{"meta":{"query_hash":"d9ff4133a46a","filters":{"venue":"Conference on Innovative Data Systems Research"},"cohort_total":5,"direct_labels_cover":1,"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/d9ff4133a46a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Conference+on+Innovative+Data+Systems+Research"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Thread (computing); Programming language","score_opus":0.4392051732051863,"score_gpt":0.4339388316145014,"score_spread":0.005266341590684898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397606137","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":[0.007533293,0.00009632522,0.9750239,0.0040873415,0.0006084349,0.005690206,0.00035501173,0.00016294536,0.006442506],"genre_scores_gemma":[0.98529804,0.000028180857,0.007691807,0.00017121747,0.00024487,0.0037431684,0.0005239033,0.000022423888,0.0022763852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623686,0.00053523364,0.000505607,0.0010986092,0.00089399173,0.000729704],"domain_scores_gemma":[0.99192476,0.00075796084,0.00015751683,0.0034889306,0.0035349512,0.00013588998],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034860026,0.00020825854,0.00025887243,0.0005307274,0.0004162701,0.0015497273,0.0036134077,0.00008011074,0.000088910325],"category_scores_gemma":[0.00039926014,0.0001740592,0.00002089772,0.0024698712,0.00016388937,0.001361854,0.0018193889,0.00037705092,0.0008177004],"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":[0.0000077325685,0.000066108376,0.00004552213,0.00009449619,0.000039269493,0.00012525305,0.00016722486,0.000033740827,0.00017114755,0.6381583,0.32510892,0.035982266],"study_design_scores_gemma":[0.0007070016,0.00056662346,0.00009193464,0.00022205368,0.0000030275628,0.00014431388,0.0011745909,0.8974717,0.0002554068,0.0077506667,0.091212265,0.0004003731],"about_ca_topic_score_codex":0.0015174692,"about_ca_topic_score_gemma":0.000120416,"teacher_disagreement_score":0.9777647,"about_ca_system_score_codex":0.00018660129,"about_ca_system_score_gemma":0.00040546444,"threshold_uncertainty_score":0.9999603},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ingestion; Medicine","score_opus":0.9484017230905639,"score_gpt":0.6713623530691826,"score_spread":0.27703937002138135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583699183","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":[0.005522109,0.0006263262,0.45330533,0.1717604,0.010070287,0.016485639,0.1798762,0.00026783245,0.16208589],"genre_scores_gemma":[0.9747884,0.000066857734,0.00028932886,0.00016640042,0.00048526344,0.0002847146,0.00710516,0.000018046507,0.01679582],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99250394,0.0013980637,0.00087368884,0.0015515607,0.003095837,0.000576882],"domain_scores_gemma":[0.94324183,0.0155006265,0.0010446927,0.03154089,0.008521804,0.0001501352],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.060575463,0.00018046139,0.0003630426,0.0006285084,0.0026699193,0.007006608,0.02731622,0.00007358223,0.0002100638],"category_scores_gemma":[0.07575348,0.00010639686,0.000017336664,0.0016988615,0.0010721635,0.0024670889,0.0123276105,0.000597105,0.00078612217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010513038,0.000038574115,0.00013999092,0.000021646012,0.000040798033,0.0000025329525,0.00006615131,0.0000017330412,0.00003463729,0.43471894,0.48719916,0.07763071],"study_design_scores_gemma":[0.00047053254,0.000094809686,0.0040212222,0.00017026968,0.000006161026,0.0000012349255,0.0036828965,0.06365814,0.00003278553,0.011803441,0.91589785,0.00016064102],"about_ca_topic_score_codex":0.0010904167,"about_ca_topic_score_gemma":0.0021297482,"teacher_disagreement_score":0.9692663,"about_ca_system_score_codex":0.0000614393,"about_ca_system_score_gemma":0.00044243576,"threshold_uncertainty_score":0.9999919},"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":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.6414419922836844,"score_gpt":0.5044311967031525,"score_spread":0.13701079558053186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585438896","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":[0.0057767523,0.0017229846,0.570177,0.03664406,0.0078568095,0.0036286362,0.019200578,0.0010382246,0.35395494],"genre_scores_gemma":[0.99527246,0.00009849805,0.0005788262,0.000016544303,0.00032251122,0.000060676815,0.0011088082,0.00001574625,0.0025259505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99417686,0.0010567576,0.00055867253,0.0016252573,0.001777166,0.0008053111],"domain_scores_gemma":[0.96531934,0.0009541845,0.00041834117,0.030773813,0.0023911146,0.00014320498],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.014865428,0.00022445788,0.0003606796,0.0002904342,0.004139095,0.009152149,0.045889173,0.00009965778,0.0000067357073],"category_scores_gemma":[0.0034968276,0.00014211779,0.000018444462,0.001222321,0.0007843953,0.0028282215,0.021050163,0.00083788973,0.0008002319],"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":[0.000012113286,0.00003257725,0.00039217802,0.00006721194,0.000112420894,0.00004364416,0.00008714563,8.4247483e-7,0.0001534632,0.7966109,0.1535977,0.0488898],"study_design_scores_gemma":[0.00047220718,0.0001255221,0.0018921099,0.00082892436,0.0000074938107,0.000032890417,0.0030701158,0.7378812,0.00008442844,0.00045267228,0.25472707,0.0004253858],"about_ca_topic_score_codex":0.0012448857,"about_ca_topic_score_gemma":0.0001892868,"teacher_disagreement_score":0.9894957,"about_ca_system_score_codex":0.00009898134,"about_ca_system_score_gemma":0.00067846774,"threshold_uncertainty_score":0.99997777},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Crowdsourcing; Computer science; Data science; Multidisciplinary approach; Open research; World Wide Web","score_opus":0.8778779383011985,"score_gpt":0.5952426953214541,"score_spread":0.2826352429797444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963114423","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":[0.10947283,0.0013060592,0.5122795,0.07458124,0.010918263,0.008692658,0.027779505,0.0013401315,0.25362977],"genre_scores_gemma":[0.9558611,0.000022617854,0.00077442307,0.00006555922,0.0005513675,0.000053780528,0.0011198781,0.00003125565,0.041520044],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98185563,0.002127251,0.0016841474,0.006587493,0.0066403216,0.0011051752],"domain_scores_gemma":[0.92328465,0.005346508,0.001127678,0.057644613,0.012173529,0.00042304158],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.09826914,0.00029989163,0.00053869205,0.0017025922,0.00088425924,0.004136809,0.02002726,0.00011843831,0.00048580323],"category_scores_gemma":[0.064143375,0.00017146196,0.000022055998,0.009011733,0.0009407128,0.0025805016,0.017534487,0.0005947058,0.0036819493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071208146,0.00009218704,0.00087233627,0.00003683477,0.000023607941,0.000024614928,0.00019449348,0.0000032972703,0.0036244933,0.019568635,0.5757372,0.39975113],"study_design_scores_gemma":[0.0010098931,0.00022636645,0.0038008364,0.0015802527,0.000007150498,0.000031072726,0.0066510695,0.054123316,0.0008903958,0.008143147,0.922855,0.0006814513],"about_ca_topic_score_codex":0.00025546213,"about_ca_topic_score_gemma":0.000024270708,"teacher_disagreement_score":0.8463882,"about_ca_system_score_codex":0.0001398682,"about_ca_system_score_gemma":0.0009407757,"threshold_uncertainty_score":0.9970938},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Analytics; Data warehouse; Data science; Database","score_opus":0.946872203848267,"score_gpt":0.6271471361658597,"score_spread":0.31972506768240727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146147323","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":[0.249746,0.0027703966,0.5759263,0.023073073,0.0034406069,0.009840389,0.06722741,0.00019456184,0.06778129],"genre_scores_gemma":[0.9801367,0.00037585036,0.002712554,0.00013178543,0.00013672862,0.000019000538,0.010260554,0.000020799074,0.006206062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932848,0.0007882873,0.0010139283,0.0016013354,0.002890029,0.0004215709],"domain_scores_gemma":[0.9875896,0.0012918293,0.0004681597,0.007103241,0.003382313,0.00016486396],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.019207867,0.00018466251,0.00056346966,0.00059909845,0.0003330643,0.003047313,0.007935701,0.000091730806,0.00023713899],"category_scores_gemma":[0.008996663,0.00014009132,0.000011425733,0.004048625,0.00034387552,0.0041077984,0.017280541,0.00043297556,0.00007979927],"study_design_candidate":"not_applicable","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":[0.0001245676,0.00017454982,0.001017623,0.00013185429,0.0001444601,0.000058347774,0.00076859584,0.00007274096,0.0034837474,0.46158478,0.3228096,0.20962912],"study_design_scores_gemma":[0.0036883366,0.0005489678,0.0037389675,0.0014846445,0.00003481059,0.00003717185,0.06252182,0.17396653,0.006345469,0.0286581,0.7179775,0.0009976816],"about_ca_topic_score_codex":0.0013094897,"about_ca_topic_score_gemma":0.0018380821,"teacher_disagreement_score":0.73039067,"about_ca_system_score_codex":0.0000617585,"about_ca_system_score_gemma":0.0014795832,"threshold_uncertainty_score":0.99935097},"labels":[],"label_agreement":null}]}