{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":5,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"d9ff4133a46a","filters":{"venue":"Conference on Innovative Data Systems Research"}},"results":[{"id":"W3146147323","doi":"","title":"Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics.","year":2021,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Analytics; Data warehouse; Data science; Database","authors":[{"name":"Matei Zaharia","is_ca":false},{"name":"Ali Ghodsi","is_ca":true},{"name":"Reynold Xin","is_ca":false},{"name":"Michael Armbrust","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.946872203848267,"gpt":0.6271471361658597,"spread":0.3197250676824073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004961494,0.001172767,0.0008321572,0.003113824,0.001535476,0.005280169,0.003856873,0.001416581,0.02585185],"category_scores_gemma":[0.01085848,0.001353781,0.001070228,0.003616216,0.001378592,0.01531218,0.01057294,0.003468674,0.01116495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007915081,"about_ca_system_score_gemma":0.004133927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005541218,"about_ca_topic_score_gemma":0.007719381,"domain_scores_codex":[0.9959047,0.0004049517,0.0002769852,0.0004677093,0.0024827,0.0004628987],"domain_scores_gemma":[0.9918575,0.00181728,0.0007296607,0.002428088,0.001412067,0.001755406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002503405,0.0008971508,0.00661137,0.0009564207,0.0003214015,0.0008151053,0.001727654,0.001705671,0.0407924,0.03384379,0.6478489,0.2619768],"study_design_scores_gemma":[0.0009105901,0.0006041232,0.01117215,0.0003720092,0.0002282819,0.0005993579,0.0007433756,0.02883803,0.03267048,0.04026911,0.8831127,0.0004798861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.06195461,0.003726544,0.3011427,0.01107496,0.001890227,0.001886712,0.04864962,0.4991799,0.07049476],"genre_scores_gemma":[0.1844584,0.003767609,0.3934363,0.005636442,0.00166515,0.002605648,0.1740969,0.0449231,0.1894105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02585185,"threshold_uncertainty_score":0.08648306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2585438896","doi":"","title":"The data civilizer system","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","authors":[{"name":"Dong Deng","is_ca":false},{"name":"Raul Castro Fernandez","is_ca":false},{"name":"Ziawasch Abedjan","is_ca":false},{"name":"Sibo Wang","is_ca":false},{"name":"Michael Stonebraker","is_ca":false},{"name":"Ahmed K. Elmagarmid","is_ca":false},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Samuel Madden","is_ca":false},{"name":"Mourad Ouzzani","is_ca":false},{"name":"Nan Tang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6414419922836844,"gpt":0.5044311967031525,"spread":0.1370107955805319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00725413,0.001461874,0.001763607,0.006275731,0.001439812,0.006318755,0.002672391,0.001623552,0.1199788],"category_scores_gemma":[0.02564324,0.001515758,0.001438842,0.005629128,0.001162419,0.007126191,0.005836281,0.003323982,0.1106685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468501,"about_ca_system_score_gemma":0.004278447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003654358,"about_ca_topic_score_gemma":0.002024312,"domain_scores_codex":[0.994228,0.001479811,0.0007081583,0.001422849,0.001715909,0.0004451861],"domain_scores_gemma":[0.9850706,0.002685582,0.000473312,0.008820027,0.002072307,0.0008781185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001103628,0.0002016102,0.002651093,0.0003854377,0.0001651075,0.0002048712,0.0003120849,0.001514807,0.005294672,0.03471392,0.7811111,0.1723416],"study_design_scores_gemma":[0.0003511275,0.00008609988,0.001560797,0.00008932059,0.00006263683,0.0002184559,0.00009128368,0.01756111,0.01303822,0.01796874,0.9488799,0.00009229402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.008063158,0.001111095,0.232193,0.004031873,0.001459352,0.001158295,0.1097401,0.571889,0.07035417],"genre_scores_gemma":[0.1158024,0.001648258,0.1754462,0.003348728,0.001157026,0.001850672,0.4921064,0.1012466,0.1073937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1199788,"threshold_uncertainty_score":0.4013689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2583699183","doi":"","title":"Data Ingestion for the Connected World.","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ingestion; Medicine","authors":[{"name":"John Meehan","is_ca":false},{"name":"Cansu Aslantas","is_ca":false},{"name":"Stan Zdonik","is_ca":false},{"name":"Nesime Tatbul","is_ca":false},{"name":"Jiang Du","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.9484017230905639,"gpt":0.6713623530691826,"spread":0.2770393700213813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008336633,0.0009813579,0.001015283,0.003465313,0.002526005,0.009847531,0.002847907,0.002645242,0.02167739],"category_scores_gemma":[0.02964368,0.0008862456,0.001240175,0.005397003,0.001902352,0.01842966,0.008626588,0.002972838,0.01006711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001470906,"about_ca_system_score_gemma":0.003430326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883541,"about_ca_topic_score_gemma":0.003923412,"domain_scores_codex":[0.9952683,0.001658594,0.0004135694,0.0006789845,0.001659924,0.0003205624],"domain_scores_gemma":[0.9777657,0.006688742,0.000601296,0.01075168,0.003140142,0.001052456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001537388,0.0003571335,0.01259934,0.0008803311,0.0003752091,0.000926865,0.001316612,0.008563974,0.005718277,0.1195946,0.3800803,0.4680501],"study_design_scores_gemma":[0.0002322377,0.0001991492,0.00607223,0.001023006,0.0002622201,0.001010575,0.002236554,0.1126787,0.02027926,0.270132,0.5857106,0.0001634312],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05185302,0.0146488,0.6837714,0.0453192,0.0055824,0.001124915,0.02441284,0.09136271,0.08192468],"genre_scores_gemma":[0.4607695,0.01063785,0.4175049,0.004765498,0.002063966,0.0005849376,0.05253784,0.01098053,0.04015487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02167739,"threshold_uncertainty_score":0.07251805,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2397606137","doi":"","title":"A Case for Thread Migration.","year":2013,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Mobile Agent-Based Network Management","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Thread (computing); Programming language","authors":[{"name":"Pınar Tözün","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4392051732051863,"gpt":0.4339388316145014,"spread":0.005266341590684898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006928791,0.0004826823,0.0003707273,0.001011028,0.006228,0.008071966,0.002598912,0.009125219,0.01471527],"category_scores_gemma":[0.02921455,0.000736595,0.0008871627,0.001076395,0.005056058,0.01802652,0.005772559,0.007104723,0.003471901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002139868,"about_ca_system_score_gemma":0.002977547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003800773,"about_ca_topic_score_gemma":0.005033808,"domain_scores_codex":[0.9953178,0.002151704,0.0001831025,0.0006339346,0.0007180034,0.0009954824],"domain_scores_gemma":[0.9868051,0.005205676,0.0007815376,0.004029855,0.001359126,0.001818638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001928846,0.00008262676,0.002555992,0.00007010035,0.0000170273,0.006014947,0.004568239,0.000818259,0.001185437,0.9046693,0.04529541,0.03452975],"study_design_scores_gemma":[0.0001325593,0.0000689944,0.0008534126,0.0003478314,0.00004605715,0.007507106,0.004145877,0.01404501,0.002279594,0.4953999,0.4751165,0.00005719853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.08441527,0.005705832,0.2499377,0.2415019,0.008077599,0.000515104,0.0002699495,0.00256537,0.4070113],"genre_scores_gemma":[0.74077,0.002226808,0.1261696,0.01785167,0.00208543,0.0005949861,0.0002096128,0.001109676,0.1089822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01471527,"threshold_uncertainty_score":0.04922754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963114423","doi":"","title":"Reprowd: Crowdsourced Data Processing Made Reproducible.","year":2016,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Crowdsourcing; Computer science; Data science; Multidisciplinary approach; Open research; World Wide Web","authors":[{"name":"Ruochen Jiang","is_ca":true},{"name":"Jiannan Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8778779383011985,"gpt":0.5952426953214541,"spread":0.2826352429797444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02941054,0.002412522,0.001897056,0.007062745,0.002707317,0.006620785,0.007555971,0.002977458,0.01894837],"category_scores_gemma":[0.1073552,0.001844111,0.003039171,0.006113676,0.003079507,0.007461583,0.02518695,0.003915095,0.02025621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001404129,"about_ca_system_score_gemma":0.005841531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00625838,"about_ca_topic_score_gemma":0.004723717,"domain_scores_codex":[0.9755492,0.007885529,0.002536699,0.005275195,0.007880658,0.00087265],"domain_scores_gemma":[0.9086402,0.02357496,0.003642102,0.05272483,0.007893927,0.003524007],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001850946,0.0004748935,0.006229317,0.003456152,0.001516698,0.001405688,0.004040576,0.0104391,0.01999376,0.030701,0.6506087,0.2692831],"study_design_scores_gemma":[0.0008089385,0.0002573589,0.005050309,0.000637582,0.000198797,0.000506797,0.001081367,0.07910993,0.02562798,0.1093284,0.7768274,0.0005651932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005100691,0.000774912,0.5893799,0.002556002,0.001851043,0.003124965,0.04108224,0.341922,0.01420827],"genre_scores_gemma":[0.07155457,0.0008817337,0.7256321,0.00221038,0.0005709527,0.006163976,0.1294776,0.04709549,0.01641313],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9705895,"threshold_uncertainty_score":0.1555397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}