{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.16175", "kind": "paper", "url": "https://arxiv.org/abs/2606.16175"}], "authors": ["Qiwei Yan", "Zhiqiang Yuan", "Zexi Jia", "Nanxing Hu", "Kailin Lyu", "Jie Zhou", "Jinchao Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.16175", "source_url": "https://arxiv.org/abs/2606.16175"}, "categories": ["Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "PAL-Bench evaluates evidence-grounded profile reconstruction from longitudinal personal albums, scoring agents on owner facts, identities, and relations with a seven-metric protocol."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.16175", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.16175", "title": "PAL-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tencent (China)", "University of Chinese Academy of Sciences", "Beihang University", "Chinese Academy of Sciences", "Institute of Automation"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.16175", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.16175", "source_url": "https://openalex.org/W7164939312"}, "key": "claire-radar:2606.16175", "modality": null, "name": "PAL-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_pal-bench_e5d27a42", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2dc5fb47eaac558da5f40f0d7566204b4eda398471578909a129ffa0fb1c5501", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.16175"}, "publisher": null, "released": "2026-06-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.16175", "source_url": "https://arxiv.org/abs/2606.16175"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-16175", "source": "claire_radar", "source_benchmark_id": "2606.16175", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Software & AI Compute"], "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/2606.16175", "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": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d51d5404520fd53b33f34db135127f437a7ce01430b90c28ba184dc277b194bb", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PAL-Bench evaluates evidence-grounded profile reconstruction from longitudinal personal albums, scoring agents on owner facts, identities, and relations with a seven-metric protocol.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract."}, "familyId": "bmf_645decf62e6a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_pal-bench_e5d27a42", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.16175", "paper": "https://arxiv.org/abs/2606.16175", "pdf": "https://arxiv.org/pdf/2606.16175", "project": null, "report": "https://arxiv.org/abs/2606.16175"}, "metrics": [], "motivation": "Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events.", "name": "PAL-Bench", "oneLine": "PAL-Bench evaluates evidence-grounded profile reconstruction from longitudinal personal albums, scoring agents on owner facts, identities, and relations with a seven-metric protocol.", "paperTitle": "PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.16175", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-15", "source": {"authors": ["Qiwei Yan", "Zhiqiang Yuan", "Zexi Jia", "Nanxing Hu", "Kailin Lyu", "Jie Zhou", "and Jinchao Zhang"], "categories": ["cs.AI"], "id": "2606.16175", "title": "PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums", "type": "arxiv", "url": "https://arxiv.org/abs/2606.16175"}, "sourceUpdatedAt": "2026-06-15T03:42:59Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing benchmarks test sub-problems of multimodal understanding, but PAL-Bench addresses the gap in album-scale reconstruction with social identity binding and evidence citation, offering a controlled public-record contract for evaluating perceptual entity resolution and multimodal integration."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
