{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01223", "kind": "paper", "url": "https://arxiv.org/abs/2606.01223"}], "authors": ["Jingjie Lin", "Bingbing Wang", "Zihan Wang", "Zhengda Jin", "Weiming Qiao", "Jing Li", "Ruifeng Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01223", "source_url": "https://arxiv.org/abs/2606.01223"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "RefMem-Bench is a benchmark for reflective memory in long-horizon dialogue, containing 26K QA instances across eight reflective-memory dimensions and three task formats."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01223", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01223", "title": "RefMem-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Harbin Institute of Technology", "Hong Kong Polytechnic University", "Fudan University", "Peng Cheng Laboratory"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01223", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01223", "source_url": "https://openalex.org/W7163135831"}, "key": "claire-radar:2606.01223", "modality": null, "name": "RefMem-Bench", "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_refmem-bench_c6cd0aef", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7661fb504105588118f85be04d6898d3167e28b9a2782f86ee85aa7ae9c041de", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01223"}, "publisher": null, "released": "2026-05-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01223", "source_url": "https://arxiv.org/abs/2606.01223"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01223", "source": "claire_radar", "source_benchmark_id": "2606.01223", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.01223", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "46107058f8122d18b9afcdd06180ee89c64834ec4a1427d54a4184e6709cd9e0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RefMem-Bench is a benchmark for reflective memory in long-horizon dialogue, containing 26K QA instances across eight reflective-memory dimensions and three task formats.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue."}, "familyId": "bmf_06cc5544fe08", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_refmem-bench_c6cd0aef", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01223", "paper": "https://arxiv.org/abs/2606.01223", "pdf": "https://arxiv.org/pdf/2606.01223", "project": null, "report": "https://arxiv.org/abs/2606.01223"}, "metrics": [], "motivation": "Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations.", "name": "RefMem-Bench", "oneLine": "RefMem-Bench is a benchmark for reflective memory in long-horizon dialogue, containing 26K QA instances across eight reflective-memory dimensions and three task formats.", "paperTitle": "Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01223", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-31", "source": {"authors": ["Jingjie Lin", "Bingbing Wang", "Zihan Wang", "Zhengda Jin", "Weiming Qiao", "Jing Li", "Ruifeng Xu"], "categories": ["cs.CL", "cs.AI"], "id": "2606.01223", "title": "Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01223"}, "sourceUpdatedAt": "2026-05-31T13:16:02Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It evaluates the ability of models to synthesize fragmented multimodal cues into high-level interpretations, going beyond explicit recall."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
