{"id":"W4410104909","doi":"10.1111/sode.12803","title":"Young Children's Strategic Evaluation of Others’ Work","year":2025,"lang":"en","type":"article","venue":"Social Development","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Anonymity; Psychology; Affect (linguistics); Identification (biology); Developmental psychology; Work (physics); Social psychology; Early childhood; Applied psychology; Computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008998078,0.0001327339,0.0001867469,0.0001110602,0.0002143374,0.0000187172,0.0001450324,0.0001061962,0.001269747],"category_scores_gemma":[0.00001981453,0.0001320255,0.00005955519,0.0003960607,0.00005081356,0.00002007309,0.00004402754,0.0001360902,0.0001511274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001832265,"about_ca_system_score_gemma":0.0004962925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000312405,"about_ca_topic_score_gemma":0.00001643163,"domain_scores_codex":[0.9986363,0.0001480534,0.0003267087,0.0002714839,0.000388069,0.0002293996],"domain_scores_gemma":[0.9995905,0.00002077815,0.0001159828,0.0001054071,0.0001404754,0.0000268251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001684812,0.0005087921,0.4610402,0.00003018585,0.001170809,0.000002429152,0.05597364,0.00001261253,0.000192059,0.1093222,0.01187495,0.3597036],"study_design_scores_gemma":[0.0007364561,0.00001015178,0.9938631,0.00004759094,0.00004062662,4.222832e-7,0.0016239,0.000001252294,0.0001255934,0.001177721,0.002230602,0.0001425854],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8131095,0.0002427696,0.00004296218,0.0002334311,0.0005955787,0.0002738441,0.000001419517,0.00004454293,0.1854559],"genre_scores_gemma":[0.9951851,0.000001862817,0.0004759734,0.0001148055,0.0000883196,0.00005253758,0.00002678074,0.00001132946,0.004043241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5328229,"threshold_uncertainty_score":0.9996432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04503104995048626,"score_gpt":0.339062459856625,"score_spread":0.2940314099061387,"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."}}