{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.31154", "kind": "paper", "url": "https://arxiv.org/abs/2606.31154"}, {"id": "gh:microsoft/ppteval", "kind": "repo", "url": "https://github.com/microsoft/PPTEval"}, {"kind": "website", "url": "https://microsoft.github.io/ppteval"}], "authors": ["Apurva Gandhi", "Vishwas Suryanarayanan", "Raja Hasnain Anwar", "Firoz Shaik", "Shubhang Desai", "Thong Q. Nguyen", "Muhammad Taqi Raza", "Vishal Chowdhary", "Graham Neubig"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.31154", "source_url": "https://arxiv.org/abs/2606.31154"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "PPT-Eval is a benchmark of 120 PowerPoint tasks across 12 files for computer-use agents. It covers content creation and editing, with rubric-based evaluation that awards partial credit and provides natural language feedback."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.31154", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.31154", "title": "PPT-Eval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.31154", "modality": null, "name": "PPT-Eval", "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_ppt-eval_9317e9e6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a6e0cbc4a7d2545aa637b2779929704596747772fb3a9c3524182503daf07802", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.31154"}, "publisher": null, "released": "2026-06-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.31154", "source_url": "https://arxiv.org/abs/2606.31154"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-31154", "source": "claire_radar", "source_benchmark_id": "2606.31154", "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/microsoft/PPTEval", "githubScope": "benchmark_repo", "githubStars": 14, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.31154", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "5a27f5023da02e575c3b0c42ea5523c37770d4f14da9bd97bdf8f660b8fd44ab", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PPT-Eval is a benchmark of 120 PowerPoint tasks across 12 files for computer-use agents. It covers content creation and editing, with rubric-based evaluation that awards partial credit and provides natural language feedback.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce PPT-Eval, a benchmark of 120 PowerPoint tasks across 12 files that cover both content creation and presentation editing scenarios, organized by difficulty."}, "familyId": "bmf_32aec5f2ab84", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/microsoft/PPTEval", "url": "https://microsoft.github.io/ppteval"}], "scope": "benchmark_repo", "url": "https://github.com/microsoft/PPTEval", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ppt-eval_9317e9e6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/microsoft/PPTEval", "data": null, "hfPaper": "https://huggingface.co/papers/2606.31154", "paper": "https://arxiv.org/abs/2606.31154", "pdf": "https://arxiv.org/pdf/2606.31154", "project": "https://microsoft.github.io/ppteval", "report": "https://arxiv.org/abs/2606.31154"}, "metrics": [], "motivation": "Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents.", "name": "PPT-Eval", "oneLine": "PPT-Eval is a benchmark of 120 PowerPoint tasks across 12 files for computer-use agents. It covers content creation and editing, with rubric-based evaluation that awards partial credit and provides natural language feedback.", "paperTitle": "PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.31154", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Microsoft", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://microsoft.github.io/ppteval"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-30", "source": {"authors": ["Apurva Gandhi", "Vishwas Suryanarayanan", "Raja Hasnain Anwar", "Firoz Shaik", "Shubhang Desai", "Thong Q. Nguyen", "Muhammad Taqi Raza", "Vishal Chowdhary", "Graham Neubig"], "categories": ["cs.LG", "cs.AI"], "id": "2606.31154", "title": "PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2606.31154"}, "sourceUpdatedAt": "2026-06-30T05:26:51Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Provides a realistic, multimodal testbed for computer-use agents. The rubric-based scoring captures partial progress and correlates with human judgment, enabling nuanced comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
