{"meta":{"query_hash":"1c411d0ea448","filters":{"venue":"Theory and Practice of Science and Technology"},"cohort_total":1,"direct_labels_cover":0,"predictions_cover":1,"exported":1,"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/1c411d0ea448","api":"https://metacan.xera.ac/api/v1/cohort?venue=Theory+and+Practice+of+Science+and+Technology"},"results":[{"id":"W4412689102","doi":"10.47297/taposatwsp2633-456911.20250605","title":"Optimizing Random Forest with Apache Spark: A Survey on Distributed Machine Learning and Big Data Scalability","year":2025,"lang":"en","type":"article","venue":"Theory and Practice of Science and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"SPARK (programming language); Scalability; Big data; Random forest; Computer science; Database; Operating system; Data science; Distributed computing; Machine learning; Programming language","score_opus":0.03292571789572647,"score_gpt":0.30944922155147464,"score_spread":0.2765235036557482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412689102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4004462,0.0010781713,0.5850613,0.010970126,0.0000867141,0.00026768807,0.000056454934,0.00017698974,0.0018563296],"genre_scores_gemma":[0.99178225,0.0003020955,0.007780851,0.000072428775,0.000003901116,0.0000027555407,0.0000276362,0.0000021637793,0.000025903058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984354,0.000512807,0.00015059237,0.0005616254,0.00016506556,0.00017452812],"domain_scores_gemma":[0.99592197,0.0030731,0.00014345245,0.00064386136,0.00017237199,0.000045215707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011407244,0.000099560275,0.00017312224,0.000275116,0.00047030603,0.00013452982,0.00064628787,0.00006513117,7.281176e-7],"category_scores_gemma":[0.012816519,0.00007210388,0.00000380516,0.0013535878,0.002050256,0.0007711396,0.0007854177,0.00033717472,3.4828335e-7],"study_design_candidate":"theoretical_or_conceptual","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":[0.0014015904,0.00013758775,0.07874222,0.00005554616,0.00003225984,0.0000049157966,0.00031268937,0.00006869704,0.0018159698,0.47369358,0.000018265806,0.44371668],"study_design_scores_gemma":[0.010379719,0.0037671411,0.3663277,0.00064254383,0.00033587602,0.0006136883,0.0058777547,0.47880992,0.006582225,0.08951258,0.03572509,0.0014257464],"about_ca_topic_score_codex":0.00013700729,"about_ca_topic_score_gemma":0.00005668826,"teacher_disagreement_score":0.5913361,"about_ca_system_score_codex":0.000009254008,"about_ca_system_score_gemma":0.00011308071,"threshold_uncertainty_score":0.99549896},"labels":[],"label_agreement":null}]}