{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24256", "kind": "paper", "url": "https://arxiv.org/abs/2606.24256"}, {"id": "gh:tailor-bench/code", "kind": "repo", "url": "https://github.com/tailor-bench/code"}], "authors": ["Bingxuan Li", "Yining Hong", "Cheng Qian", "Hyeonjeong Ha", "Jiateng Liu", "Zhenhailong Wang", "Yue Guo", "Yunzhu Li", "Heng Ji"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24256", "source_url": "https://arxiv.org/abs/2606.24256"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Tailor-Bench evaluates visual world models on simulating irregular physical interactions with three scenario modes (regular, unconventional, impossible) and predictive/descriptive generation settings."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24256", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24256", "title": "Tailor-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Illinois Urbana-Champaign", "Stanford University", "Columbia University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24256", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24256", "source_url": "https://openalex.org/W7165771808"}, "key": "claire-radar:2606.24256", "modality": null, "name": "Tailor-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_tailor-bench_613b036f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "518f522af809a518b6172da42daf0a28e6946414d7e66c15ea562414ed3a5738", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24256"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24256", "source_url": "https://arxiv.org/abs/2606.24256"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24256", "source": "claire_radar", "source_benchmark_id": "2606.24256", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/tailor-bench/code", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 40, "hfPaperUrl": "https://huggingface.co/papers/2606.24256", "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": "2026-10-04", "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": "c52a5c3176cb1aaeda5789a3e911165d98cebdc86bb78e307c888f7694d5ceb4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Tailor-Bench evaluates visual world models on simulating irregular physical interactions with three scenario modes (regular, unconventional, impossible) and predictive/descriptive generation settings.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions."}, "familyId": "bmf_a1f4ed1db648", "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/tailor-bench/code", "url": "https://github.com/tailor-bench/code"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/tailor-bench/code", "url": "https://huggingface.co/papers/2606.24256"}], "scope": "project_repo", "url": "https://github.com/tailor-bench/code", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_tailor-bench_613b036f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/tailor-bench/code", "data": null, "hfPaper": "https://huggingface.co/papers/2606.24256", "paper": "https://arxiv.org/abs/2606.24256", "pdf": "https://arxiv.org/pdf/2606.24256", "project": null, "report": "https://arxiv.org/abs/2606.24256"}, "metrics": [], "motivation": "Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented.", "name": "Tailor-Bench", "oneLine": "Tailor-Bench evaluates visual world models on simulating irregular physical interactions with three scenario modes (regular, unconventional, impossible) and predictive/descriptive generation settings.", "paperTitle": "Trimming the Long-Tail of Visual World Modeling Evaluation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24256", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "GitHub", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/tailor-bench/code"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Bingxuan Li", "Yining Hong", "Cheng Qian", "Hyeonjeong Ha", "Jiateng Liu", "Zhenhailong Wang", "Yue Guo", "Yunzhu Li", "Heng Ji"], "categories": ["cs.CV"], "id": "2606.24256", "title": "Trimming the Long-Tail of Visual World Modeling Evaluation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24256"}, "sourceUpdatedAt": "2026-06-23T07:43:41Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Current benchmarks focus on common interactions; Tailor-Bench exposes the long-tail gap in physical world modeling, testing generalization and constraint awareness beyond typical scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
