{"id":"W2991191531","doi":"10.1037/bul0000220","title":"Crowdsourcing hypothesis tests: Making transparent how design choices shape research results.","year":2020,"lang":"en","type":"article","venue":"Psychological Bulletin","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":180,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Memorial University of Newfoundland; University of British Columbia; Booth University College","funders":"Marsden Fund; Knut och Alice Wallenbergs Stiftelse; Institut Européen d'Administration des Affaires; Austrian Science Fund; Jan Wallanders och Tom Hedelius Stiftelse samt Tore Browaldhs Stiftelse","keywords":"PsycINFO; Psychology; Statistical hypothesis testing; Consistency (knowledge bases); Empirical research; Test (biology); Crowdsourcing; Statistical power; Research design; Social psychology; Null hypothesis; Cognitive psychology; Applied psychology; Econometrics; Statistics; Computer science; MEDLINE; Mathematics; Artificial intelligence","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":["insufficient_payload"],"category_scores_codex":[0.002023384,0.0002866715,0.0004009234,0.0001442944,0.0004179644,0.0001538434,0.0008062028,0.0003718586,0.02772512],"category_scores_gemma":[0.00118733,0.0002385616,0.0002488673,0.0006239249,0.0002936524,0.00004631724,0.00007626016,0.001249478,0.009114407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006032592,"about_ca_system_score_gemma":0.00001332366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004042016,"about_ca_topic_score_gemma":0.000004637338,"domain_scores_codex":[0.9948989,0.001639663,0.0006707261,0.001189301,0.0004980264,0.001103342],"domain_scores_gemma":[0.9973075,0.001343085,0.0001666438,0.0005495194,0.0001445158,0.0004887639],"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":[0.003152425,0.001686803,0.001914787,0.00004965511,0.00005041681,0.0003007136,0.002118128,0.00001173002,0.001019279,0.000858347,0.7776706,0.2111671],"study_design_scores_gemma":[0.002904975,0.003575407,0.1872525,0.0002330398,0.00004802004,0.00004317132,0.001601404,0.00009261751,0.0001219931,0.0003694569,0.8031357,0.0006216792],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3475518,0.003058342,0.008503493,0.4685334,0.001767243,0.003096562,0.0002639424,0.001315402,0.1659099],"genre_scores_gemma":[0.9853423,0.00004826197,0.005655858,0.005322509,0.0005198801,0.0003127489,0.00001080032,0.00004599789,0.002741703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6377905,"threshold_uncertainty_score":0.9916571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6072536598472963,"score_gpt":0.5019315143195294,"score_spread":0.1053221455277669,"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."}}