{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.19407", "kind": "paper", "url": "https://arxiv.org/abs/2607.19407"}], "authors": ["Jiayi Wu", "Robert Joseph George", "Anima Anandkumar"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.19407", "source_url": "https://arxiv.org/abs/2607.19407"}, "categories": ["Language & Knowledge", "Mathematics & Formal Science", "cs.AI"], "description": {"en": "ITPEval evaluates automated formal proof translation across four interactive theorem provers (Lean 4, Rocq, Isabelle, HOL Light), with 1,560 source files and 6,848 theorems, covering statement and proof translation on 12 directed pairs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.19407", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.19407", "title": "ITPEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.19407", "modality": null, "name": "ITPEval", "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_itpeval_0f85127f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e66fb6f3917d0086652e504ea72c4c076d780558fde7a18c8d04c92d84bef85e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.19407"}, "publisher": null, "released": "2026-07-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.19407", "source_url": "https://arxiv.org/abs/2607.19407"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-19407", "source": "claire_radar", "source_benchmark_id": "2607.19407", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mathematics & Formal Science"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.19407", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d50cedcc907e1b100a284c56cc9839dbb3cbb7076415c193f377570d249016d1", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ITPEval evaluates automated formal proof translation across four interactive theorem provers (Lean 4, Rocq, Isabelle, HOL Light), with 1,560 source files and 6,848 theorems, covering statement and proof translation on 12 directed pairs.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We present ITPEval, the first benchmark for evaluating automated formal proof translation across four major ITPs (Lean 4, Rocq, Isabelle, and HOL Light), spanning two distinct logical foundations."}, "familyId": "bmf_edcd96daf17a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_itpeval_0f85127f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.19407", "paper": "https://arxiv.org/abs/2607.19407", "pdf": "https://arxiv.org/pdf/2607.19407", "project": null, "report": "https://arxiv.org/abs/2607.19407"}, "metrics": [], "motivation": "Formal theorem proving has emerged as a frontier challenge for machine learning, yet the ecosystem is fragmented: proofs remain siloed across incompatible systems, limiting both training data for learning-based provers and the portability of verified results.", "name": "ITPEval", "oneLine": "ITPEval evaluates automated formal proof translation across four interactive theorem provers (Lean 4, Rocq, Isabelle, HOL Light), with 1,560 source files and 6,848 theorems, covering statement and proof translation on 12 directed pairs.", "paperTitle": "ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers", "primaryDomain": "Mathematics & Formal Science", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.19407", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ITPEval team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.19407"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-07", "source": {"authors": ["Jiayi Wu", "Robert Joseph George", "Anima Anandkumar"], "categories": ["cs.AI", "cs.LO"], "id": "2607.19407", "title": "ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers", "type": "arxiv", "url": "https://arxiv.org/abs/2607.19407"}, "sourceUpdatedAt": "2026-07-07T22:05:55Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "ITPEval addresses the lack of a unified benchmark for cross-prover formal proof translation, providing a standardized evaluation of a key capability for automated reasoning and verified software portability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
