{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.12608", "kind": "paper", "url": "https://arxiv.org/abs/2606.12608"}], "authors": ["Shuxian Fan", "Seonwoo Min", "Youna Hu", "Botao Xia", "Jayakrishnan Unnikrishnan", "Rowan Musselmann", "Yifan Gao", "Qingyu Yin", "Priyanka Nigam", "Bing Yin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.12608", "source_url": "https://arxiv.org/abs/2606.12608"}, "categories": ["Language & Knowledge", "Reasoning", "Software & AI Compute"], "description": {"en": "Assesses multi-turn conversational shopping assistants across 525 expert-authored missions with importance-weighted binary rubrics. Evaluates reasoning across five categories covering preference refinement, trade-off analysis, and compatibility assessment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.12608", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.12608", "title": "Shopping Reasoning Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.12608", "modality": null, "name": "Shopping Reasoning 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_shopping-reasoning-bench_1ec16882", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "af373962b88897a3ce5a06b8f92f1420dc82389a29fdc3baec5833bbaa3e12a8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.12608"}, "publisher": null, "released": "2026-06-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.12608", "source_url": "https://arxiv.org/abs/2606.12608"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-12608", "source": "claire_radar", "source_benchmark_id": "2606.12608", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.12608", "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": "2026-10-01", "state": "stale"}}, "status": "stale"}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "55844d5eb57bd09832f19037d0227541a00378d75d1ac069ce01f7cc260e7955", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Assesses multi-turn conversational shopping assistants across 525 expert-authored missions with importance-weighted binary rubrics. Evaluates reasoning across five categories covering preference refinement, trade-off analysis, and compatibility assessment.", "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 the Shopping Reasoning Bench, an expert-authored benchmark of 525 missions (232 single-turn, 293 multi-turn) with 10863 importance-weighted binary rubrics authored by retail domain experts."}, "familyId": "bmf_241bcbe846af", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_shopping-reasoning-bench_1ec16882", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.12608", "paper": "https://arxiv.org/abs/2606.12608", "pdf": "https://arxiv.org/pdf/2606.12608", "project": null, "report": "https://arxiv.org/abs/2606.12608"}, "metrics": [], "motivation": "Conversational shopping assistants now serve hundreds of millions of customers, yet no existing benchmark jointly evaluates the open-ended multi-turn reasoning, domain expertise, and criterion-level quality that real shopping conversations demand.", "name": "Shopping Reasoning Bench", "oneLine": "Assesses multi-turn conversational shopping assistants across 525 expert-authored missions with importance-weighted binary rubrics. Evaluates reasoning across five categories covering preference refinement, trade-off analysis, and compatibility assessment.", "paperTitle": "Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.12608", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Shopping Reasoning Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/papers/2606.12608"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-10", "source": {"authors": ["Shuxian Fan", "Seonwoo Min", "Youna Hu", "Botao Xia", "Jayakrishnan Unnikrishnan", "Rowan Musselmann", "Yifan Gao", "Qingyu Yin", "Priyanka Nigam", "Bing Yin"], "categories": ["cs.CL", "cs.LG"], "id": "2606.12608", "title": "Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants", "type": "arxiv", "url": "https://arxiv.org/abs/2606.12608"}, "sourceUpdatedAt": "2026-06-10T19:04:09Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Fills the lack of benchmarks for open-ended shopping dialogue with objective criteria and nuanced reasoning, providing a standardized testbed for improving assistant performance in real-world e-commerce."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
