{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.02556", "kind": "paper", "url": "https://arxiv.org/abs/2606.02556"}], "authors": ["Anshun Asher Zheng", "Kanishka Misra", "David I. Beaver", "Junyi Jessy Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.02556", "source_url": "https://arxiv.org/abs/2606.02556"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Tests rule induction in goal-directed episodic tasks through text games, covering eight tasks across attribute and procedural induction families with controllable lexical grounding and identifiability conditions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.02556", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.02556", "title": "HERO'S JOURNEY"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The University of Texas at Austin"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.02556", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.02556", "source_url": "https://openalex.org/W7163156355"}, "key": "claire-radar:2606.02556", "modality": null, "name": "HERO'S JOURNEY", "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_hero-s-journey_260791d3", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "61329255b1dff30e3033e1b5110057eec53f398dea5630ab151d15af0d1ab6d9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.02556"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.02556", "source_url": "https://arxiv.org/abs/2606.02556"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-02556", "source": "claire_radar", "source_benchmark_id": "2606.02556", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.02556", "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", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "f2300d37789974d7bc2d7c042e56275c010d65a35c8714a823251140a5f065fa", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Tests rule induction in goal-directed episodic tasks through text games, covering eight tasks across attribute and procedural induction families with controllable lexical grounding and identifiability conditions.", "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 HERO'S JOURNEY, a benchmark for rule induction in goal-directed episodic tasks, where agents must infer hidden rules from demonstrations and act on them through multi-step execution."}, "familyId": "bmf_c5187f03b592", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_hero-s-journey_260791d3", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.02556", "paper": "https://arxiv.org/abs/2606.02556", "pdf": "https://arxiv.org/pdf/2606.02556", "project": null, "report": "https://arxiv.org/abs/2606.02556"}, "metrics": [], "motivation": "We introduce HERO'S JOURNEY, a benchmark for rule induction in goal-directed episodic tasks, where agents must infer hidden rules from demonstrations and act on them through multi-step execution.", "name": "HERO'S JOURNEY", "oneLine": "Tests rule induction in goal-directed episodic tasks through text games, covering eight tasks across attribute and procedural induction families with controllable lexical grounding and identifiability conditions.", "paperTitle": "HERO'S JOURNEY: Testing Complex Rule Induction with Text Games", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.02556", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "HERO'S JOURNEY Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.02556"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Anshun Asher Zheng", "Kanishka Misra", "David I. Beaver", "Junyi Jessy Li"], "categories": ["cs.CL"], "id": "2606.02556", "title": "HERO'S JOURNEY: Testing Complex Rule Induction with Text Games", "type": "arxiv", "url": "https://arxiv.org/abs/2606.02556"}, "sourceUpdatedAt": "2026-06-01T17:51:40Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Evaluates a specific cognitive capability in LLMs, revealing limitations in procedural induction and execution bottlenecks. Provides a structured testbed for studying rule learning and guiding method development."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
