{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.06440", "kind": "paper", "url": "https://arxiv.org/abs/2607.06440"}, {"id": "gh:wuyuhang05/pipbench", "kind": "repo", "url": "https://github.com/wuyuhang05/PIPBench"}, {"kind": "website", "url": "https://wuyuhang05.github.io/PIPBench/"}], "authors": ["Yuhang Wu", "Shuxiang Zhang", "Wee Hian Ching", "Chi Zhang", "Miao Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.06440", "source_url": "https://arxiv.org/abs/2607.06440"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "PIPBench evaluates personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. It includes real-user and agent-based data across psychological and demographic profiles."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.06440", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.06440", "title": "PIPBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.06440", "modality": null, "name": "PIPBench", "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_pipbench_0f193694", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "adef0358673eb07f275b3e3001f5c20b31bbc9096325adbeebfb9322bc08e54c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.06440"}, "publisher": null, "released": "2026-07-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.06440", "source_url": "https://arxiv.org/abs/2607.06440"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-06440", "source": "claire_radar", "source_benchmark_id": "2607.06440", "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/wuyuhang05/PIPBench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.06440", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "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": "7c3605029971c551431e90afe5d31d46d04c2f5a5e1b1d5c900b143416d8891a", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PIPBench evaluates personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. It includes real-user and agent-based data across psychological and demographic profiles.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To this end, we introduce PIPBench, the first profile-inclusive benchmark for evaluating personalized image generation."}, "familyId": "bmf_76865cb5cf7c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/wuyuhang05/PIPBench", "url": "https://wuyuhang05.github.io/PIPBench/"}], "scope": "benchmark_repo", "url": "https://github.com/wuyuhang05/PIPBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_pipbench_0f193694", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/wuyuhang05/PIPBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.06440", "paper": "https://arxiv.org/abs/2607.06440", "pdf": "https://arxiv.org/pdf/2607.06440", "project": "https://wuyuhang05.github.io/PIPBench/", "report": "https://arxiv.org/abs/2607.06440"}, "metrics": [], "motivation": "Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences.", "name": "PIPBench", "oneLine": "PIPBench evaluates personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. It includes real-user and agent-based data across psychological and demographic profiles.", "paperTitle": "PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.06440", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "PIPBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://wuyuhang05.github.io/PIPBench/"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 381, "score": 23}, "method": "attention-ranking-v13", "rank": 381, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-07-07", "source": {"authors": ["Yuhang Wu", "Shuxiang Zhang", "Wee Hian Ching", "Chi Zhang", "Miao Liu"], "categories": ["cs.CV"], "id": "2607.06440", "title": "PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.06440"}, "sourceUpdatedAt": "2026-07-07T16:09:30Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing text-to-image benchmarks focus on prompt following but ignore individual aesthetic preferences. PIPBench addresses the evaluation gap for personalized generation, offering a standardized way to compare methods aligning outputs with user profiles."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
