{"meta":{"query_hash":"aea2e2b14ad7","filters":{"venue":"Journal of Psychology and AI"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/aea2e2b14ad7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Psychology+and+AI"},"results":[{"id":"W4411035583","doi":"10.1080/29974100.2025.2503343","title":"Evaluating firearm examiner testimony using large language models: a comparison of standard and knowledge-enhanced AI systems","year":2025,"lang":"en","type":"article","venue":"Journal of Psychology and AI","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Shanghai","keywords":"Computer science; Forensic engineering; Natural language processing; Engineering","score_opus":0.06091395159346706,"score_gpt":0.4294073973453022,"score_spread":0.3684934457518351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411035583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97069955,0.00030728552,0.025689516,0.0002459541,0.000031645424,0.00036940325,0.00006676949,0.00026992997,0.0023200274],"genre_scores_gemma":[0.9609482,0.00012577667,0.0379081,0.0002015595,0.000024814864,0.0002098573,0.00007773554,0.000024085386,0.00047974463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98961747,0.0064306487,0.00077886134,0.0012440585,0.0017091088,0.00021992125],"domain_scores_gemma":[0.8837434,0.09690293,0.0072475784,0.007031571,0.003802419,0.0012720722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01990381,0.00080788764,0.0007704312,0.0009529577,0.0004131745,0.0025668691,0.0014000223,0.0013599958,0.0018511713],"category_scores_gemma":[0.11565859,0.0004953449,0.00071772496,0.00030332024,0.0008399,0.0030651065,0.002200957,0.0010189294,0.00050444243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022040213,0.006244673,0.11799137,0.00246601,0.0017748746,0.0011876192,0.013107803,0.09858706,0.10309659,0.006613265,0.0019367236,0.6249538],"study_design_scores_gemma":[0.0024292264,0.020310167,0.121122114,0.0007329003,0.001772874,0.0019414305,0.004335172,0.7293413,0.08472125,0.024383007,0.008162974,0.0007476274],"about_ca_topic_score_codex":0.0008321881,"about_ca_topic_score_gemma":0.0015367892,"teacher_disagreement_score":0.01990381,"about_ca_system_score_codex":0.0012327912,"about_ca_system_score_gemma":0.0011356772,"threshold_uncertainty_score":0.10526264},"labels":[],"label_agreement":null},{"id":"W4413773148","doi":"10.1080/29974100.2025.2545258","title":"AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts","year":2025,"lang":"en","type":"article","venue":"Journal of Psychology and AI","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child, Adolescent and Family Mental Health","funders":"","keywords":"Psychology; Psychotherapist; Competence (human resources); Exploratory research; Cognitive science; Social psychology; Sociology; Social science","score_opus":0.033336967492254836,"score_gpt":0.4432401068165597,"score_spread":0.40990313932430483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413773148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99424535,0.00006742203,0.0029623504,0.00029706804,0.0000037016896,0.00027369228,0.00002542789,0.000019098901,0.0021058843],"genre_scores_gemma":[0.99236876,0.000097581375,0.006252857,0.0001457451,0.0000040926825,0.00045435544,0.000038248745,0.000019452482,0.0006188974],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98649627,0.01109386,0.00032878527,0.0005617458,0.00086440676,0.0006549654],"domain_scores_gemma":[0.9680159,0.025991103,0.0018238866,0.0015519352,0.0011184072,0.0014988126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014384351,0.000436531,0.0004666118,0.0014843167,0.0028213407,0.0042232433,0.0013322599,0.0012055023,0.0021921396],"category_scores_gemma":[0.03626776,0.0006416894,0.00033358933,0.00086783175,0.0033436522,0.0035470577,0.005146992,0.0020719287,0.00038386698],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020603457,0.002338769,0.04449218,0.0002818418,0.00002016169,0.00080162723,0.9062355,0.00061129977,0.0029537347,0.0035601198,0.0006531721,0.03784555],"study_design_scores_gemma":[0.00013220981,0.0024849393,0.0602647,0.0003626794,0.00004800608,0.0013672485,0.89599645,0.007326518,0.004017437,0.0071942373,0.020694792,0.000110724475],"about_ca_topic_score_codex":0.0020780822,"about_ca_topic_score_gemma":0.003968785,"teacher_disagreement_score":0.014384351,"about_ca_system_score_codex":0.0028028735,"about_ca_system_score_gemma":0.0037822458,"threshold_uncertainty_score":0.07607257},"labels":[],"label_agreement":null},{"id":"W4414986010","doi":"10.1080/29974100.2025.2561692","title":"From human artefact to machine output: automating the “art” of psychological measurement","year":2025,"lang":"en","type":"article","venue":"Journal of Psychology and AI","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado da Bahia; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Automation; Measure (data warehouse); Set (abstract data type); Identification (biology)","score_opus":0.12206823465212999,"score_gpt":0.42830475883155705,"score_spread":0.30623652417942704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414986010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032850247,0.00032480058,0.95416474,0.0013187642,0.0001814297,0.0013508342,0.00036863514,0.0038181182,0.005622339],"genre_scores_gemma":[0.25237086,0.0003455919,0.74102664,0.00075006933,0.00012828136,0.0026021583,0.00043202858,0.00090895005,0.0014353704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9532445,0.0334894,0.0018236563,0.0036882635,0.007369418,0.00038484207],"domain_scores_gemma":[0.8091494,0.14359789,0.005661786,0.030932872,0.009773822,0.0008842649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044530496,0.0015116667,0.0011095601,0.0032350235,0.0008540827,0.004429583,0.002141013,0.0011771426,0.0061263484],"category_scores_gemma":[0.18897654,0.0008980994,0.0010382249,0.0017484591,0.00431728,0.005369659,0.005367821,0.0019305109,0.0033076433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047856054,0.0003832393,0.019699886,0.0015755772,0.00022512575,0.00013553863,0.007719095,0.003989456,0.026113916,0.023938876,0.007873251,0.90786755],"study_design_scores_gemma":[0.000591638,0.004638336,0.11833141,0.002845044,0.0004474401,0.0016231292,0.011316392,0.17455356,0.10950588,0.40248466,0.17282446,0.0008379624],"about_ca_topic_score_codex":0.0011831705,"about_ca_topic_score_gemma":0.001024042,"teacher_disagreement_score":0.044530496,"about_ca_system_score_codex":0.001191881,"about_ca_system_score_gemma":0.0023586561,"threshold_uncertainty_score":0.2355026},"labels":[],"label_agreement":null}]}