{"schema":"https://pith.science/schemas/pith-integrity/v1.json","pith_number":"2605.17894","arxiv_id":"2605.17894","integrity":{"available":true,"endpoint":"/pith/2605.17894/integrity.json","summary":{"critical":0,"advisory":3,"informational":0,"by_detector":{"doi_compliance":{"total":3,"critical":0,"advisory":3,"informational":0}}},"clean":false,"detectors_run":[{"name":"claim_evidence","version":"1.0.0","status":"completed","ran_at":"2026-05-21T01:02:17.597070Z","findings_count":0},{"name":"doi_title_agreement","version":"1.0.0","status":"completed","ran_at":"2026-05-20T11:01:23.686017Z","findings_count":0},{"name":"doi_compliance","version":"1.0.0","status":"completed","ran_at":"2026-05-20T10:43:01.519882Z","findings_count":3},{"name":"ai_meta_artifact","version":"1.0.0","status":"skipped","ran_at":"2026-05-20T00:34:07.500724Z","findings_count":0}],"findings":[{"detector":"doi_compliance","finding_type":"recoverable_identifier","severity":"advisory","verdict_class":"incontrovertible","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.11009.14) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detected_doi":"10.48550/arXiv.2508.11009.14","detected_arxiv_id":null,"ref_index":28,"audited_at":"2026-05-20T10:43:01.519882Z"},{"detector":"doi_compliance","finding_type":"recoverable_identifier","severity":"advisory","verdict_class":"incontrovertible","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1609/aaai.v38i17.29868.Guangfu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detected_doi":"10.1609/aaai.v38i17.29868.Guangfu","detected_arxiv_id":null,"ref_index":6,"audited_at":"2026-05-20T10:43:01.519882Z"},{"detector":"doi_compliance","finding_type":"recoverable_identifier","severity":"advisory","verdict_class":"incontrovertible","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.findings-emnlp.722.Karan) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detected_doi":"10.18653/v1/2023.findings-emnlp.722.Karan","detected_arxiv_id":null,"ref_index":23,"audited_at":"2026-05-20T10:43:01.519882Z"}],"snapshot_sha256":"6d5fad397e1fa00b2f89067cd1d937c3e8a07b27d22edee5becca169f818dab4"},"events":[{"event_id":5018,"event_type":"pith.integrity.v1","payload_sha256":"3d42032d392380c8efc8b90b8773707745100ddf55a693053fa8799585fada10","signature_b64":"KewU1zy4K+nqOsOfi5SqVWTdPJpYs92H+WHceDFd/BOdl+BikDnZTOan1t7B5CYf6uxCRyQ1oZONNZKyHmElBg==","signing_key_id":"pith-v1-2026-05","created_at":"2026-05-20T10:47:53.597550+00:00","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.11009.14) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.48550/arXiv. 2508.11009. 14 Hengwei Ye, Yuanting Guan, Yuxuan Ge, Tianying Zhu, Zhenhan Guan, Yijia Zhong, Yijing Zhang, Han Zhang, Yingna Wu, and Zheng Tian. Children’s intelligence tests pose challenges for mllms? kidgym: A 2d gri","arxiv_id":"2605.17894","detector":"doi_compliance","evidence":{"ref_index":28,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.48550/arXiv. 2508.11009. 14 Hengwei Ye, Yuanting Guan, Yuxuan Ge, Tianying Zhu, Zhenhan Guan, Yijia Zhong, Yijing Zhang, Han Zhang, Yingna Wu, and Zheng Tian. Children’s intelligence tests pose challenges for mllms? kidgym: A 2d gri","reconstructed_doi":"10.48550/arXiv.2508.11009.14"},"severity":"advisory","ref_index":28,"audited_at":"2026-05-20T10:43:01.519882Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2508.11009.14","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"37a3ef768125275692541e7b1363da4edb4ced765928ec7b9365853e1f30fc06","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null}},{"event_id":5017,"event_type":"pith.integrity.v1","payload_sha256":"f370b095062dd1984dbc3e9f6a702794a08ea411d7698131ad8c3bdb80f2fa75","signature_b64":"5gslWY9gwOsmW4V6ULAN5FW4TB4xxAl4DonTGcfTR53AQRqFNxDCQrCZV8JIEyToPFa/k1Xb3eOMIjOipdrACg==","signing_key_id":"pith-v1-2026-05","created_at":"2026-05-20T10:47:53.596201+00:00","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.findings-emnlp.722.Karan) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.18653/v1/2023. findings-emnlp.722. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Chou, Irene Kraus, Brendan Bechtoli, et al. Large language models encode clinical knowledge.N","arxiv_id":"2605.17894","detector":"doi_compliance","evidence":{"ref_index":23,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.18653/v1/2023. findings-emnlp.722. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Chou, Irene Kraus, Brendan Bechtoli, et al. Large language models encode clinical knowledge.N","reconstructed_doi":"10.18653/v1/2023.findings-emnlp.722.Karan"},"severity":"advisory","ref_index":23,"audited_at":"2026-05-20T10:43:01.519882Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2023.findings-emnlp.722.Karan","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"54d4a365c7c34dd36306df301de8a2dcb06eab6659ba2ad5792759c7760b11e6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null}},{"event_id":5016,"event_type":"pith.integrity.v1","payload_sha256":"c4c7f81eec5f918beaafb1b66d72e959d3a8e942c32ca154695d5b8453db667f","signature_b64":"qLHMCsDKSqr7H5VVOjWxudcMOjE8eI1x6UbfXjHutz+FB7Vw0ta8ONqdotyEo6xANBCt1oQFynAxOSN6p7yCAw==","signing_key_id":"pith-v1-2026-05","created_at":"2026-05-20T10:47:53.594789+00:00","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1609/aaai.v38i17.29868.Guangfu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1609/aaai. v38i17.29868. Guangfu Hao, Frederic Alexandre, and Shan Yu. Visual large language models exhibit human-level cognitive flexibility in the wisconsin card sorting test,","arxiv_id":"2605.17894","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1609/aaai. v38i17.29868. Guangfu Hao, Frederic Alexandre, and Shan Yu. Visual large language models exhibit human-level cognitive flexibility in the wisconsin card sorting test,","reconstructed_doi":"10.1609/aaai.v38i17.29868.Guangfu"},"severity":"advisory","ref_index":6,"audited_at":"2026-05-20T10:43:01.519882Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/aaai.v38i17.29868.Guangfu","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1ff9f8fda113b2aa6285b263a1daef659258d41e6dc65ab3c01f7be62ba8f90f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null}}],"endpoint_self":"/pith/2605.17894/integrity.json","protocol_url":"https://pith.science/pith-integrity-protocol"}