{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04442", "kind": "paper", "url": "https://arxiv.org/abs/2606.04442"}], "authors": ["Qiyang Xie", "Jialun Wu", "Xinjie He", "Su Liu", "Shuai Xiao", "Zhiyuan Lin", "Weikai Zhou"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04442", "source_url": "https://arxiv.org/abs/2606.04442"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "MemoryDocDataSet evaluates joint conversational memory and long-document reasoning through 50 synthetic micro-worlds, each with personas, temporal event graphs, real legal documents, multi-session conversations, and QA pairs. Questions are categorized by reasoning type, with Hybrid questions requiring navigation of conversation history to locate the relevant document and extract answers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04442", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04442", "title": "MemoryDocDataSet"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Northeastern University", "Johns Hopkins University", "Columbia University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.04442", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.04442", "source_url": "https://openalex.org/W7163537440"}, "key": "claire-radar:2606.04442", "modality": null, "name": "MemoryDocDataSet", "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_memorydocdataset_b8a1ebc4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "87982811008521b70ea1bb3f080ac4670bfc77129850882ccf9923af915f94b2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04442"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04442", "source_url": "https://arxiv.org/abs/2606.04442"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04442", "source": "claire_radar", "source_benchmark_id": "2606.04442", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.04442", "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": ["Reasoning"], "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": "7582237fc995bda61f2d12f50b43f09493628f139ae5c218d4e2abd742f21d33", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MemoryDocDataSet evaluates joint conversational memory and long-document reasoning through 50 synthetic micro-worlds, each with personas, temporal event graphs, real legal documents, multi-session conversations, and QA pairs. Questions are categorized by reasoning type, with Hybrid questions requiring navigation of conversation history to locate the relevant document and extract answers.", "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"], "snippet": "We introduce MemoryDocDataSet, a synthetic benchmark of 50 micro-worlds and 1,000 QA pairs in which each instance comprises 3-5 personas, a temporal event graph spanning months of activity, 3-5 real long documents (20,000-50,000 tokens each sourced from the Caselaw Access Project), multi-session conversations grounded on those documents, and 20 question-answer pairs across five reasoning categories."}, "familyId": "bmf_19a123656f60", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_memorydocdataset_b8a1ebc4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.04442", "paper": "https://arxiv.org/abs/2606.04442", "pdf": "https://arxiv.org/pdf/2606.04442", "project": null, "report": "https://arxiv.org/abs/2606.04442"}, "metrics": [], "motivation": "AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehension within long documents.", "name": "MemoryDocDataSet", "oneLine": "MemoryDocDataSet evaluates joint conversational memory and long-document reasoning through 50 synthetic micro-worlds, each with personas, temporal event graphs, real legal documents, multi-session conversations, and QA pairs. Questions are categorized by reasoning type, with Hybrid questions requiring navigation of conversation history to locate the relevant document and extract answers.", "paperTitle": "MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.04442", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.04442"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Qiyang Xie", "Jialun Wu", "Xinjie He", "Su Liu", "Shuai Xiao", "Zhiyuan Lin", "Weikai Zhou"], "categories": ["cs.CL", "cs.AI"], "id": "2606.04442", "title": "MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04442"}, "sourceUpdatedAt": "2026-06-03T04:44:50Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing benchmarks evaluate conversational memory or document reasoning separately, leaving a gap in measuring integrated performance. MemoryDocDataSet provides a controlled, synthetic environment to assess systems on tasks that require both capabilities, useful for developing and comparing architectures that unify conversation memory with long-document retrieval."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
