLine": "AMO-Bench-P is a 39-problem subset of AMO-Bench with parser-graded answers (numbers, sets, variables), excluding description-type answers that require an LLM judge.", "paperTitle": "amo-bench-p", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://huggingface.co/datasets/djalexj/amo-bench-p", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:51.988821Z"}, "publications": [], "ranking": {"90d": {"confidence": "High", "coverage": 0.85, "datasetDownloadRank": 44, "datasetRankPopulation": 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": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.6870979806705099, "value": 171}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.5419514298129436, "value": 192}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "High", "coverage": 0.85, "rank": 14, "score": 62}, "method": "attention-ranking-v13", "rank": 14, "score": 62}}, "readiness": "Inspectable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-20", "source": {"authors": ["djalexj"], "categories": [], "id": "huggingface:djalexj/amo-bench-p", "title": "amo-bench-p", "type": "huggingface", "url": "https://huggingface.co/datasets/djalexj/amo-bench-p"}, "sourceUpdatedAt": "2026-08-20T10:54:51.000Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It provides a focused, automatically verifiable mathematical reasoning subset, but it is a derivative subset without a formal benchmark declaration."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
