{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.29002", "kind": "paper", "url": "https://arxiv.org/abs/2607.29002"}], "authors": ["Zeying Hao", "Hao Guo", "Mengtao Xu", "Yimin Hu", "Yuheng Song", "Zesheng Zhou", "Jinsong Lan", "Xiaoyong Zhu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.29002", "source_url": "https://arxiv.org/abs/2607.29002"}, "categories": ["General AI", "Multimodal"], "description": {"en": "MMShopBench is a real-log benchmark for multimodal multi-turn shopping agents. It uses cleaned shopping logs with annotations for purchase intent and mandatory product requirements. Agents must infer requirements from images and dialogue, retrieve candidates, and verify product satisfaction."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.29002", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.29002", "title": "MMShopBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.29002", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.29002", "source_url": "https://openalex.org/W7172270348"}, "key": "claire-radar:2607.29002", "modality": null, "name": "MMShopBench", "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_mmshopbench_a4cdc83b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e7baac890a72e29db9bc989b9b4a2354e036485259a8bf06a04aa04eaec7166b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.29002"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.29002", "source_url": "https://arxiv.org/abs/2607.29002"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-29002", "source": "claire_radar", "source_benchmark_id": "2607.29002", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2607.29002", "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": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d1a96fc9628e62a6a2cedc0d6b03def4a0b9e8b0e9447f8634fabfecbce69001", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MMShopBench is a real-log benchmark for multimodal multi-turn shopping agents. It uses cleaned shopping logs with annotations for purchase intent and mandatory product requirements. Agents must infer requirements from images and dialogue, retrieve candidates, and verify product satisfaction.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce MMShopBench, the first real-log benchmark for multimodal, multi-turn shopping agents."}, "familyId": "bmf_b4f7e925e936", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mmshopbench_a4cdc83b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.29002", "paper": "https://arxiv.org/abs/2607.29002", "pdf": "https://arxiv.org/pdf/2607.29002", "project": null, "report": "https://arxiv.org/abs/2607.29002"}, "metrics": [], "motivation": "Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult to articulate in text alone.", "name": "MMShopBench", "oneLine": "MMShopBench is a real-log benchmark for multimodal multi-turn shopping agents. It uses cleaned shopping logs with annotations for purchase intent and mandatory product requirements. Agents must infer requirements from images and dialogue, retrieve candidates, and verify product satisfaction.", "paperTitle": "MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.29002", "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/2607.29002"}], "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": "2026-07-31", "source": {"authors": ["Zeying Hao", "Hao Guo", "Mengtao Xu", "Yimin Hu", "Yuheng Song", "Zesheng Zhou", "Jinsong Lan", "Xiaoyong Zhu"], "categories": ["cs.AI"], "id": "2607.29002", "title": "MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2607.29002"}, "sourceUpdatedAt": "2026-07-31T04:00:15Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing benchmarks often rely on text-only or synthetic requests, missing complex real-world multimodal shopping needs. MMShopBench provides a realistic evaluation to advance shopping agents, with an offline sandbox for reproducible experimentation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
