{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.14832", "kind": "paper", "url": "https://arxiv.org/abs/2606.14832"}, {"id": "gh:phoneharness/phoneharness", "kind": "repo", "url": "https://github.com/PhoneHarness/PhoneHarness"}, {"kind": "website", "url": "https://phoneharness.github.io/"}], "authors": ["Chenxin Li", "Zhengyao Fang", "Zhengyang Tang", "Pengyuan Lyu", "Xingran Zhou", "Xin Lai", "Fei Tang", "Liang Wu", "Yiduo Guo", "Weinong Wang", "Junyi Li", "Yi Zhang", "Yang Ding", "Huawen Shen", "Sunqi Fan", "Shangpin Peng", "Zheng Ruan", "Anran Zhang", "Benyou Wang", "Chengquan Zhang", "Han Hu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.14832", "source_url": "https://arxiv.org/abs/2606.14832"}, "categories": ["Agents & Tool Use", "Mobile & Personal Computing", "cs.CL"], "description": {"en": "PhoneHarness Bench evaluates phone-use agents on verifiable mobile workflows with mixed GUI, CLI, and tool actions, scored by observable side effects from auditable execution traces."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.14832", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.14832", "title": "PhoneHarness"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tencent (China)", "Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.14832", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.14832", "source_url": "https://openalex.org/W7164878659"}, "key": "claire-radar:2606.14832", "modality": null, "name": "PhoneHarness", "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_phoneharness_125a2bf7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "48a26b4d4962b9c079b5c95c7277a88dc57f106529c6cfbd6a668c1cabe4c916", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.14832"}, "publisher": null, "released": "2026-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.14832", "source_url": "https://arxiv.org/abs/2606.14832"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-14832", "source": "claire_radar", "source_benchmark_id": "2606.14832", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mobile & Personal Computing"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/PhoneHarness/PhoneHarness", "githubScope": "benchmark_repo", "githubStars": 80, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 11, "hfPaperUrl": "https://huggingface.co/papers/2606.14832", "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", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "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": "88de4646e887ccf34184dcc526f7bf49218637039c4f01fe9b09cb182befd1cc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PhoneHarness Bench evaluates phone-use agents on verifiable mobile workflows with mixed GUI, CLI, and tool actions, scored by observable side effects from auditable execution traces.", "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 PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows."}, "familyId": "bmf_a6d0de088cce", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/PhoneHarness/PhoneHarness", "url": "https://github.com/PhoneHarness/PhoneHarness"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/PhoneHarness/PhoneHarness", "url": "https://huggingface.co/papers/2606.14832"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/PhoneHarness/phoneharness", "url": "https://phoneharness.github.io/"}], "scope": "benchmark_repo", "url": "https://github.com/PhoneHarness/PhoneHarness", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_phoneharness_125a2bf7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Consumer Technology"], "links": {"code": "https://github.com/PhoneHarness/PhoneHarness", "data": null, "hfPaper": "https://huggingface.co/papers/2606.14832", "paper": "https://arxiv.org/abs/2606.14832", "pdf": "https://arxiv.org/pdf/2606.14832", "project": "https://phoneharness.github.io/", "report": "https://arxiv.org/abs/2606.14832"}, "metrics": [], "motivation": "Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action.", "name": "PhoneHarness", "oneLine": "PhoneHarness Bench evaluates phone-use agents on verifiable mobile workflows with mixed GUI, CLI, and tool actions, scored by observable side effects from auditable execution traces.", "paperTitle": "PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions", "primaryDomain": "Mobile & Personal Computing", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.14832", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-12", "source": {"authors": ["Chenxin Li", "Zhengyao Fang", "Zhengyang Tang", "Pengyuan Lyu", "Xingran Zhou", "Xin Lai", "Fei Tang", "Liang Wu", "Yiduo Guo", "Weinong Wang", "Junyi Li", "Yi Zhang", "Yang Ding", "Huawen Shen", "Sunqi Fan", "Shangpin Peng", "Zheng Ruan", "Anran Zhang", "Benyou Wang", "Chengquan Zhang", "Han Hu"], "categories": ["cs.CL"], "id": "2606.14832", "title": "PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.14832"}, "sourceUpdatedAt": "2026-06-12T15:01:32Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Mobile agent evaluation often ignores non-GUI actions and side effects; this benchmark measures complete task completion in real device environments, filling a gap for reliable phone automation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
