{"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":"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":[0.86470485,0.002571647,0.12336938,0.00031192278,0.0003074479,0.0002170027,0.0014951711,0.00492529,0.0020972686],"genre_scores_gemma":[0.9057147,0.0006159516,0.08798498,0.00007873143,0.00006109755,0.000116550524,0.00382487,0.00013846184,0.0014646754],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884415,0.00032182434,0.00017502959,0.00024819543,0.0002885808,0.00012214934],"domain_scores_gemma":[0.9969163,0.0019290508,0.00021949825,0.00026828446,0.00058388023,0.000083005776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016372693,0.0012701295,0.00081867207,0.0016380395,0.00023794248,0.0007506537,0.00048740482,0.0006606099,0.0012717842],"category_scores_gemma":[0.0059690927,0.00020673429,0.0007091789,0.0011450682,0.00030676002,0.0018740204,0.00076250924,0.00066435867,0.0008269283],"study_design_candidate":"bench_or_experimental","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":[0.0018421035,0.0010375656,0.018354947,0.00065951183,0.00046500063,0.00019559734,0.00020062077,0.11504515,0.038278993,0.0011028493,0.005435574,0.8173822],"study_design_scores_gemma":[0.0000893301,0.0020262708,0.009892496,0.000041584764,0.00014930872,0.0003598788,0.00019326921,0.92928314,0.054878533,0.00094865484,0.0020943382,0.00004325674],"about_ca_topic_score_codex":0.0019219934,"about_ca_topic_score_gemma":0.0020678618,"teacher_disagreement_score":0.0019219934,"about_ca_system_score_codex":0.00043726002,"about_ca_system_score_gemma":0.0004361616,"threshold_uncertainty_score":0.008658767},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014958025,0.98535013,0.006773467,0.0011889245,0.00031157606,0.00025620457,0.0023654196,0.00020736526,0.002051107],"genre_scores_gemma":[0.008955919,0.9712867,0.013304355,0.00081042614,0.00023903641,0.0005955309,0.004274845,0.00009366979,0.0004396418],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9935408,0.0020379347,0.0015756312,0.0008411336,0.001876915,0.00012765492],"domain_scores_gemma":[0.9124775,0.07282084,0.0038632373,0.002326645,0.008119318,0.00039244563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013046726,0.0016660756,0.003127611,0.017503906,0.000724861,0.002853329,0.0028100756,0.0016947122,0.0037880803],"category_scores_gemma":[0.06099378,0.0009590143,0.0032423725,0.019351179,0.0012093362,0.0041426164,0.0016106265,0.0015313538,0.0015255924],"study_design_candidate":"systematic_review","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":[0.0001643939,0.00012094188,0.002650826,0.2339805,0.0011580115,0.0000987386,0.00035112782,0.0019194455,0.0007241939,0.0055690412,0.029209813,0.72405285],"study_design_scores_gemma":[0.00009817779,0.0005196658,0.012265271,0.3436985,0.0071117533,0.0010523312,0.00081057975,0.0036219351,0.0031260008,0.012024497,0.6153985,0.0002727605],"about_ca_topic_score_codex":0.005162123,"about_ca_topic_score_gemma":0.01022822,"teacher_disagreement_score":0.017503906,"about_ca_system_score_codex":0.0019334042,"about_ca_system_score_gemma":0.010816525,"threshold_uncertainty_score":0.068998516},"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":"other","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":[0.12673062,0.0055387495,0.002219356,0.006724952,0.0003772815,0.0005913143,0.29546905,0.0006217823,0.5617269],"genre_scores_gemma":[0.6026532,0.01692144,0.006941478,0.0017626411,0.00012277132,0.0005088449,0.12705803,0.0002229573,0.24380864],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99273694,0.00029699382,0.00021901123,0.00061827974,0.0049993023,0.0011294346],"domain_scores_gemma":[0.99029166,0.0005845147,0.00049460557,0.00027244148,0.007299069,0.0010577271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016607827,0.00078393164,0.00056093984,0.006940643,0.0030188677,0.003879146,0.001735664,0.00047887323,0.035683136],"category_scores_gemma":[0.008886772,0.00036428348,0.0010552353,0.01761272,0.0005447442,0.001166505,0.0013596099,0.0011507976,0.004612958],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002009934,0.00018878793,0.21818265,0.0017611544,0.0001808845,0.0003092392,0.004038593,0.0024962155,0.0009369392,0.03060248,0.40361238,0.33748963],"study_design_scores_gemma":[0.000021476137,0.00006212075,0.48887277,0.00034786895,0.00006674448,0.00009611507,0.0023962336,0.0010368561,0.0004421032,0.0007318426,0.505848,0.00007785931],"about_ca_topic_score_codex":0.993238,"about_ca_topic_score_gemma":0.9953334,"teacher_disagreement_score":0.06957196,"about_ca_system_score_codex":0.06957196,"about_ca_system_score_gemma":0.10691853,"threshold_uncertainty_score":0.5047822},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5882167,0.0024283084,0.39413652,0.0011931908,0.00011801082,0.000590839,0.00044617933,0.0006086881,0.012261533],"genre_scores_gemma":[0.9101187,0.000335725,0.08806735,0.00013866379,0.000026647604,0.0001643667,0.00019355757,0.00005349841,0.0009013432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990655,0.0058624824,0.00041983442,0.0009241856,0.0017111212,0.00042742427],"domain_scores_gemma":[0.91904974,0.070550755,0.0020253656,0.0038896159,0.0040267357,0.00045779895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019176608,0.001642923,0.0011160711,0.0028201498,0.0007653357,0.001691279,0.001168493,0.0019524428,0.0018759561],"category_scores_gemma":[0.040786512,0.00031208337,0.0011962104,0.0022401412,0.0015286745,0.0017808125,0.0018702637,0.001742073,0.00022099941],"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":[0.0010617116,0.00042091988,0.018700266,0.0006614456,0.00033629523,0.0005661306,0.0005190463,0.8396661,0.0046433248,0.016217548,0.0022976438,0.11490946],"study_design_scores_gemma":[0.000064898144,0.0006981561,0.0059477687,0.00009766328,0.000084827785,0.0003077333,0.00056259416,0.96568674,0.010181548,0.014532254,0.0017729116,0.00006282955],"about_ca_topic_score_codex":0.0031074525,"about_ca_topic_score_gemma":0.0036871592,"teacher_disagreement_score":0.019176608,"about_ca_system_score_codex":0.0021234956,"about_ca_system_score_gemma":0.000985834,"threshold_uncertainty_score":0.10141677},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015046653,0.002110592,0.9343568,0.009135784,0.00039562036,0.0028063492,0.0011365237,0.0013997324,0.03361193],"genre_scores_gemma":[0.06799558,0.001420573,0.9208638,0.00070593314,0.00012176342,0.0035776182,0.0017595183,0.00027338386,0.0032818266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95447177,0.022161288,0.0067793992,0.0040426166,0.0110050645,0.0015398354],"domain_scores_gemma":[0.88911676,0.058434613,0.0072402786,0.011177127,0.031729035,0.0023021442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048016373,0.0022018012,0.001830953,0.033672143,0.005814946,0.015057805,0.004545473,0.0043655625,0.0057167546],"category_scores_gemma":[0.122406535,0.0013926413,0.0031120675,0.018206773,0.007337368,0.022588223,0.007868591,0.005812129,0.002296243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000129088,0.00031192665,0.013831027,0.0025237822,0.00016080638,0.0006612518,0.054071166,0.002914925,0.002880008,0.5199071,0.020530421,0.38207844],"study_design_scores_gemma":[0.00008637302,0.00025293883,0.0064373096,0.0047986275,0.00019052446,0.0011009787,0.05669238,0.025615076,0.00211449,0.6088402,0.29365537,0.00021574697],"about_ca_topic_score_codex":0.0075552813,"about_ca_topic_score_gemma":0.007319084,"teacher_disagreement_score":0.048016373,"about_ca_system_score_codex":0.009204898,"about_ca_system_score_gemma":0.015726212,"threshold_uncertainty_score":0.25393784},"labels":[],"label_agreement":null}]}