{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.10388", "kind": "paper", "url": "https://arxiv.org/abs/2606.10388"}], "authors": ["Jiandong Ding", "Honglei Ji", "Ming Liu", "Tao Duan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.10388", "source_url": "https://arxiv.org/abs/2606.10388"}, "categories": ["Agents", "General AI", "Information retrieval", "Language & Knowledge"], "description": {"en": "SkillResolve-Bench 1.0 evaluates agent skill retrieval under same-capability ambiguity, pairing helpful skills with risky siblings. It includes 661 pairs, a 7,982-candidate pool, disjoint splits, and reports Recall@K and harmful sibling rate (HSR@K)."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.10388", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.10388", "title": "SkillResolve-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.10388", "modality": null, "name": "SkillResolve-Bench", "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-indexed", "display_eligible": "unknown", "origin_record_id": "bm_skillresolve-bench_99845262", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "f22352a2a6a41cd35affd3bad927c533a0f7c9e3b1f1a37bb0561e42ddffa3a4", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.10388"}, "publisher": null, "released": "2026-06-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.10388", "source_url": "https://arxiv.org/abs/2606.10388"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-10388", "source": "claire_radar", "source_benchmark_id": "2606.10388", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2606.10388", "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", "lastSuccessfulDate": "2026-09-24", "state": "stale"}}, "status": "stale"}, "capabilities": ["Information retrieval"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "a39b09a08c49f30abc0881fb8d26b02163a742f40d34c9d96279d74301e94972", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SkillResolve-Bench 1.0 evaluates agent skill retrieval under same-capability ambiguity, pairing helpful skills with risky siblings. It includes 661 pairs, a 7,982-candidate pool, disjoint splits, and reports Recall@K and harmful sibling rate (HSR@K).", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce SkillResolve-Bench 1.0, an auditable benchmark for this setting with 661 helpful/risky pairs, source-role and admission evidence, cue/leakage checks, query-disjoint splits, and a 7,982-candidate pool that includes 6,660 public SkillRet candidates."}, "familyId": "bmf_df773b457612", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_skillresolve-bench_99845262", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.10388", "paper": "https://arxiv.org/abs/2606.10388", "pdf": "https://arxiv.org/pdf/2606.10388", "project": null, "report": "https://arxiv.org/abs/2606.10388"}, "metrics": [], "motivation": "Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent.", "name": "SkillResolve-Bench", "oneLine": "SkillResolve-Bench 1.0 evaluates agent skill retrieval under same-capability ambiguity, pairing helpful skills with risky siblings. It includes 661 pairs, a 7,982-candidate pool, disjoint splits, and reports Recall@K and harmful sibling rate (HSR@K).", "paperTitle": "SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.10388", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.10388"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-09", "source": {"authors": ["Jiandong Ding"], "categories": ["cs.IR", "cs.AI"], "id": "2606.10388", "title": "SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval", "type": "arxiv", "url": "https://arxiv.org/abs/2606.10388"}, "sourceUpdatedAt": "2026-06-09T03:54:45Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Skill retrieval carries execution risk beyond relevance. This benchmark quantifies exposure to risky siblings, supporting development of retrievers that select safe representatives, reducing harmful failures in agent deployments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
