{"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":"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":[0.08441527,0.0057058316,0.2499377,0.24150194,0.008077599,0.000515104,0.0002699495,0.0025653702,0.4070113],"genre_scores_gemma":[0.74077,0.0022268083,0.1261696,0.017851667,0.00208543,0.0005949861,0.00020961282,0.0011096759,0.10898221],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953178,0.0021517044,0.00018310253,0.00063393463,0.0007180034,0.0009954824],"domain_scores_gemma":[0.9868051,0.005205676,0.00078153756,0.004029855,0.0013591264,0.0018186376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069287913,0.00048268226,0.0003707273,0.0010110278,0.006228,0.008071966,0.0025989125,0.009125219,0.014715272],"category_scores_gemma":[0.029214554,0.00073659496,0.0008871627,0.0010763946,0.005056058,0.018026516,0.0057725594,0.007104723,0.0034719014],"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":[0.00019288457,0.00008262676,0.0025559915,0.00007010035,0.000017027303,0.006014947,0.004568239,0.00081825897,0.0011854372,0.90466934,0.045295406,0.034529746],"study_design_scores_gemma":[0.00013255929,0.0000689944,0.00085341255,0.00034783137,0.000046057146,0.0075071063,0.0041458765,0.014045013,0.0022795943,0.49539986,0.47511646,0.000057198526],"about_ca_topic_score_codex":0.003800773,"about_ca_topic_score_gemma":0.0050338083,"teacher_disagreement_score":0.014715272,"about_ca_system_score_codex":0.0021398682,"about_ca_system_score_gemma":0.002977547,"threshold_uncertainty_score":0.049227536},"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":"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":[0.051853023,0.014648803,0.68377143,0.045319203,0.0055823997,0.0011249152,0.02441284,0.091362715,0.081924684],"genre_scores_gemma":[0.46076953,0.010637851,0.41750494,0.0047654975,0.0020639661,0.0005849376,0.052537836,0.01098053,0.040154874],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952683,0.0016585937,0.00041356945,0.0006789845,0.0016599242,0.00032056242],"domain_scores_gemma":[0.97776574,0.0066887415,0.00060129596,0.010751679,0.0031401417,0.001052456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008336633,0.0009813579,0.0010152826,0.0034653135,0.0025260048,0.009847531,0.0028479074,0.002645242,0.021677388],"category_scores_gemma":[0.029643683,0.00088624563,0.0012401751,0.005397003,0.0019023519,0.018429665,0.008626588,0.0029728382,0.010067108],"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":[0.0015373876,0.0003571335,0.012599342,0.0008803311,0.00037520906,0.00092686503,0.0013166124,0.008563974,0.005718277,0.11959459,0.38008025,0.4680501],"study_design_scores_gemma":[0.00023223774,0.00019914916,0.00607223,0.0010230059,0.00026222013,0.0010105747,0.0022365537,0.112678744,0.020279258,0.270132,0.58571064,0.00016343122],"about_ca_topic_score_codex":0.003883541,"about_ca_topic_score_gemma":0.0039234124,"teacher_disagreement_score":0.021677388,"about_ca_system_score_codex":0.0014709058,"about_ca_system_score_gemma":0.0034303262,"threshold_uncertainty_score":0.07251805},"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":"software","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":[0.008063158,0.0011110948,0.23219302,0.004031873,0.0014593517,0.001158295,0.10974009,0.571889,0.07035417],"genre_scores_gemma":[0.11580239,0.0016482578,0.17544621,0.0033487284,0.0011570258,0.001850672,0.4921064,0.101246625,0.107393675],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994228,0.0014798114,0.0007081583,0.0014228495,0.0017159085,0.0004451861],"domain_scores_gemma":[0.9850706,0.0026855823,0.00047331201,0.008820027,0.0020723073,0.0008781185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072541297,0.001461874,0.0017636066,0.006275731,0.0014398119,0.0063187554,0.002672391,0.001623552,0.11997876],"category_scores_gemma":[0.025643243,0.0015157582,0.0014388423,0.005629128,0.0011624187,0.0071261907,0.0058362805,0.003323982,0.11066848],"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":[0.0011036276,0.0002016102,0.0026510928,0.00038543774,0.00016510747,0.00020487123,0.0003120849,0.0015148073,0.005294672,0.034713924,0.78111106,0.17234163],"study_design_scores_gemma":[0.00035112753,0.00008609988,0.0015607974,0.000089320594,0.000062636835,0.00021845588,0.00009128368,0.017561108,0.013038223,0.017968744,0.9488799,0.000092294016],"about_ca_topic_score_codex":0.003654358,"about_ca_topic_score_gemma":0.0020243118,"teacher_disagreement_score":0.11997876,"about_ca_system_score_codex":0.0014685014,"about_ca_system_score_gemma":0.0042784465,"threshold_uncertainty_score":0.40136892},"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":"methods","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051006908,0.000774912,0.5893799,0.0025560015,0.0018510434,0.003124965,0.041082237,0.34192196,0.0142082665],"genre_scores_gemma":[0.07155457,0.0008817337,0.72563213,0.0022103803,0.0005709527,0.006163976,0.12947762,0.047095485,0.016413132],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9755492,0.007885529,0.0025366987,0.0052751945,0.007880658,0.00087264995],"domain_scores_gemma":[0.9086402,0.023574961,0.0036421018,0.052724835,0.007893927,0.0035240066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029410543,0.0024125217,0.0018970565,0.007062745,0.002707317,0.006620785,0.0075559714,0.0029774578,0.018948372],"category_scores_gemma":[0.10735518,0.0018441114,0.0030391712,0.0061136764,0.003079507,0.007461583,0.025186954,0.0039150952,0.020256214],"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":[0.0018509463,0.00047489355,0.006229317,0.0034561518,0.0015166977,0.0014056878,0.0040405756,0.010439099,0.019993756,0.030701004,0.65060866,0.26928312],"study_design_scores_gemma":[0.0008089385,0.00025735892,0.0050503095,0.00063758204,0.00019879703,0.00050679705,0.001081367,0.07910993,0.025627976,0.10932838,0.7768274,0.0005651932],"about_ca_topic_score_codex":0.0062583797,"about_ca_topic_score_gemma":0.0047237175,"teacher_disagreement_score":0.97058946,"about_ca_system_score_codex":0.0014041294,"about_ca_system_score_gemma":0.005841531,"threshold_uncertainty_score":0.15553969},"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":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06195461,0.0037265436,0.3011427,0.01107496,0.0018902267,0.001886712,0.04864962,0.49917987,0.07049476],"genre_scores_gemma":[0.18445843,0.0037676094,0.3934363,0.0056364425,0.0016651498,0.002605648,0.17409687,0.0449231,0.18941046],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590474,0.00040495166,0.0002769852,0.00046770927,0.0024827004,0.00046289866],"domain_scores_gemma":[0.99185747,0.00181728,0.0007296607,0.0024280883,0.0014120667,0.0017554058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004961494,0.0011727673,0.0008321572,0.003113824,0.0015354757,0.005280169,0.003856873,0.0014165815,0.025851853],"category_scores_gemma":[0.010858477,0.0013537813,0.0010702284,0.003616216,0.0013785923,0.015312176,0.010572937,0.0034686741,0.011164952],"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":[0.0025034053,0.00089715084,0.0066113696,0.0009564207,0.00032140146,0.00081510533,0.0017276544,0.0017056712,0.040792402,0.03384379,0.6478489,0.26197678],"study_design_scores_gemma":[0.00091059005,0.0006041232,0.011172151,0.00037200924,0.00022828186,0.0005993579,0.00074337557,0.028838025,0.032670483,0.04026911,0.88311267,0.0004798861],"about_ca_topic_score_codex":0.005541218,"about_ca_topic_score_gemma":0.007719381,"teacher_disagreement_score":0.025851853,"about_ca_system_score_codex":0.0007915081,"about_ca_system_score_gemma":0.004133927,"threshold_uncertainty_score":0.08648306},"labels":[],"label_agreement":null}]}