{"id":"W2887346961","doi":"10.1257/aer.20181065","title":"Testing the Waters: Behavior across Participant Pools","year":2021,"lang":"en","type":"article","venue":"American Economic Review","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Leverage (statistics); Sample (material); Population; Set (abstract data type); Amazon rainforest; Scale (ratio); Psychology; Statistics; Computer science; Geography; Ecology; Mathematics; Demography; Biology; Cartography; Sociology; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006541784,0.0001491498,0.0004071617,0.00000899336,0.0002191243,0.0002802949,0.0005941513,0.00001333047,0.00001941221],"category_scores_gemma":[0.0001552086,0.0001061818,0.0001288657,0.0002428347,0.0001751659,0.0001768994,0.0003081314,0.0001285301,0.0003568498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000057099,"about_ca_system_score_gemma":0.0001304925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001421814,"about_ca_topic_score_gemma":0.00001390224,"domain_scores_codex":[0.9984442,0.0001694792,0.000429967,0.0004391466,0.00007419002,0.0004429934],"domain_scores_gemma":[0.9982999,0.0002339517,0.000249707,0.001070196,0.0000482525,0.00009800114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[2.772578e-7,0.00001977362,0.00246594,0.00007936882,0.00002119956,0.00004401595,0.0003425622,0.0000573437,0.0003924537,0.0004417721,0.001357175,0.9947781],"study_design_scores_gemma":[0.0007659995,0.0003876098,0.1289877,0.006938313,0.0006394762,0.003380364,0.002806529,0.01630413,0.00651684,0.0004222755,0.8302368,0.002613995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9349986,0.03951937,0.00642789,0.01358888,0.0009357287,0.0007870122,0.00001014593,0.0003875785,0.003344792],"genre_scores_gemma":[0.9805227,0.00403271,0.00726859,0.007648152,0.0001341,0.0001367005,0.000002940945,0.00002148794,0.0002326243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9921641,"threshold_uncertainty_score":0.4586701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08043842403601754,"score_gpt":0.3246748597124279,"score_spread":0.2442364356764103,"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."}}