{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.09461", "kind": "paper", "url": "https://arxiv.org/abs/2606.09461"}], "authors": ["Shiping Zhu", "Yibo Yang", "Zhengyang Wang", "Tiancheng Shen", "Dandan Guo", "Ming-Hsuan Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.09461", "source_url": "https://arxiv.org/abs/2606.09461"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "H2HMem is a benchmark for evaluating memory capabilities of agents in human-human multimodal interactions, covering dyadic and multi-party conversations with tasks in memory recall, reasoning, and application."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.09461", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.09461", "title": "H2HMem"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Jilin University", "Shanghai Jiao Tong University", "University of California, Merced"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.09461", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.09461", "source_url": "https://openalex.org/W7164044979"}, "key": "claire-radar:2606.09461", "modality": null, "name": "H2HMem", "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_h2hmem_6775c266", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6aa77ea03f701699a9c9eef15e734504ede9c6deab85a0b26dbbba553fce4ce9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.09461"}, "publisher": null, "released": "2026-06-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.09461", "source_url": "https://arxiv.org/abs/2606.09461"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-09461", "source": "claire_radar", "source_benchmark_id": "2606.09461", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "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": 2, "hfPaperUrl": "https://huggingface.co/papers/2606.09461", "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": "2026-09-25", "state": "stale"}}, "status": "stale"}, "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": "1dd0b93d91fc092466bc89b8b73897273985ddbd246c507c7d855c0c25cf004d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "H2HMem is a benchmark for evaluating memory capabilities of agents in human-human multimodal interactions, covering dyadic and multi-party conversations with tasks in memory recall, reasoning, and application.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce H2HMem, a Human-to-Human Multimodal Memory Benchmark for evaluating memory capabilities in complex human-human interactions."}, "familyId": "bmf_5903d1e9207d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_h2hmem_6775c266", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.09461", "paper": "https://arxiv.org/abs/2606.09461", "pdf": "https://arxiv.org/pdf/2606.09461", "project": null, "report": "https://arxiv.org/abs/2606.09461"}, "metrics": [], "motivation": "Large language model agents are increasingly deployed in human-human interaction settings, such as meeting assistants and clinical documentation systems, where they must observe conversations and retain information for downstream queries.", "name": "H2HMem", "oneLine": "H2HMem is a benchmark for evaluating memory capabilities of agents in human-human multimodal interactions, covering dyadic and multi-party conversations with tasks in memory recall, reasoning, and application.", "paperTitle": "H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.09461", "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": "2026-06-08", "source": {"authors": ["Shiping Zhu", "Yibo Yang", "Zhengyang Wang", "Tiancheng Shen", "Dandan Guo", "Ming-Hsuan Yang"], "categories": ["cs.CL"], "id": "2606.09461", "title": "H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.09461"}, "sourceUpdatedAt": "2026-06-08T13:17:16Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing memory benchmarks focus on single-user text interactions; H2HMem addresses the need for evaluating agents in complex multimodal human-human settings with asynchronous and conflicting information from multiple participants."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
