{"meta":{"query_hash":"899828b34cd6","filters":{"venue":"Discover Data"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/899828b34cd6","api":"https://metacan.xera.ac/api/v1/cohort?venue=Discover+Data"},"results":[{"id":"W4362554721","doi":"10.1007/s44248-023-00002-y","title":"Evaluating Word Embedding Feature Extraction Techniques for Host-Based Intrusion Detection Systems","year":2023,"lang":"en","type":"article","venue":"Discover Data","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Vector Institute","keywords":"Word2vec; Computer science; Intrusion detection system; Word embedding; Host (biology); Embedding; System call; Data mining; Feature (linguistics); Artificial intelligence; Feature extraction; Machine learning","score_opus":0.0767570373767207,"score_gpt":0.378191707457228,"score_spread":0.30143467008050734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362554721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022266483,0.00010412083,0.972852,0.0005563041,0.0022944056,0.0007851571,0.00009742636,0.00096906844,0.00007507142],"genre_scores_gemma":[0.9614083,0.00008113216,0.035741296,0.00021778156,0.0010507748,0.00029071252,0.0008760083,0.00003952991,0.00029445536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822,0.00012983054,0.00025065185,0.0006864509,0.00040948324,0.00030356197],"domain_scores_gemma":[0.9981648,0.0002476422,0.00019600033,0.0012338372,0.00010254278,0.000055213088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014407473,0.00016418849,0.00015944646,0.00025094164,0.0004700295,0.00054575485,0.0009279488,0.0001524854,0.000005211373],"category_scores_gemma":[0.0002735595,0.00015409407,0.00005744145,0.00092404836,0.000019693829,0.002199349,0.000541013,0.00023606174,0.000030698415],"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":[0.00014602735,0.00006995533,0.000032597563,0.000199952,0.00003124988,0.0000070660035,0.0002445736,0.005052324,0.10412728,0.0012705304,0.021200333,0.8676181],"study_design_scores_gemma":[0.00022634625,0.0001432759,0.00016502893,0.00012817529,0.000015504029,0.000008810456,0.00006679635,0.9473455,0.020397795,0.00029183552,0.031017527,0.00019340805],"about_ca_topic_score_codex":0.000068279776,"about_ca_topic_score_gemma":0.000047639256,"teacher_disagreement_score":0.94229317,"about_ca_system_score_codex":0.00009650414,"about_ca_system_score_gemma":0.00006572146,"threshold_uncertainty_score":0.6283774},"labels":[],"label_agreement":null},{"id":"W4362677817","doi":"10.1007/s44248-023-00003-x","title":"A systematic literature review of cyber-security data repositories and performance assessment metrics for semi-supervised learning","year":2023,"lang":"en","type":"review","venue":"Discover Data","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Computer science; Scarcity; Machine learning; Data science; Limiting; Artificial intelligence; Computer security; Engineering","score_opus":0.07736740096400081,"score_gpt":0.3581277139363865,"score_spread":0.2807603129723857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362677817","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.576813e-7,0.9844811,0.010997188,0.000030327987,0.000858314,0.0019423093,0.0015613,0.000084822816,0.00004379014],"genre_scores_gemma":[0.0000037129228,0.98931503,0.0023350462,0.00003626027,0.00023384854,0.00013574788,0.0078094597,0.000031611045,0.00009929415],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9961599,0.00050768815,0.0012722597,0.0011955292,0.0005930258,0.00027156435],"domain_scores_gemma":[0.992757,0.0009147269,0.0010781604,0.005003216,0.0001689914,0.000077897304],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003299735,0.000393319,0.001980369,0.00022880026,0.00022427946,0.0005996376,0.0045541795,0.00021200326,0.0000019630297],"category_scores_gemma":[0.00124728,0.00029211107,0.00015711806,0.0020597917,0.000041101575,0.0025676675,0.0061053257,0.00059324014,0.000004047779],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012757395,0.00002139806,0.0000022294037,0.91980743,0.00016820377,0.0000050765266,0.00007238961,2.7899526e-7,3.976955e-8,0.0005716657,0.0040328987,0.075317115],"study_design_scores_gemma":[0.000068649606,0.000068277615,7.5715445e-7,0.59532106,0.00066095305,0.000051493385,0.000006753192,0.03287487,2.1451582e-7,0.000027622656,0.37067726,0.00024208546],"about_ca_topic_score_codex":0.000009084343,"about_ca_topic_score_gemma":0.0000047806648,"teacher_disagreement_score":0.36664435,"about_ca_system_score_codex":0.00005809448,"about_ca_system_score_gemma":0.00029463024,"threshold_uncertainty_score":0.9999531},"labels":[],"label_agreement":null},{"id":"W4392721011","doi":"10.1007/s44248-024-00008-0","title":"Canadian agriculture technology adoption","year":2024,"lang":"en","type":"article","venue":"Discover Data","topic":"Agricultural Innovations and Practices","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"MacEwan University; Government of Alberta; Olds College","funders":"","keywords":"Agriculture; Business; Agricultural economics; Geography; Economics; Archaeology","score_opus":0.038935506991865584,"score_gpt":0.26517855602823065,"score_spread":0.22624304903636505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392721011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90057576,0.0030618173,0.000019258146,0.075932994,0.00071408786,0.00027512916,0.004044444,0.00036365545,0.0150128845],"genre_scores_gemma":[0.9901686,0.00013410347,0.00008874225,0.00027414158,0.00037885367,0.000008002325,0.006756957,5.6181744e-7,0.002190079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927384,0.0000142117615,0.00010766334,0.00031634132,0.00009671046,0.00019124849],"domain_scores_gemma":[0.9997288,0.00004312837,0.000022756407,0.00011989045,0.000037462156,0.00004796214],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010919242,0.00009172632,0.00006465706,0.000024425259,0.00017315768,0.00032009624,0.000501382,0.00010422953,0.0009603129],"category_scores_gemma":[0.000029000803,0.000025761055,0.000019972402,0.0011193773,0.000021103882,0.0010309089,0.00013974443,0.00015962704,0.00035965233],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042349743,0.00003923009,0.0039417823,0.00001549682,0.000061293846,0.000056141547,0.00004258326,0.0000034829843,0.07776956,0.053041242,0.57255775,0.29246718],"study_design_scores_gemma":[0.000011916066,0.000021422204,0.01392875,0.000021588745,0.000014000566,0.000025228703,0.00037265502,0.00007967981,0.00016677428,0.0007903879,0.98444647,0.000121123485],"about_ca_topic_score_codex":0.03736804,"about_ca_topic_score_gemma":0.26860505,"teacher_disagreement_score":0.41188872,"about_ca_system_score_codex":0.000039891333,"about_ca_system_score_gemma":0.000026276275,"threshold_uncertainty_score":0.999953},"labels":[],"label_agreement":null},{"id":"W4414909223","doi":"10.1007/s44248-025-00067-x","title":"A comparative case study on the performance of global sensitivity analysis methods on digit classification","year":2025,"lang":"en","type":"article","venue":"Discover Data","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sensitivity (control systems); MNIST database; Key (lock); Deep learning; Digit recognition","score_opus":0.3825434191462059,"score_gpt":0.5072527023867561,"score_spread":0.12470928324055025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414909223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71664596,0.000007223763,0.2806543,0.00016062948,0.000082168095,0.0002213178,0.00041716566,0.000009890315,0.001801314],"genre_scores_gemma":[0.9988631,6.567252e-7,0.00085281325,0.00005479131,0.000009196278,0.0000070671545,0.0000281595,0.0000015777011,0.00018263278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978663,0.0007157558,0.0003470313,0.00047778565,0.0004891557,0.00010398272],"domain_scores_gemma":[0.99413455,0.0033819273,0.00013496251,0.0022179259,0.00010473517,0.000025895366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037030752,0.00011080716,0.00033372632,0.00010143532,0.00012248656,0.00012041348,0.00070303946,0.000026609292,0.000016024676],"category_scores_gemma":[0.0014812084,0.00005837535,0.000061914245,0.0020010273,0.00009956721,0.00023159188,0.0002990106,0.00009795238,0.000023415574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007363231,0.00424462,0.40116376,0.000033316246,0.004291349,0.00023799684,0.004697958,0.4206906,0.0004760856,0.06463782,0.044371255,0.054418914],"study_design_scores_gemma":[0.00019103465,0.00013229097,0.27397153,0.000017338449,0.0003602116,0.0000065514137,0.006454333,0.7177824,0.00021431183,0.00037942766,0.00038107525,0.00010953494],"about_ca_topic_score_codex":0.00013094986,"about_ca_topic_score_gemma":0.00013036616,"teacher_disagreement_score":0.29709175,"about_ca_system_score_codex":0.000048775168,"about_ca_system_score_gemma":0.00008010935,"threshold_uncertainty_score":0.23804776},"labels":[],"label_agreement":null},{"id":"W7117471227","doi":"10.1007/s44248-025-00096-6","title":"Interpretability taxonomy: an approach for artificial intelligence developers technique selection","year":2025,"lang":"en","type":"article","venue":"Discover Data","topic":"Explainable Artificial Intelligence (XAI)","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":"University of Guelph","funders":"","keywords":"Interpretability; Operationalization; CLARITY; Taxonomy (biology); Categorization; Selection (genetic algorithm); Construct (python library)","score_opus":0.14090403599969797,"score_gpt":0.3543921964187081,"score_spread":0.21348816041901014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117471227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006867464,0.000027941687,0.99484974,0.0003442229,0.00031788755,0.001516034,0.00009491338,0.00023466973,0.0019278444],"genre_scores_gemma":[0.5526999,0.0000047049443,0.44580963,0.00028327797,0.00006139006,0.0007434413,0.00027680895,0.000012064181,0.00010874078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745554,0.00013480325,0.00050734676,0.0012772536,0.00018484525,0.0004402304],"domain_scores_gemma":[0.9971895,0.00015509462,0.00010163933,0.0022864935,0.00018132306,0.00008595455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013774362,0.00022788036,0.00023624962,0.00020153257,0.00028869652,0.000548626,0.0039144685,0.00011988575,0.0000145072545],"category_scores_gemma":[0.00048559313,0.00022248067,0.000059276266,0.0010407643,0.00013829766,0.0033436494,0.001320468,0.00021624935,0.00001698738],"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":[0.000109567176,0.0006327768,0.0010216984,0.00012044472,0.000060462145,0.0000015626848,0.00057740504,0.0017057776,0.003882712,0.6292914,0.0017492226,0.36084697],"study_design_scores_gemma":[0.000028145601,0.00008893469,0.000092133414,0.000030623647,0.00001809444,0.0000040106424,0.0006693789,0.8129867,0.123963654,0.051709075,0.010039324,0.00036993553],"about_ca_topic_score_codex":0.00029923068,"about_ca_topic_score_gemma":0.00025096405,"teacher_disagreement_score":0.8112809,"about_ca_system_score_codex":0.00019019932,"about_ca_system_score_gemma":0.00056002726,"threshold_uncertainty_score":0.9072498},"labels":[],"label_agreement":null}]}