{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.11504", "kind": "paper", "url": "https://arxiv.org/abs/2609.11504"}, {"id": "gh:varun-2538/koan", "kind": "repo", "url": "https://github.com/Varun-2538/Koan"}], "authors": ["Abhinav Rajeev Kumar", "Harshit Arora", "Varun Singh", "Manikandan Nanjappan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11504", "source_url": "https://arxiv.org/abs/2609.11504"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "Benchmark of 207 prompts for synthesizing DeFi workflows from natural language."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11504", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11504", "title": "DeFiFlowBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["SRM Institute of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.11504", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.11504", "source_url": "https://openalex.org/W7212246070"}, "key": "claire-radar:2609.11504", "modality": null, "name": "DeFiFlowBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_defiflowbench_75ae0752", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d89dd3abf01f047676e507586ee6e378d7229ec3d05c542ba2aad90377a1c3a3", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-12T00:56:20.009268Z", "source_url": "https://arxiv.org/abs/2609.11504"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11504", "source_url": "https://arxiv.org/abs/2609.11504"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11504", "source": "claire_radar", "source_benchmark_id": "2609.11504", "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/Varun-2538/Koan", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.11504", "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", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Blockchain-specific benchmark appeal is moderate, but unavailable artifacts dampen immediate adoption interest.", "score": 15}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-12T00:56:20.009268Z", "inputHash": "09ffbc38f30df13fd5fb39aa7e218ac712f68833a4d73b05feb97e4f56fd485d", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis", "canonicalNameSource": "paper_title", "decisionReason": "Associated code repository is a platform product without specific benchmark data or scoring implementation for the described prompts.", "evaluationEvidence": {"reuse": "https://github.com/Varun-2538/Koan", "scoring": "It measures graph coverage, configuration completeness, and declared safety predicates, then tests supported trade configurations on a local EVM.", "task": "We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-language DeFi workflow synthesis."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-12T00:56:20.009268Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmark of 207 prompts for synthesizing DeFi workflows from natural language.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-language DeFi workflow synthesis."}, "familyId": "bmf_8a52472a07a8", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_defiflowbench_75ae0752", "indexedAt": "2026-09-11T06:20:12.012226Z", "industrySectors": [], "links": {"code": "https://github.com/Varun-2538/Koan", "data": null, "paper": "https://arxiv.org/abs/2609.11504", "pdf": "https://arxiv.org/pdf/2609.11504", "project": null, "report": "https://arxiv.org/abs/2609.11504"}, "metrics": [], "motivation": "A structurally valid DeFi workflow can still authorize a costly trade.", "name": "DeFiFlowBench", "oneLine": "Benchmark of 207 prompts for synthesizing DeFi workflows from natural language.", "paperTitle": "DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.11504", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T06:20:12.012226Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 189, "score": 23}, "method": "attention-ranking-v13", "rank": 189, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 453, "score": 23}, "method": "attention-ranking-v13", "rank": 453, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-10", "source": {"authors": ["Abhinav Rajeev Kumar", "Harshit Arora", "Varun Singh", "Manikandan Nanjappan"], "categories": ["cs.LG", "cs.SE"], "id": "2609.11504", "title": "DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11504"}, "sourceUpdatedAt": "2026-09-10T13:10:32Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "May advance safe DeFi automation, but no evaluation protocol or usable dataset is currently provided."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
