{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05661", "kind": "paper", "url": "https://arxiv.org/abs/2606.05661"}], "authors": ["Parth Asawa", "Christopher M. Glaze", "Gabriel Orlanski", "Ramya Ramakrishnan", "Benji Xu", "Asim Biswal", "Vincent Sunn Chen", "Frederic Sala", "Matei Zaharia", "Joseph E. Gonzalez"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05661", "source_url": "https://arxiv.org/abs/2606.05661"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates continual learning in LLM-based systems across six expert-validated domains with stateful tasks sharing learnable latent structure."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05661", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05661", "title": "Continual Learning Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Berkeley", "University of Wisconsin–Madison"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05661", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05661", "source_url": "https://openalex.org/W7163694368"}, "key": "claire-radar:2606.05661", "modality": null, "name": "Continual Learning 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_continual-learning-bench_09825e20", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f27fd84d72772f913fa6ddbb0b00cb2f06c652ec76579f4419d259d8ed1a683f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05661"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05661", "source_url": "https://arxiv.org/abs/2606.05661"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05661", "source": "claire_radar", "source_benchmark_id": "2606.05661", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.05661", "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": "e20dcf6c1741424cdc7388d88ad9d277ae2ff4388ff3fa11d9e27ee9ebdeb8d3", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates continual learning in LLM-based systems across six expert-validated domains with stateful tasks sharing learnable latent structure.", "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 Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems genuinely improve with experience."}, "familyId": "bmf_427801ebd816", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_continual-learning-bench_09825e20", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05661", "paper": "https://arxiv.org/abs/2606.05661", "pdf": "https://arxiv.org/pdf/2606.05661", "project": null, "report": "https://arxiv.org/abs/2606.05661"}, "metrics": [], "motivation": "Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it.", "name": "Continual Learning Bench", "oneLine": "Evaluates continual learning in LLM-based systems across six expert-validated domains with stateful tasks sharing learnable latent structure.", "paperTitle": "Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05661", "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": "2026-06-04", "source": {"authors": ["Parth Asawa", "Christopher M. Glaze", "Gabriel Orlanski", "Ramya Ramakrishnan", "Benji Xu", "Asim Biswal", "Vincent Sunn Chen", "Frederic Sala", "Matei Zaharia", "and Joseph E. Gonzalez"], "categories": ["cs.AI", "cs.CL"], "id": "2606.05661", "title": "Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05661"}, "sourceUpdatedAt": "2026-06-04T03:43:28Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Could address the absence of high-quality benchmarks for genuine continual learning, but currently lacks verifiable public artifacts or scoring details."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
