{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05563", "kind": "paper", "url": "https://arxiv.org/abs/2606.05563"}, {"id": "gh:disl-lab/socrates", "kind": "repo", "url": "https://github.com/DISL-Lab/SoCRATES"}], "authors": ["Taewon Yun", "Hyeonseong Park", "Jeonghwan Choi", "Hayoon Park", "Yeeun Choi", "Hwanjun Song"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05563", "source_url": "https://arxiv.org/abs/2606.05563"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "SoCRATES is a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It contains 600 conflict scenarios across eight domains, probing five socio-cognitive adaptation axes, with topic-localized scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05563", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05563", "title": "SoCRATES"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Chungnam National University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05563", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05563", "source_url": "https://openalex.org/W7163638313"}, "key": "claire-radar:2606.05563", "modality": null, "name": "SoCRATES", "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_socrates_dac2012d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3a4684ff1d0ba03e6ac93b85523f91b4f86f148e2a6cdf21b52be26a50eb809a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05563"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05563", "source_url": "https://arxiv.org/abs/2606.05563"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05563", "source": "claire_radar", "source_benchmark_id": "2606.05563", "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": "https://github.com/DISL-Lab/SoCRATES", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 56, "hfPaperUrl": "https://huggingface.co/papers/2606.05563", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "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": "57fa78e57b3da75f3b3f92c36fd4c142a2ffdddf0fbba27fb1d3582d54bda95e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SoCRATES is a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It contains 600 conflict scenarios across eight domains, probing five socio-cognitive adaptation axes, with topic-localized scoring.", "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 SoCRATES, a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds."}, "familyId": "bmf_710482eaa280", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/DISL-Lab/SoCRATES", "url": "https://github.com/DISL-Lab/SoCRATES"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/DISL-Lab/SoCRATES", "url": "https://huggingface.co/papers/2606.05563"}], "scope": "benchmark_repo", "url": "https://github.com/DISL-Lab/SoCRATES", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_socrates_dac2012d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/DISL-Lab/SoCRATES", "data": null, "hfPaper": "https://huggingface.co/papers/2606.05563", "paper": "https://arxiv.org/abs/2606.05563", "pdf": "https://arxiv.org/pdf/2606.05563", "project": null, "report": "https://arxiv.org/abs/2606.05563"}, "metrics": [], "motivation": "Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context.", "name": "SoCRATES", "oneLine": "SoCRATES is a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It contains 600 conflict scenarios across eight domains, probing five socio-cognitive adaptation axes, with topic-localized scoring.", "paperTitle": "SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05563", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "DISL-Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/DISL-Lab/SoCRATES"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Taewon Yun", "Hyeonseong Park", "Jeonghwan Choi", "Hayoon Park", "Yeeun Choi", "Hwanjun Song"], "categories": ["cs.AI", "cs.CL"], "id": "2606.05563", "title": "SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05563"}, "sourceUpdatedAt": "2026-06-04T01:19:40Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Mediation evaluation requires realistic trajectories and topic-specific scoring. SoCRATES provides a structured testbed with socio-cognitive variations, enabling reliable comparison of LLM mediators."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
