{"id":"W6930646685","doi":"10.5281/zenodo.14927285","title":"Data for LakeM2ARS Simulations","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Replicate; Data file; Data modeling; Data collection; Focus (optics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006469301,0.0002496316,0.0002811568,0.0004107254,0.003585261,0.002058737,0.002535539,0.0001343412,0.02743632],"category_scores_gemma":[0.005643484,0.0002764605,0.00006905673,0.0001421883,0.0002015819,0.0002424172,0.002135538,0.0003356679,0.001715732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001357287,"about_ca_system_score_gemma":0.00001821116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002294239,"about_ca_topic_score_gemma":0.0001047566,"domain_scores_codex":[0.9979087,0.0002029347,0.0004576222,0.0006859152,0.0003773834,0.0003675201],"domain_scores_gemma":[0.9964796,0.0001887871,0.0002673011,0.001750862,0.001214827,0.0000986069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002526616,0.000108677,2.622098e-8,0.0002696289,0.0001134324,0.000002678744,0.0007557184,0.00003177147,0.000002833498,0.03389087,0.9619648,0.00283428],"study_design_scores_gemma":[0.0003918913,0.00008226607,0.000001557609,0.00009958076,0.0001708044,0.000004224845,0.000357406,0.001246919,0.000001557482,0.003148874,0.9942206,0.0002742984],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000005076864,0.00003263999,0.00138999,0.003252882,0.001122118,0.0008334224,0.9797924,0.0004098073,0.01316165],"genre_scores_gemma":[0.0006046591,0.00004397259,0.0001781278,0.0002180156,0.001877476,9.714181e-8,0.9934648,0.0006158303,0.002996968],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03225581,"threshold_uncertainty_score":0.9999688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09214289419366276,"score_gpt":0.2923684810295865,"score_spread":0.2002255868359237,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}