{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04706", "kind": "paper", "url": "https://arxiv.org/abs/2609.04706"}, {"id": "gh:abhisheksharma2411/finalitybench", "kind": "repo", "url": "https://github.com/abhisheksharma2411/finalitybench"}], "authors": ["Abhishek Sharma"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.04706", "source_url": "https://arxiv.org/abs/2609.04706"}, "categories": ["Agents", "Finance", "Language & Knowledge"], "description": {"en": "FinalityBench evaluates agent decisions in financial exception scenarios where payment systems have inconsistent views due to message faults. It uses a hidden canonical event log and derives system states via faulted delivery. Scoring measures executed monetary effects against a reference outcome."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04706", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04706", "title": "FinalityBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.04706", "modality": null, "name": "FinalityBench", "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": "true", "origin_record_id": "bm_finalitybench_36a71d92", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "80ab130939039355d76f9e680e328f79aa8455f565921f76d55ed1228be4b176", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-08T00:56:29.478814Z", "source_url": "https://arxiv.org/abs/2609.04706"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04706", "source_url": "https://arxiv.org/abs/2609.04706"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04706", "source": "claire_radar", "source_benchmark_id": "2609.04706", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-07", "attemptedAt": "2026-09-07T01:28:43.988909Z", "githubRepo": "https://github.com/abhisheksharma2411/finalitybench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.04706", "observedAt": "2026-09-07T01:28:43.988909Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-07T01:28:43.988909Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-07T01:28:43.988909Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets niche financial decision-making but includes executable code, clear comparison metrics, and results involving language models, which may attract applied AI and finance researchers.", "score": 65}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:59:06.803818Z", "inputHash": "893d7225851433f167a85d37ba25d00c2ab947fe7b975cdcb3a0923c51fe2cbe", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "We present FinalityBench, an executable benchmark for that decision.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is fully open-sourced with a clear scoring rubric, corpus, and reproducible experiments, allowing other teams to submit policies or models.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T00:56:29.478814Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinalityBench evaluates agent decisions in financial exception scenarios where payment systems have inconsistent views due to message faults. It uses a hidden canonical event log and derives system states via faulted delivery. Scoring measures executed monetary effects against a reference outcome.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present FinalityBench, an executable benchmark for that decision."}, "familyId": "bmf_815c68b62cd4", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_finalitybench_36a71d92", "indexedAt": "2026-09-07T00:39:11.978130Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/abhisheksharma2411/finalitybench", "data": null, "paper": "https://arxiv.org/abs/2609.04706", "pdf": "https://arxiv.org/pdf/2609.04706", "project": null, "report": "https://arxiv.org/abs/2609.04706"}, "metrics": [], "motivation": "A merchant's payment processor, ledger, ERP and bank feed are updated by messages that get delayed, duplicated, dropped and reordered, so for minutes at a time the four hold contradictory beliefs about the same order.", "name": "FinalityBench", "oneLine": "FinalityBench evaluates agent decisions in financial exception scenarios where payment systems have inconsistent views due to message faults. It uses a hidden canonical event log and derives system states via faulted delivery. Scoring measures executed monetary effects against a reference outcome.", "paperTitle": "FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04706", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T00:39:11.978130Z"}, "publications": [], "publishers": [{"name": "Abhishek Sharma", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/abhisheksharma2411/finalitybench"}], "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": null, "historyDate": null, "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": 123, "score": 23}, "method": "attention-ranking-v13", "rank": 123, "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": 318, "score": 23}, "method": "attention-ranking-v13", "rank": 318, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-04", "source": {"authors": ["Abhishek Sharma"], "categories": ["cs.AI"], "id": "2609.04706", "title": "FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04706"}, "sourceUpdatedAt": "2026-09-04T04:24:10Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Existing benchmarks often assume perfect information, while real financial systems suffer delays and conflicts. FinalityBench provides repeatable evaluation of agents under uncertainty, enabling comparison of policies and models on realistic financial decision-making, with a focus on irreversible actions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
