{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":67,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":67,"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"},"query_hash":"323cac591371","filters":{"venue":"ACM SIGMOD Record"}},"results":[{"id":"W2064853889","doi":"10.1145/335191.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6360,"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":"Computer science; Data mining; Scalability; Set (abstract data type); Tree (set theory); GSP Algorithm; Trie; Apriori algorithm; Association rule learning; Database transaction; Data structure; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02961243143666664,"gpt":0.2688342363591712,"spread":0.2392218049225046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347452,0.0001160786,0.0001125526,0.00004543518,0.0001709769,0.0002053458,0.0009652141,0.00004245195,0.0002379336],"category_scores_gemma":[0.00001965805,0.0001076114,0.00003441189,0.0001763004,0.00001513094,0.0004159127,0.0001366032,0.00007983806,0.0001809084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002978156,"about_ca_system_score_gemma":0.00003698879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005004618,"about_ca_topic_score_gemma":0.0001915441,"domain_scores_codex":[0.9989803,0.00003029193,0.0001990298,0.0004091923,0.0001540332,0.0002271486],"domain_scores_gemma":[0.9987328,0.000033456,0.00005686031,0.001060004,0.00002970633,0.00008713994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.213145e-7,0.00002687723,0.003585535,0.000002062584,0.000008742509,0.000003806644,0.0002893022,0.00002836535,0.0007479956,0.0003752284,0.004856424,0.9900748],"study_design_scores_gemma":[0.0008090095,0.000231119,0.01132679,0.00007052186,0.00002738519,0.0000611908,0.00005418539,0.7520654,0.00656089,0.001676776,0.2262554,0.0008614005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6896045,0.00003295649,0.307116,0.00134116,0.0002875429,0.0001334093,0.00002210895,0.0001835684,0.001278754],"genre_scores_gemma":[0.6193132,0.0001050628,0.3764024,0.0006936823,0.0004421746,0.00009794698,0.0001005486,0.00001781967,0.002827053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9892133,"threshold_uncertainty_score":0.4388266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144182447","doi":"10.1145/335191.335388","title":"LOF","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":5181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Local outlier factor; Computer science; Object (grammar); Anomaly detection; Degree (music); Data mining; Property (philosophy); Binary number; Theoretical computer science; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01295973480496317,"gpt":0.2442732101353005,"spread":0.2313134753303373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003804536,0.00006035997,0.00006145999,0.0000322863,0.00009083017,0.00004875777,0.0008472514,0.00003877567,0.0005769607],"category_scores_gemma":[0.000009114733,0.00005594824,0.0000438223,0.0002483986,0.00001657201,0.000177733,0.00009139064,0.00006965944,0.0006258794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001321747,"about_ca_system_score_gemma":0.00001224157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004216504,"about_ca_topic_score_gemma":0.000005720213,"domain_scores_codex":[0.9994681,0.00001196072,0.0001072414,0.0002127743,0.00007423,0.0001257234],"domain_scores_gemma":[0.9990669,0.00002895156,0.00002400522,0.0008137341,0.00001898557,0.00004736869],"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":[9.133561e-7,0.0000172974,0.000107426,7.308028e-7,0.000001932548,7.903496e-7,0.00001628107,0.000002387615,0.0004085148,0.005248801,0.00884214,0.9853528],"study_design_scores_gemma":[0.00009579901,0.00009326492,0.001549793,0.000004652049,0.000002373166,0.00001789906,0.000003685845,0.004283755,0.007099624,0.05620403,0.9304689,0.0001762793],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05122017,0.00004161914,0.8993725,0.002540506,0.0001167152,0.0001780123,0.000001165409,0.00101536,0.04551391],"genre_scores_gemma":[0.7039994,0.0001291782,0.2709524,0.0009854356,0.000129375,0.000096807,0.000001327564,0.00001114469,0.02369489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9851765,"threshold_uncertainty_score":0.8044622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132851185","doi":"10.1145/776985.776986","title":"Issues in data stream management","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":916,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Timestamp; Data stream mining; Database; Query language; Streaming data; Data stream; Data management; Data science; Data mining; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.04335612978330646,"gpt":0.3055749116071249,"spread":0.2622187818238184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002969938,0.0001118442,0.0001447774,0.00008254938,0.00004874193,0.00003851685,0.001381857,0.0000270342,0.00003155632],"category_scores_gemma":[0.0001209432,0.00009910932,0.00001602248,0.000291468,0.00001892636,0.0009589166,0.001069485,0.00007531655,0.00008110548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002174346,"about_ca_system_score_gemma":0.00001634025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637656,"about_ca_topic_score_gemma":0.0003568002,"domain_scores_codex":[0.9988372,0.0000667561,0.0002072153,0.0004967254,0.0001525928,0.000239466],"domain_scores_gemma":[0.9968245,0.00005857241,0.00005305098,0.003002434,0.0000148336,0.00004661906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005840381,0.0001184578,0.005661293,0.0000608452,0.00002714379,0.0001820204,0.0002537628,0.0000338228,0.00007387413,0.5717079,0.02110867,0.4007663],"study_design_scores_gemma":[0.000256242,0.00002624155,0.0007173659,0.00004839499,0.000002333813,0.000008071451,0.0001312891,0.001024582,0.0003054952,0.007734839,0.989558,0.0001871022],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01082637,0.001157096,0.9682918,0.00122335,0.001349448,0.000444374,0.00003905268,0.0002301225,0.01643836],"genre_scores_gemma":[0.04000651,0.0004905977,0.9547675,0.0001890011,0.00006723812,0.00003094146,0.00004336386,0.00001422878,0.004390629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9684494,"threshold_uncertainty_score":0.4041561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2044936152","doi":"10.1145/2094114.2094118","title":"Parallel data processing with MapReduce","year":2012,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":555,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Abstraction; Data science; Big data; Volume (thermodynamics); Data processing; Simple (philosophy); Node (physics); Parallel processing; Database; Parallel computing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.05152052286016848,"gpt":0.2733963681575956,"spread":0.2218758452974271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000403816,0.0001483202,0.0001379464,0.00006136885,0.0001791368,0.0001648165,0.003304876,0.00003694976,0.000007931911],"category_scores_gemma":[0.00005153329,0.0001079984,0.00002202999,0.0003200393,0.00003425208,0.0001919256,0.002609532,0.0001400696,0.0000688943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002203139,"about_ca_system_score_gemma":0.00003473121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018138,"about_ca_topic_score_gemma":0.000005416462,"domain_scores_codex":[0.9986069,0.0000469369,0.0001581619,0.0004552001,0.0002675683,0.0004651874],"domain_scores_gemma":[0.9972955,0.00006989136,0.00009860076,0.00237592,0.00003022723,0.0001298329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001129884,0.0001446479,0.007321362,0.00003856555,0.00003129193,0.00000961901,0.0008456981,0.0005030078,0.00002980828,0.0009649448,0.009056501,0.9810433],"study_design_scores_gemma":[0.001355862,0.0003246156,0.01983501,0.0002980943,0.00007284473,0.0001536036,0.0003523018,0.5660803,0.0001982566,0.00217475,0.4078528,0.001301547],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2788881,0.0009860436,0.7055041,0.00408271,0.0008128721,0.0003006311,0.000001471734,0.0006852493,0.008738832],"genre_scores_gemma":[0.7494628,0.000003897678,0.2485778,0.0003107289,0.0003643327,0.000007493051,0.000003848704,0.0000139564,0.001255073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9797417,"threshold_uncertainty_score":0.6141337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098416578","doi":"10.1145/335191.335419","title":"Efficient and extensible algorithms for multi query optimization","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":409,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Query optimization; Heuristics; Benchmark (surveying); Overhead (engineering); Greedy algorithm; Heuristic; Algorithm; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04290867931345283,"gpt":0.2807725920124819,"spread":0.2378639126990291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002295013,0.0001314743,0.0001364876,0.00008989274,0.0001522858,0.0002120198,0.00067268,0.00004419554,0.00005851686],"category_scores_gemma":[0.00005787947,0.0001207758,0.00004288409,0.0002313686,0.00002944756,0.0003262915,0.000262134,0.00005367472,0.00003121945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001555317,"about_ca_system_score_gemma":0.00001430133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003722021,"about_ca_topic_score_gemma":0.000004304424,"domain_scores_codex":[0.9989354,0.00002295325,0.0001789507,0.0004649151,0.0001330828,0.0002647201],"domain_scores_gemma":[0.9990844,0.00008123619,0.00004796709,0.0006637301,0.00004995728,0.0000727315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008155907,0.00007509506,0.00005151922,0.00001321532,0.0000129061,0.000004346927,0.00008119923,0.01583252,0.00001669655,0.0006743433,0.001985737,0.9812443],"study_design_scores_gemma":[0.0005906847,0.00008373343,0.0002380324,0.00001304947,0.000008778405,0.000003559371,0.00001068818,0.9842018,0.00007027005,0.00041765,0.01418564,0.0001761105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005635933,0.0001240355,0.992231,0.0006004897,0.0003947254,0.0003865989,0.00000934215,0.0001718424,0.0004460661],"genre_scores_gemma":[0.003481713,0.0001408554,0.9923778,0.0003289561,0.0001115072,0.00004865535,0.00002483227,0.00001428488,0.003471451],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9810681,"threshold_uncertainty_score":0.4925096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162294668","doi":"10.1145/373626.373713","title":"The Clio project","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":343,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Set (abstract data type); Data integration; Transformation (genetics); Data science; Software engineering; Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03176797434431566,"gpt":0.2904903462625901,"spread":0.2587223719182744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002533592,0.00009831609,0.00009606039,0.00003503499,0.0003213318,0.00007626139,0.0009620723,0.00002914284,0.000005928815],"category_scores_gemma":[0.0002013191,0.00005952154,0.00004863336,0.0003290305,0.00004450929,0.0005016279,0.0004734308,0.00009997709,0.00009527167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001897826,"about_ca_system_score_gemma":0.00005024514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001819963,"about_ca_topic_score_gemma":0.0004177155,"domain_scores_codex":[0.9990768,0.00005677253,0.0001731607,0.0002655329,0.0001553581,0.0002724093],"domain_scores_gemma":[0.9982502,0.0002516623,0.00007288758,0.00135066,0.00003555289,0.0000390026],"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":[0.0000115283,0.00001706073,0.001735345,0.00000433066,0.00001051156,0.00001698228,0.0001743807,0.000003075662,0.00014451,0.1267185,0.01371622,0.8574476],"study_design_scores_gemma":[0.00009251935,0.00005624884,0.0004152221,0.000009869996,0.000001131949,0.00002836031,0.00003768624,0.000929342,0.000116996,0.005422624,0.9927845,0.0001055165],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01279748,0.000494583,0.9676254,0.003037106,0.002014798,0.000378603,0.00000427948,0.0003369183,0.01331083],"genre_scores_gemma":[0.2095221,0.004926079,0.7359444,0.001483586,0.002118556,0.0004590952,0.000017429,0.00007811592,0.04545057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9790683,"threshold_uncertainty_score":0.2471457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116493296","doi":"10.1145/335191.335409","title":"XTRACT","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; XML validation; Document Structure Description; Document type definition; RELAX NG; XML Schema Editor; Well-formed document; XML Schema (W3C); Streaming XML; XML; Information retrieval; Programming language; Simple API for XML; Efficient XML Interchange; XML database; XML Signature; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01034075916582253,"gpt":0.2474894671120009,"spread":0.2371487079461783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001524755,0.00009424842,0.0001007527,0.00004037277,0.00009885225,0.00009605048,0.001149316,0.00004127081,0.001044988],"category_scores_gemma":[0.00006729605,0.00008052059,0.00005641572,0.0002057928,0.00001443976,0.0002345867,0.0001086314,0.000190283,0.001220989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001009078,"about_ca_system_score_gemma":0.0000205704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001240357,"about_ca_topic_score_gemma":0.00000453637,"domain_scores_codex":[0.999175,0.0000498735,0.0001214791,0.0002833513,0.0001452545,0.0002250562],"domain_scores_gemma":[0.9989718,0.0001027935,0.00002926505,0.0008043212,0.00001513503,0.00007670466],"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":[0.000001830345,0.00002219204,0.0008164868,0.000001631322,0.000004208011,0.00001372079,0.00009363781,0.00005610891,0.00004851586,0.0005378108,0.0031812,0.9952226],"study_design_scores_gemma":[0.0004037672,0.0002190958,0.01126388,0.00002030612,0.000004797553,0.00006100355,0.000005217439,0.1182701,0.000361894,0.01502964,0.8539644,0.0003958909],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5872807,0.0003648837,0.2258428,0.01416038,0.002206501,0.0002631627,0.000002473473,0.001847912,0.1680312],"genre_scores_gemma":[0.726635,0.00008602018,0.2317421,0.001261142,0.0005659762,0.00001270197,0.000003198482,0.00002059106,0.03967332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9948268,"threshold_uncertainty_score":0.9998682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046769817","doi":"10.1145/1147376.1147391","title":"Consistent query answering in databases","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Database; Set (abstract data type); Query optimization; Query language; View; Sargable; Data integrity; Information retrieval; Distributed database; Web search query; Database design; Programming language; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.02901131692479943,"gpt":0.2536003828049169,"spread":0.2245890658801175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002252819,0.000138544,0.0001848697,0.000116437,0.00007075725,0.00007991371,0.0008536645,0.00004252582,0.00002739832],"category_scores_gemma":[0.0001893008,0.00012327,0.00006114512,0.0003063088,0.00003950408,0.0003920101,0.0005188677,0.0001275874,0.00009381381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005486753,"about_ca_system_score_gemma":0.00006349735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001334443,"about_ca_topic_score_gemma":0.002162681,"domain_scores_codex":[0.9988182,0.00005718988,0.0002426689,0.0004123642,0.0001371624,0.0003323812],"domain_scores_gemma":[0.9987214,0.0002364535,0.00006797305,0.000880454,0.0000378399,0.00005593876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003138121,0.0006769823,0.4250862,0.0000929528,0.00003271577,0.0005359004,0.0007933219,0.0001944781,0.005265261,0.1959942,0.02792714,0.3433695],"study_design_scores_gemma":[0.003964967,0.0005376692,0.3688931,0.0005465216,0.00003953171,0.000270976,0.0002622786,0.0528937,0.01978951,0.07754246,0.4724321,0.002827182],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7790526,0.001721679,0.1568066,0.0009188441,0.00229658,0.0003467353,0.00000696766,0.0005284566,0.05832152],"genre_scores_gemma":[0.9621798,0.00004325312,0.0363954,0.0001490789,0.0001814324,0.00001776449,0.000007820392,0.000009839302,0.001015626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4445049,"threshold_uncertainty_score":0.5026806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018758714","doi":"10.1145/945721.945733","title":"The hyperion project","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Database; Distributed database; Database schema; Key (lock); Information retrieval; Database design; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.02685393339233145,"gpt":0.2671210670957384,"spread":0.240267133703407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004312656,0.0001323064,0.0001138067,0.00008352145,0.0002741014,0.00019249,0.002698777,0.00007701667,0.000003146087],"category_scores_gemma":[0.001080857,0.00008893343,0.00005254903,0.0007650167,0.00005252393,0.0001950366,0.0006469243,0.0001812193,0.0001522956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004807706,"about_ca_system_score_gemma":0.0000743813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000327131,"about_ca_topic_score_gemma":0.0001135328,"domain_scores_codex":[0.9987538,0.00008082329,0.0001632466,0.0003725862,0.0002185668,0.000410986],"domain_scores_gemma":[0.9977266,0.0003058845,0.00005416761,0.001825402,0.00004478331,0.00004311676],"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":[0.000003756373,0.00001864625,0.001168263,0.000001806403,0.00001043231,0.000005361605,0.0001257254,0.00001278897,0.0004096623,0.04042483,0.0436204,0.9141983],"study_design_scores_gemma":[0.0001099052,0.0001648623,0.0007573931,0.000009431468,0.000002465061,0.00001808824,0.00003742823,0.001018456,0.002926794,0.04863776,0.9461141,0.0002032788],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3957192,0.001603803,0.4801357,0.04722306,0.008819721,0.002325804,0.000002814886,0.005413834,0.05875603],"genre_scores_gemma":[0.6654592,0.0002417405,0.3295672,0.0006666312,0.000115242,0.0001819309,5.606868e-7,0.0000245871,0.00374297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.913995,"threshold_uncertainty_score":0.5015043,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041835352","doi":"10.1145/945721.945722","title":"Analysis of SIGMOD's co-authorship graph","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Information retrieval; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02584356087544954,"gpt":0.3026211155237821,"spread":0.2767775546483325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004807494,0.0002307631,0.0006578331,0.0005937535,0.00009567934,0.00003366883,0.0005299647,0.00007084545,0.00311633],"category_scores_gemma":[0.00005681327,0.0002228312,0.0007460293,0.002211042,0.00007841563,0.00009280713,0.00007264839,0.0002051523,0.00001939143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000203622,"about_ca_system_score_gemma":0.00003568141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004267454,"about_ca_topic_score_gemma":0.0000724631,"domain_scores_codex":[0.9982873,0.000218726,0.0004972179,0.0004100666,0.0002421434,0.0003445396],"domain_scores_gemma":[0.9979818,0.0003132996,0.0002983851,0.001176627,0.000114513,0.0001154074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001913206,0.0002424784,0.9166691,0.000007391097,0.003500434,0.000001475166,0.0001821412,0.0004229863,0.001305394,0.03366781,0.00376384,0.04021783],"study_design_scores_gemma":[0.001690059,0.0005623291,0.1053426,0.0001007946,0.01452593,0.000001594395,0.000791322,0.01223651,0.06249532,0.7069401,0.09244139,0.002872037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8880239,0.0001026903,0.07397047,0.00006381906,0.00009474787,0.0002268277,0.00003774348,0.0001235099,0.03735631],"genre_scores_gemma":[0.9918146,0.000008360932,0.007352605,0.00002800807,0.00008361217,0.00003247668,0.00008838088,0.00002452814,0.0005674459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8113265,"threshold_uncertainty_score":0.997795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4250963083","doi":"10.1145/376284.375677","title":"Filtering algorithms and implementation for very fast publish/subscribe systems","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Publication; Scalability; Implementation; Event (particle physics); Workload; Polling; Database; Distributed computing; Computer network; Programming language; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03398909794582906,"gpt":0.2917580653035587,"spread":0.2577689673577296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003400631,0.0001710972,0.0002038376,0.0002110181,0.0001519906,0.0005948801,0.001316924,0.00008761044,0.000004919922],"category_scores_gemma":[0.0001557045,0.0001687629,0.00004257328,0.0004773749,0.00002495479,0.001005166,0.0008751415,0.000101936,0.00001078082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007508441,"about_ca_system_score_gemma":0.00002771264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001845488,"about_ca_topic_score_gemma":0.0001033372,"domain_scores_codex":[0.9985031,0.00002570471,0.0002809683,0.0005182818,0.0002042758,0.0004676457],"domain_scores_gemma":[0.9986731,0.000178106,0.0001003102,0.0008468024,0.000106416,0.00009524114],"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":[0.000008619817,0.00001445412,0.002660219,0.00002232503,0.0000235893,0.00001077517,0.0002328872,0.00006863544,0.0009675348,0.001674235,0.02579043,0.9685263],"study_design_scores_gemma":[0.003284283,0.001999603,0.01662803,0.0002485971,0.00005724057,0.0003934914,0.002478654,0.2675327,0.006140581,0.0248814,0.6742381,0.002117239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1471504,0.0002092945,0.8455192,0.003635285,0.001811839,0.0007267437,0.00001392903,0.0007234408,0.0002099002],"genre_scores_gemma":[0.6148847,0.0001293421,0.3827842,0.0003937156,0.0004594242,0.0005747664,0.00002857259,0.0000365526,0.0007087306],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9664091,"threshold_uncertainty_score":0.6881952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987552238","doi":"10.1145/373626.373697","title":"Constraints for semistructured data and XML","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Data integrity; XML database; Database; XML; Programming language; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04716285210807767,"gpt":0.3007392847096654,"spread":0.2535764326015877,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001600003,0.0001069413,0.0001464771,0.00002656431,0.0001136287,0.00004764126,0.0008932583,0.0000412718,0.0000174522],"category_scores_gemma":[0.0003224048,0.00009116108,0.0000177432,0.00009457357,0.00008631372,0.0006185637,0.0008025585,0.0000559607,0.000004209329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008538163,"about_ca_system_score_gemma":0.00003952716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002365415,"about_ca_topic_score_gemma":0.00004814136,"domain_scores_codex":[0.9990737,0.00001736499,0.0001617222,0.0004562448,0.00008640323,0.0002045029],"domain_scores_gemma":[0.997985,0.0001745333,0.00007046713,0.001652724,0.00003980503,0.00007743862],"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":[0.00002012062,0.00001265496,0.001670826,0.00004081434,0.00002371743,0.00002284911,0.0001570713,0.000002543033,0.00263441,0.03129234,0.008808781,0.9553139],"study_design_scores_gemma":[0.0007884705,0.00008836199,0.0005926964,0.00004630851,0.000009436899,0.0002792308,0.00009425517,0.01688233,0.0007950322,0.01599602,0.9640759,0.0003519565],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01337201,0.0001939234,0.984474,0.0005812038,0.0004628654,0.0002053873,0.0001923399,0.00009208006,0.0004261966],"genre_scores_gemma":[0.1660896,0.0001277749,0.8324769,0.0002899592,0.0002433486,0.00002366055,0.0001370285,0.00001327603,0.0005984096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9552671,"threshold_uncertainty_score":0.3717441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126321570","doi":"10.1145/335191.335393","title":"How to roll a join","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Materialized view; Asynchronous communication; Process (computing); Join (topology); Point (geometry); Refresh rate; Distributed computing; Database; Operating system; Computer hardware; Computer network; View","retraction":null,"screen_n_in":null,"score":{"opus":0.01619001446389559,"gpt":0.2327563099770128,"spread":0.2165662955131172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001516456,0.0001400501,0.0001973829,0.00005210831,0.00009039453,0.0003618472,0.0015187,0.00006254551,0.0001009269],"category_scores_gemma":[0.00007471314,0.0001230126,0.00007566722,0.0004705204,0.00001173448,0.0004183958,0.000161907,0.0001001382,0.0006938732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002975607,"about_ca_system_score_gemma":0.00003018982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001031541,"about_ca_topic_score_gemma":0.00004684655,"domain_scores_codex":[0.9987774,0.00004283398,0.000173991,0.0004376023,0.0002224975,0.0003456468],"domain_scores_gemma":[0.9984578,0.0000487023,0.00004015068,0.001228197,0.00004923548,0.0001759142],"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":[0.0000100028,0.00003944375,0.0003652778,0.000006566218,0.00001084023,0.00002805899,0.0002431258,0.00004703343,0.0003956968,0.001834035,0.05185544,0.9451645],"study_design_scores_gemma":[0.0003205385,0.0001467255,0.001759814,0.00003440782,0.000002413137,0.00002120596,0.00001406456,0.005285594,0.0004175111,0.002520302,0.9892058,0.0002715771],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3143614,0.000359503,0.6019365,0.03938935,0.002156476,0.0008525256,0.0000388073,0.0008793681,0.04002608],"genre_scores_gemma":[0.9336844,0.00001704862,0.03818214,0.001356589,0.0002670923,0.00005324936,0.000003567182,0.0000140034,0.0264219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9448929,"threshold_uncertainty_score":0.8918567,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041888157","doi":"10.1145/376284.375685","title":"Independence is good","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Curse of dimensionality; Data mining; Histogram; Independence (probability theory); Exploit; Set (abstract data type); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02571035878820951,"gpt":0.2582570222251933,"spread":0.2325466634369838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002174879,0.0001233658,0.0001141766,0.00009447867,0.0000953697,0.0002371646,0.002773164,0.00005236455,0.0002243273],"category_scores_gemma":[0.00005602997,0.0001131271,0.00005072787,0.0004678546,0.00002013618,0.001225807,0.001236009,0.0001371754,0.0008396296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001801662,"about_ca_system_score_gemma":0.00002089287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008185939,"about_ca_topic_score_gemma":0.00001982525,"domain_scores_codex":[0.9987487,0.00002390102,0.0001576542,0.0004434682,0.0003197199,0.0003065243],"domain_scores_gemma":[0.9983273,0.00005593881,0.0000616481,0.001437473,0.0000379872,0.00007962962],"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":[0.000002646887,0.00005008435,0.01000081,0.000004564468,0.00001729593,0.00007731074,0.0001201252,0.000001224285,0.00006624984,0.01003217,0.02587903,0.9537485],"study_design_scores_gemma":[0.0006822131,0.0002132377,0.01235668,0.00003219865,0.00001441915,0.00004516809,0.00004468891,0.02524465,0.0008043218,0.06978617,0.8901344,0.0006418492],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03927759,0.0001625438,0.8789832,0.01041584,0.002332116,0.0003240152,0.000007258864,0.0006695846,0.06782787],"genre_scores_gemma":[0.6272457,0.0006942636,0.3127816,0.006831782,0.0007305333,0.00005128715,0.00001954768,0.00003992358,0.05160546],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9531066,"threshold_uncertainty_score":0.9999383,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026730210","doi":"10.1145/362084.362104","title":"Generating spatiotemporal datasets on the WWW","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Financiadora de Estudos e Projetos; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Search engine indexing; Data mining; Information retrieval; Interface (matter); Database; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03161233494466065,"gpt":0.2537045766043308,"spread":0.2220922416596702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003022141,0.0001127354,0.00008337827,0.0000361724,0.000211668,0.0003213739,0.002114062,0.00002445661,0.0005691629],"category_scores_gemma":[0.0000628488,0.00007496291,0.00003399621,0.0002160983,0.00002192668,0.0005853166,0.0004157474,0.0001156224,0.001079743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001169127,"about_ca_system_score_gemma":0.00001268142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008796137,"about_ca_topic_score_gemma":0.0000239456,"domain_scores_codex":[0.9990119,0.00006371942,0.0001520546,0.0003405428,0.000216871,0.0002148978],"domain_scores_gemma":[0.9981888,0.0001228146,0.00004791646,0.001589766,0.000009720684,0.00004098015],"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":[0.000002118765,0.00002351102,0.00008806538,0.000001597972,0.000008268771,0.00001119189,0.00002912354,0.00004800066,0.00002727194,0.00347471,0.1262856,0.8700006],"study_design_scores_gemma":[0.0002228123,0.0001263977,0.0005259264,0.00001937995,0.000005742433,0.00000294592,0.000009292813,0.2267267,0.0004395647,0.003963111,0.767701,0.0002571773],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6059836,0.0002645525,0.258378,0.07071173,0.004541916,0.001885118,0.0004608115,0.001469941,0.05630436],"genre_scores_gemma":[0.3761817,0.0003733227,0.5552338,0.02823809,0.002926155,0.0001635503,0.001539438,0.00008677708,0.03525723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8697434,"threshold_uncertainty_score":0.999698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128114397","doi":"10.1145/1228268.1228284","title":"Normalization theory for XML","year":2006,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Toronto","keywords":"Computer science; Relational database; Normalization (sociology); XML; XML database; Database; Relational model; Information retrieval; Simple (philosophy); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01201127058155481,"gpt":0.2430984318000188,"spread":0.231087161218464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002108923,0.00008611705,0.000101232,0.00004461816,0.0001201793,0.00003232326,0.0003784572,0.00003434943,0.00001071788],"category_scores_gemma":[0.0001158483,0.00007365647,0.00004466417,0.000141055,0.0000197408,0.0006162221,0.000151319,0.00003216072,0.00002170119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001666239,"about_ca_system_score_gemma":0.00002225697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006919369,"about_ca_topic_score_gemma":0.00006587836,"domain_scores_codex":[0.9992929,0.00003320621,0.0001718255,0.0002330834,0.00008949971,0.0001794542],"domain_scores_gemma":[0.9990202,0.0001723657,0.00007952828,0.0006371126,0.00006472581,0.00002611991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009587953,0.00001648599,0.0003668062,0.0000164859,0.000003716905,0.000001522836,0.00004567035,0.0001086061,0.0007098474,0.9200097,0.004751886,0.07395966],"study_design_scores_gemma":[0.0004228833,0.0001053292,0.0006753214,0.00002687268,0.000005543459,0.00001052571,0.00002185579,0.0100732,0.005146617,0.220839,0.7623949,0.0002779247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00341222,0.0001161137,0.9937985,0.0001946777,0.0005765315,0.0001950907,0.00001409419,0.0001474706,0.001545318],"genre_scores_gemma":[0.1368319,0.00001673334,0.857011,0.000327451,0.0006089603,0.0001380441,0.0000888606,0.00002281329,0.004954232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.757643,"threshold_uncertainty_score":0.3003624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975270911","doi":"10.1145/601858.601873","title":"Toward autonomic computing with DB2 universal database","year":2002,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Total cost of ownership; Database; IBM; Unix; Scale (ratio); Software; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03708365375936235,"gpt":0.2339088816940285,"spread":0.1968252279346662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001307243,0.0001929142,0.0002244843,0.00009197909,0.0001767999,0.00006326535,0.0009196725,0.00003967405,0.00007748746],"category_scores_gemma":[0.00005518551,0.0001610936,0.00004336422,0.0002917846,0.00006826366,0.001184856,0.0007388653,0.0001684658,0.0001759405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007043947,"about_ca_system_score_gemma":0.00003947754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002013517,"about_ca_topic_score_gemma":0.00005409121,"domain_scores_codex":[0.9986475,0.00005240763,0.0002200668,0.000536188,0.0001800332,0.0003637694],"domain_scores_gemma":[0.9981778,0.0001480503,0.000136056,0.001360269,0.0000494521,0.0001283708],"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":[0.00008002794,0.0003151777,0.006468586,0.0001666689,0.0001949569,0.001069179,0.005463668,0.001804744,0.002970051,0.340097,0.02301992,0.6183501],"study_design_scores_gemma":[0.002501538,0.0006976759,0.001090412,0.0003715812,0.00003291606,0.0004128532,0.0006659284,0.3724856,0.002176271,0.0008531515,0.6171033,0.001608702],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03901655,0.0001457687,0.9565166,0.0007112974,0.0005188562,0.0001653746,0.00002429396,0.0003533732,0.00254786],"genre_scores_gemma":[0.5295432,0.00003678989,0.4692394,0.0002146649,0.0001689899,0.00000447618,0.00001627412,0.00002008874,0.0007561778],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6167414,"threshold_uncertainty_score":0.6569206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4238783465","doi":"10.1145/376284.375729","title":"Data-driven understanding and refinement of schema mappings","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Schema evolution; Database schema; Theoretical computer science; Programming language; Information retrieval; Data mining; Database design","retraction":null,"screen_n_in":null,"score":{"opus":0.1355383599680983,"gpt":0.3042947998079359,"spread":0.1687564398398376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002005291,0.00009907244,0.0001748473,0.00006686088,0.00008320907,0.00002464582,0.0006983144,0.00003027281,0.00001659075],"category_scores_gemma":[0.0001109237,0.00008653111,0.00001734663,0.0002011953,0.00005368709,0.0007258606,0.001355953,0.00006424701,0.000005142637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003322878,"about_ca_system_score_gemma":0.00002516896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009183414,"about_ca_topic_score_gemma":0.00008565571,"domain_scores_codex":[0.9990422,0.00002247496,0.0002323276,0.0003690086,0.0001581797,0.0001758594],"domain_scores_gemma":[0.9982579,0.00009599787,0.0001300408,0.001429793,0.00002882481,0.00005748146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005227929,0.0001140467,0.01402609,0.0002478058,0.0001284654,0.00009265543,0.001322504,0.00003817746,0.01272369,0.8163961,0.01318057,0.1416777],"study_design_scores_gemma":[0.001111645,0.000286231,0.001166102,0.0003819086,0.00002089264,0.0001191726,0.001205671,0.02349846,0.001347559,0.01734546,0.9529275,0.0005894521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03284807,0.0001893034,0.9643306,0.0008869363,0.0002213643,0.0001132131,0.00003120258,0.00006582073,0.001313513],"genre_scores_gemma":[0.3984821,0.0004406766,0.6004036,0.0001333094,0.00009341684,0.00000864492,0.00004007497,0.00001247303,0.0003857326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9397469,"threshold_uncertainty_score":0.3528636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1986871321","doi":"10.1145/362084.362142","title":"Knowledge discovery in data warehouses","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Data warehouse; Automatic summarization; Terabyte; Knowledge extraction; Data mining; Process (computing); Data science; Information retrieval; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.06937896728329003,"gpt":0.3180131510689414,"spread":0.2486341837856514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001854531,0.00009724587,0.0001176418,0.00006199568,0.00006903027,0.0001988157,0.003951747,0.00003634512,0.00006987739],"category_scores_gemma":[0.00007342285,0.00008785834,0.00001925148,0.0004517202,0.0000287486,0.001517393,0.001074791,0.0001110289,0.0004528978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002033822,"about_ca_system_score_gemma":0.00006811039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002167849,"about_ca_topic_score_gemma":0.0003479318,"domain_scores_codex":[0.9989541,0.0000299274,0.0001835024,0.0005243922,0.00009032308,0.0002177993],"domain_scores_gemma":[0.9967424,0.0001632391,0.00002836031,0.003003991,0.00001200757,0.00005006001],"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":[0.000001365828,0.00009613569,0.0005452315,0.000002829607,0.000003267977,0.000004084459,0.0001502886,0.000004802955,0.00002107445,0.0009323788,0.01252424,0.9857143],"study_design_scores_gemma":[0.0003884101,0.00005029528,0.008430415,0.0000550423,0.000005541555,0.00001345269,0.00002861219,0.1085044,0.000123444,0.005035246,0.8769978,0.0003673561],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4347016,0.001858088,0.5130658,0.01180466,0.00165667,0.0009276677,0.0005577902,0.001320849,0.0341069],"genre_scores_gemma":[0.3975945,0.0009353328,0.5795273,0.0006750817,0.0005729471,0.0001283862,0.0003384858,0.000051413,0.0201766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9853469,"threshold_uncertainty_score":0.7343394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792572948","doi":"10.1145/3186549.3186559","title":"Data Quality","year":2018,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Scope (computer science); Quality (philosophy); Data quality; Empiricism; Data science; Action (physics); Data mining; Epistemology; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.6848192121373361,"gpt":0.55904053398058,"spread":0.1257786781567561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009842128,0.0001118675,0.0002354045,0.0001159824,0.0001903233,0.0003212033,0.007113324,0.00005492493,0.003440154],"category_scores_gemma":[0.01962369,0.00008181413,0.00004949893,0.000543984,0.000212694,0.0009450418,0.005003255,0.00009706799,0.008168026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001572625,"about_ca_system_score_gemma":0.00004029914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004326645,"about_ca_topic_score_gemma":0.002138969,"domain_scores_codex":[0.9966689,0.000426432,0.000677238,0.0008536921,0.001103173,0.0002705388],"domain_scores_gemma":[0.9894873,0.001685167,0.000241932,0.008265403,0.0002020653,0.0001181657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002260922,0.0000391258,0.001671049,0.000002113307,0.00001158183,0.00000173286,0.00009111282,8.589792e-8,0.00004897045,0.005743865,0.5250216,0.4673462],"study_design_scores_gemma":[0.000150417,0.00006110441,0.008588974,0.000003802863,0.000006493947,7.016791e-7,0.000352305,0.0002051234,0.00007656476,0.1165323,0.8738972,0.0001249962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4250788,0.0001892553,0.218871,0.05202212,0.01240181,0.001081529,0.002532732,0.0006020995,0.2872206],"genre_scores_gemma":[0.8986552,0.00005338884,0.0450939,0.008180683,0.001891306,0.00001502949,0.0003485813,0.00002713859,0.04573471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4735765,"threshold_uncertainty_score":0.9982587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161694107","doi":"10.1145/2034863.2034873","title":"Repeatability and workability evaluation of SIGMOD 2011","year":2011,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Repeatability; Executable; Computer science; Process (computing); Statistics; Operating system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5113276891992731,"gpt":0.4290325120509692,"spread":0.08229517714830392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02923631,0.0001286875,0.0002790565,0.0001984162,0.0001240732,0.00008665833,0.001254164,0.00005997034,0.002588721],"category_scores_gemma":[0.01905989,0.0000964272,0.00008954822,0.0005072486,0.0002473075,0.0003665652,0.001107587,0.00009892801,0.0001419334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004002747,"about_ca_system_score_gemma":0.00007111008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005382609,"about_ca_topic_score_gemma":0.0002025817,"domain_scores_codex":[0.9954847,0.000678572,0.0008279699,0.001078878,0.001708369,0.0002215662],"domain_scores_gemma":[0.9934971,0.001355622,0.0003627854,0.003895067,0.0007788648,0.0001105093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000454392,0.0001244865,0.195572,0.000006205154,0.00001101733,4.226884e-7,0.0007073215,0.0000103017,0.00004340901,0.0001859572,0.00475834,0.7985351],"study_design_scores_gemma":[0.0003864723,0.0001309168,0.6933794,0.00001603536,0.00006608758,0.000001843389,0.0007221645,0.01302533,0.0006670111,0.2875907,0.003818458,0.000195591],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848324,0.0001172159,0.004014264,0.000189967,0.001046503,0.0003876138,0.00001427301,0.0000407243,0.009357054],"genre_scores_gemma":[0.9895754,0.000005268927,0.009863071,0.00002702118,0.00003671002,0.00001241605,0.000004997981,0.000005296418,0.0004698409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7983395,"threshold_uncertainty_score":0.9996055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2999873292","doi":"10.1145/376284.375664","title":"Efficient computation of Iceberg cubes with complex measures","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"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":"Pruning; Computer science; Online analytical processing; Data cube; Computation; Scalability; Cube (algebra); Data mining; Measure (data warehouse); Tree (set theory); Theoretical computer science; Algorithm; Data warehouse; Database; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.04238828177476196,"gpt":0.2641887323800171,"spread":0.2218004506052552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002141381,0.0001231551,0.0001693701,0.0001276848,0.00007903147,0.00008756069,0.001038785,0.00002324857,0.00001657472],"category_scores_gemma":[0.00003448273,0.00009745091,0.00003874478,0.0004921776,0.0000524235,0.0002117336,0.0003621444,0.00006007989,0.0000323939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001720991,"about_ca_system_score_gemma":0.00001950059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127338,"about_ca_topic_score_gemma":0.00004593468,"domain_scores_codex":[0.9988673,0.00004530096,0.0002047246,0.0003130338,0.0003612333,0.0002083696],"domain_scores_gemma":[0.9990193,0.00007539913,0.0001210363,0.00062967,0.0001029884,0.00005163126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004408594,0.0002718592,0.006613934,0.00003496333,0.00007640338,0.00003518337,0.00035532,0.01335269,0.0005827312,0.005332311,0.004359044,0.9689415],"study_design_scores_gemma":[0.001027101,0.0004379133,0.02677937,0.0000736062,0.00002744445,0.00001916973,0.00008448802,0.9493029,0.0003816665,0.00251333,0.01898118,0.0003718173],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.146329,0.00004609776,0.8492274,0.0006208377,0.0002302229,0.0001855295,0.00000271622,0.00013362,0.003224566],"genre_scores_gemma":[0.8806947,0.0000136319,0.1189252,0.0001062943,0.00004818237,0.000006544406,0.000013904,0.000008036623,0.0001834479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9685696,"threshold_uncertainty_score":0.3973933,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245210711","doi":"10.1145/376284.375666","title":"Iceberg-cube computation with PC clusters","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Computer science; Computation; Cube (algebra); Cuboid; Parallel computing; Algorithm; Data cube; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02094786219915298,"gpt":0.246467051847856,"spread":0.225519189648703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001644319,0.0001394304,0.0001280975,0.0001154486,0.0001148205,0.000256542,0.001226872,0.00003211489,0.00002636549],"category_scores_gemma":[0.00002370938,0.0001146022,0.00003435738,0.0005057715,0.00003077529,0.001155036,0.0005043711,0.00009264735,0.0001790869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002818554,"about_ca_system_score_gemma":0.0000190466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008833034,"about_ca_topic_score_gemma":0.00007430787,"domain_scores_codex":[0.9988676,0.00003681889,0.0001578015,0.0004066963,0.0002555898,0.000275517],"domain_scores_gemma":[0.9989706,0.00008267341,0.00008535161,0.0007390859,0.00004721163,0.00007505123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002103898,0.0000650147,0.003039401,0.00001100796,0.00003769061,0.0000837494,0.0001778469,0.0003850792,0.00002138386,0.001848132,0.01546398,0.9788457],"study_design_scores_gemma":[0.002808178,0.0009433207,0.01294705,0.0001011614,0.00005434968,0.0001011608,0.0001867531,0.6902483,0.0001947194,0.01520523,0.2760232,0.00118666],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03377274,0.00002254376,0.9537314,0.002843852,0.0005916705,0.000200964,0.000001425773,0.0002874947,0.008547944],"genre_scores_gemma":[0.4728291,0.0001115873,0.5172545,0.002190662,0.000386399,0.00003913827,0.00007576087,0.00003761691,0.007075218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.977659,"threshold_uncertainty_score":0.4673342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4241938281","doi":"10.1145/376284.375672","title":"Data bubbles","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; Data mining; CURE data clustering algorithm; Data stream clustering; Canopy clustering algorithm; Hierarchical clustering; Correlation clustering; Set (abstract data type); Data set; Data compression; Key (lock); Constrained clustering; Determining the number of clusters in a data set; Fuzzy clustering; Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.123803096386827,"gpt":0.366511782884858,"spread":0.242708686498031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003168061,0.0001214837,0.0001353337,0.00009631546,0.0001231608,0.0001492538,0.006887774,0.00005068796,0.00005384663],"category_scores_gemma":[0.0005330507,0.0001119645,0.00002565907,0.0005068863,0.00004501903,0.001079359,0.005314135,0.0001992424,0.0002467739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004170333,"about_ca_system_score_gemma":0.00006051792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010036,"about_ca_topic_score_gemma":0.00006600292,"domain_scores_codex":[0.9983473,0.00005282237,0.0001757449,0.0006360096,0.0003520399,0.0004360795],"domain_scores_gemma":[0.9951127,0.0002581459,0.00004699509,0.004386411,0.00006503283,0.0001307079],"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":[0.000007884198,0.00003175601,0.0007315229,0.000005157086,0.000009954611,0.00008758646,0.00005627658,0.00007121411,0.0004048741,0.0004059025,0.003807564,0.9943803],"study_design_scores_gemma":[0.0005280835,0.0001762575,0.003346164,0.00003320837,0.000003970431,0.0001944163,0.00002784676,0.4312353,0.0005222621,0.02460608,0.5388722,0.0004541536],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01508502,0.0001595912,0.9793649,0.002498984,0.0005284749,0.0001286299,0.000008645049,0.0003343661,0.001891403],"genre_scores_gemma":[0.07812442,0.0004534129,0.9138129,0.0003588917,0.0004240146,0.00002405644,0.00002581275,0.00003255143,0.006743989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9939262,"threshold_uncertainty_score":0.9984854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4248260714","doi":"10.1145/376284.375693","title":"SPARTAN","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Spartan; Lossy compression; Data mining; Table (database); Data compression; Data structure; Theoretical computer science; Algorithm; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04318286130473845,"gpt":0.272622653250019,"spread":0.2294397919452806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001762724,0.0001029215,0.0001160101,0.00005163406,0.0001066076,0.00006988255,0.001276638,0.0000674635,0.00008203275],"category_scores_gemma":[0.0001043154,0.00009286328,0.00004548988,0.000269614,0.0000213831,0.0002876374,0.0002972975,0.0001635586,0.0004712899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001967736,"about_ca_system_score_gemma":0.00004361837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006928029,"about_ca_topic_score_gemma":0.00002805779,"domain_scores_codex":[0.9990415,0.00004517238,0.0001648735,0.0003110294,0.0001447644,0.0002926524],"domain_scores_gemma":[0.9987539,0.0001012301,0.00004703638,0.0009430373,0.00005570396,0.00009911215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008854988,0.00005145661,0.01113924,0.00000531589,0.00001490622,0.00006034387,0.0003688881,0.00004624093,0.001035408,0.04930266,0.01077481,0.9271919],"study_design_scores_gemma":[0.0009293414,0.0004714862,0.00945825,0.0001011335,0.00001764105,0.0001514659,0.00007267034,0.2279545,0.001587793,0.4847562,0.2732982,0.001201307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08980364,0.00006780626,0.8905946,0.002104115,0.0006092936,0.00005947297,3.030451e-7,0.0002878392,0.01647292],"genre_scores_gemma":[0.9162623,0.00008735772,0.08013705,0.0008385464,0.0001701549,0.000008686688,8.615266e-7,0.000008049597,0.002486972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9259906,"threshold_uncertainty_score":0.6057635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978094234","doi":"10.1145/776985.776996","title":"Peer-to-peer","year":2003,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Peer-to-peer; World Wide Web; Programming language; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.02618909982454644,"gpt":0.2694503584324208,"spread":0.2432612586078743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009073826,0.0003081427,0.0003224325,0.0003585914,0.000167433,0.0002594622,0.004381703,0.000193381,0.00006741784],"category_scores_gemma":[0.004996471,0.0002935115,0.0001071874,0.001681712,0.00004685407,0.0003842218,0.001408832,0.0003489986,0.001923705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181625,"about_ca_system_score_gemma":0.00009306836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004837958,"about_ca_topic_score_gemma":0.00006995885,"domain_scores_codex":[0.9968665,0.00008528504,0.0003424642,0.0009041331,0.0009536826,0.0008479285],"domain_scores_gemma":[0.9958012,0.0002646002,0.00007987284,0.003079243,0.0004727974,0.0003022706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007750159,0.00006964633,0.002607279,0.000005361004,0.00002844215,0.00005690071,0.0004655602,0.0002084596,0.001082999,0.03439919,0.5371019,0.4239665],"study_design_scores_gemma":[0.0002315634,0.0002644493,0.00128844,0.00002054207,0.000006116872,0.00003351455,0.00004769209,0.0006260495,0.007113952,0.03851391,0.9513344,0.0005193346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1327819,0.0001628834,0.7003142,0.1215987,0.004672651,0.0008800275,0.000007860154,0.003447736,0.03613403],"genre_scores_gemma":[0.3878147,0.000007415057,0.5797241,0.003118111,0.0001355805,0.0001025121,0.000002307012,0.00003742067,0.02905778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4234472,"threshold_uncertainty_score":0.9999517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175911760","doi":"10.1145/3471485.3471494","title":"Efficient Directed Densest Subgraph Discovery","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Scalability; Computer science; Induced subgraph isomorphism problem; Graph; Enhanced Data Rates for GSM Evolution; Subgraph isomorphism problem; Core (optical fiber); Theoretical computer science; Graph factorization; Efficient algorithm; Algorithm; Database; Line graph; Artificial intelligence; Voltage graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01560761602411701,"gpt":0.2370158954038687,"spread":0.2214082793797517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001758454,0.0001466678,0.0002197973,0.0001226826,0.0001467265,0.0003640802,0.001149811,0.00005461016,0.000038382],"category_scores_gemma":[0.0005191823,0.00013124,0.0001589,0.001206829,0.00003540522,0.0002234225,0.00073046,0.0001334733,0.0001084985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002561049,"about_ca_system_score_gemma":0.0001136363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001191358,"about_ca_topic_score_gemma":0.0001106402,"domain_scores_codex":[0.9984875,0.0001086044,0.0002229092,0.0005995219,0.0002689773,0.0003124565],"domain_scores_gemma":[0.9977142,0.0002753584,0.00007725981,0.001725303,0.0001067135,0.0001012272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003948522,0.001452374,0.07758372,0.00008720342,0.0007166844,0.00192483,0.001745432,0.002284517,0.04191833,0.01566171,0.05203327,0.8045524],"study_design_scores_gemma":[0.002883314,0.0004768397,0.117064,0.0004930478,0.0004493639,0.000446266,0.0006607891,0.6805172,0.07476685,0.0108492,0.1075649,0.003828296],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8245572,0.0003672863,0.1709798,0.001495496,0.0008556404,0.00004746652,0.00001591475,0.0004061931,0.001275025],"genre_scores_gemma":[0.9413182,0.00005130765,0.05558308,0.0002993603,0.0001130211,0.000008879505,0.00003397296,0.00001266791,0.002579524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8007241,"threshold_uncertainty_score":0.5351813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139422684","doi":"10.1145/335191.336572","title":"Towards data mining benchmarking","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"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":"Computer science; Data mining; Benchmarking; Data stream mining; Database transaction; Association rule learning; Apriori algorithm; Set (abstract data type); GSP Algorithm; Database; Relational database","retraction":null,"screen_n_in":null,"score":{"opus":0.05942132737752803,"gpt":0.2999806763587709,"spread":0.2405593489812429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002983463,0.0001156648,0.0001246802,0.00004763048,0.0001794593,0.0002262204,0.004721919,0.00004527917,0.0003829614],"category_scores_gemma":[0.00007526581,0.0001098936,0.00002693806,0.0003781373,0.00002757848,0.0008260771,0.00126645,0.0001046027,0.0002095912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001565745,"about_ca_system_score_gemma":0.0000625317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001728203,"about_ca_topic_score_gemma":0.00002149445,"domain_scores_codex":[0.9986966,0.0000249903,0.0002015437,0.0006202683,0.0001863118,0.0002703261],"domain_scores_gemma":[0.9963306,0.0001108117,0.00005052442,0.003395619,0.000023201,0.00008928599],"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":[7.704501e-7,0.00002091445,0.00013698,0.000001837304,0.000006968827,0.000004271962,0.0001306116,0.000003140197,0.00002846158,0.0004282969,0.01703158,0.9822062],"study_design_scores_gemma":[0.0001946442,0.00006460295,0.002362108,0.00003449955,0.00001005067,0.00002728567,0.00002500463,0.3693551,0.0001119029,0.00223235,0.6252734,0.0003090695],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1258175,0.0003773429,0.8064063,0.008276653,0.001448251,0.0004168471,0.0001945036,0.001036884,0.05602575],"genre_scores_gemma":[0.02542416,0.0001080119,0.9722846,0.0004418142,0.000377732,0.00002140273,0.0001414631,0.00001284956,0.001187979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9818971,"threshold_uncertainty_score":0.8774579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066407644","doi":"10.1145/1041410.1041416","title":"Kanata","year":2004,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Metadata; Focus (optics); World Wide Web; Database; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02648632253714379,"gpt":0.2570926872259994,"spread":0.2306063646888556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001011324,0.00008541979,0.0001092152,0.00005325372,0.00006796281,0.00007287011,0.001656232,0.00004845936,0.00002018585],"category_scores_gemma":[0.0002269136,0.00007036249,0.00004713308,0.000195277,0.00002957686,0.0002983532,0.000449349,0.00008092262,0.0002651897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002649178,"about_ca_system_score_gemma":0.00005301662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000213748,"about_ca_topic_score_gemma":0.00008871741,"domain_scores_codex":[0.9992436,0.0000144242,0.0001182226,0.0002696455,0.0001311171,0.000223008],"domain_scores_gemma":[0.9987579,0.00008386968,0.00003648735,0.001044272,0.00002665918,0.00005080189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008149751,0.0001128888,0.006222796,0.00001556872,0.00003530404,0.000171034,0.0007721638,0.00007775901,0.001192287,0.2238557,0.008499435,0.7590368],"study_design_scores_gemma":[0.001473721,0.0003679643,0.03240957,0.00005628132,0.00001374527,0.0001148524,0.000134796,0.001504937,0.01528076,0.8800371,0.06791662,0.0006896029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2833381,0.0004563594,0.6836505,0.01568586,0.002284908,0.0001659816,8.683995e-7,0.000798305,0.01361913],"genre_scores_gemma":[0.8234584,0.00003485701,0.1753974,0.0007209857,0.00008654345,0.000006017621,6.31041e-7,0.000005145142,0.0002900976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7583473,"threshold_uncertainty_score":0.3408566,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123331342","doi":"10.1145/335191.336589","title":"DISIMA","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"","field":"","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.01982543029966458,"gpt":0.2650928007484224,"spread":0.2452673704487578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001550728,0.0001641625,0.0001766392,0.00006754362,0.00008941053,0.00004114196,0.000619781,0.00007385339,0.02249562],"category_scores_gemma":[0.0001980976,0.0001503189,0.00009311984,0.000331133,0.00005981172,0.0002165865,0.00007878291,0.0001561241,0.08877561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006250659,"about_ca_system_score_gemma":0.00002574229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001600977,"about_ca_topic_score_gemma":0.00009455004,"domain_scores_codex":[0.9987794,0.00006140978,0.0002028387,0.0003385115,0.0002232295,0.0003945949],"domain_scores_gemma":[0.9985635,0.0001218967,0.00004216933,0.001115337,0.00002882734,0.0001282768],"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":[0.0001397807,0.0001187063,0.01294884,0.000005416228,0.00003286817,0.00003050856,0.0001591918,0.00001879369,0.004186702,0.0001275289,0.1278132,0.8544185],"study_design_scores_gemma":[0.0007110836,0.0001279662,0.02055948,0.00001999538,0.00002757189,0.00002048772,0.00002343052,0.0003450165,0.001796433,0.008491694,0.9674779,0.0003988972],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9095379,0.00009000667,0.00001548549,0.0004236864,0.0002058065,0.0001530095,0.00002662679,0.0004349667,0.0891125],"genre_scores_gemma":[0.9701171,0.00004316908,0.003593509,0.0002994199,0.0003272935,0.00002835275,0.00002215036,0.0001196396,0.0254494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8540196,"threshold_uncertainty_score":0.978398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317952630","doi":"10.1145/3582302.3582314","title":"Report on the First International Workshop on Data Systems Education (DataEd '22)","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; Bridging (networking); Panel discussion; Data management; Conjunction (astronomy); Data science; Engineering management; Library science; World Wide Web; Database; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08682560969649208,"gpt":0.3362625693619047,"spread":0.2494369596654126,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124812,0.0001164575,0.00009813379,0.0001391169,0.0002952155,0.0004804025,0.003790935,0.00005355126,0.00001058434],"category_scores_gemma":[0.002553246,0.00008368027,0.00003474031,0.0004261258,0.00001973414,0.0002937159,0.0009936398,0.0003717077,0.0003347245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004315755,"about_ca_system_score_gemma":0.00008908168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002148623,"about_ca_topic_score_gemma":0.00001559751,"domain_scores_codex":[0.9984751,0.0001103417,0.0002320909,0.0005774669,0.0003968419,0.0002081762],"domain_scores_gemma":[0.9957474,0.0008782774,0.0001730225,0.003117774,0.00003704991,0.00004643109],"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":[0.000008908111,0.00008856654,0.003040868,0.000008750318,0.00003337206,0.00003853046,0.0003881543,0.0005640041,0.000005612158,0.007243108,0.1540456,0.8345345],"study_design_scores_gemma":[0.00007011954,0.00003702239,0.003694208,0.0001911721,0.000003985178,0.00003379702,0.0001566303,0.02960704,0.000006045203,0.0001866996,0.9658803,0.0001329762],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2853763,0.0003593201,0.2522799,0.338578,0.08990632,0.002372483,0.00004429053,0.006748558,0.02433479],"genre_scores_gemma":[0.9822662,0.00003336006,0.006782127,0.0007978864,0.001140331,0.00009320008,0.0003571994,0.00002721966,0.008502444],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8344015,"threshold_uncertainty_score":0.7044563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2094817912","doi":"10.1145/1084805.1084825","title":"Exchange, integration, and consistency of data","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"IBM (Canada); University of Victoria; York University; Carleton University","funders":"","keywords":"Computer science; IBM; Data exchange; Consistency (knowledge bases); Data consistency; Data integration; Database; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05743416482229315,"gpt":0.3015237353670839,"spread":0.2440895705447908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001948212,0.00007643927,0.0001377741,0.00004651811,0.0000520489,0.00001679367,0.0006850846,0.00002675714,0.00001982086],"category_scores_gemma":[0.0002085572,0.00006215675,0.00001272784,0.0001267006,0.00005683495,0.001313738,0.0009065905,0.00005100972,0.000009350702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006927945,"about_ca_system_score_gemma":0.00003015305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009642479,"about_ca_topic_score_gemma":0.000419361,"domain_scores_codex":[0.9992645,0.00002889974,0.0002115073,0.0002898276,0.00009888977,0.0001063217],"domain_scores_gemma":[0.9980927,0.0001129853,0.00009806172,0.001591723,0.00006222862,0.00004232219],"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":[0.00000325102,0.00001794569,0.0003845463,0.00002158596,0.000007328164,0.000001606255,0.0002910737,7.077479e-7,0.0008437939,0.04473526,0.005206734,0.9484861],"study_design_scores_gemma":[0.0004232978,0.0001264295,0.001164791,0.0001099375,0.000009941606,0.00004418799,0.0001653123,0.01354757,0.003491356,0.00384645,0.9767894,0.0002813477],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008073254,0.001327895,0.9874422,0.00134824,0.0002209689,0.0001196769,0.00005947065,0.00006078065,0.001347497],"genre_scores_gemma":[0.1315757,0.0003354242,0.8671762,0.0001786435,0.0001374716,0.000007508565,0.00003745467,0.000006287975,0.0005453036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9715827,"threshold_uncertainty_score":0.2534679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099464320","doi":"10.1145/1107499.1107507","title":"An apples-to-apples comparison of two database journals","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Database; Information retrieval; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06868933506628278,"gpt":0.3936536109531938,"spread":0.3249642758869111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004216206,0.0001381947,0.0002557992,0.0001425099,0.0001372546,0.0001521266,0.002636224,0.00003462006,0.00006769428],"category_scores_gemma":[0.00008013789,0.0001281025,0.00004939191,0.0004885262,0.00003435677,0.0007372607,0.0005249441,0.0001555982,0.0001379783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002194726,"about_ca_system_score_gemma":0.00005338829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001654145,"about_ca_topic_score_gemma":0.0001346712,"domain_scores_codex":[0.9985427,0.00004845835,0.0004283119,0.0004315947,0.0002801958,0.0002687718],"domain_scores_gemma":[0.9973928,0.0001547372,0.0001889514,0.001945375,0.00009238788,0.0002257409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003047457,0.0003000172,0.003812222,0.000005968335,0.00001374834,0.000001166152,0.0004431227,0.0003543789,0.02346617,0.004302556,0.01981203,0.9474856],"study_design_scores_gemma":[0.001290777,0.0005956946,0.01178109,0.0001773268,0.00004967403,0.00004275779,0.0003604541,0.538933,0.07373147,0.002934264,0.369073,0.001030502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.118383,0.000144862,0.8786974,0.001967049,0.000141675,0.0001930758,0.0001088585,0.0001129478,0.000251169],"genre_scores_gemma":[0.3669213,0.00001861966,0.6325021,0.0002063212,0.000217651,0.00002809405,0.00003611452,0.000009417407,0.00006034442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9464551,"threshold_uncertainty_score":0.5223867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020463925","doi":"10.1145/1462571.1462581","title":"Paper and proposal reviews","year":2008,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Term (time); Data science; Panel discussion; World Wide Web; Engineering ethics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1000016508214448,"gpt":0.2875434587443016,"spread":0.1875418079228569,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000196097,0.0001625272,0.0002195071,0.00008872276,0.000206639,0.00009348288,0.0003829347,0.00006566343,0.001170649],"category_scores_gemma":[0.0004214534,0.0001225717,0.00004712735,0.000300517,0.0001052611,0.001426828,0.0003656303,0.0001191042,0.001083323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000686842,"about_ca_system_score_gemma":0.00001554577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000331137,"about_ca_topic_score_gemma":0.0001028826,"domain_scores_codex":[0.9990777,0.000007831441,0.0002483187,0.000306039,0.0001346856,0.0002253606],"domain_scores_gemma":[0.9992723,0.00002991004,0.0001223609,0.0004889394,0.0000736588,0.00001287197],"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":[0.00005961889,0.0001187726,0.0776791,0.0004051912,0.00002026463,0.00004876361,0.00005654711,7.855676e-7,0.001734373,0.007663428,0.2864353,0.6257778],"study_design_scores_gemma":[0.0001246277,0.000007689414,0.01053027,0.00005817293,0.00001990347,0.00002180529,0.00001092264,0.00009063802,0.00006019198,0.005091659,0.9837649,0.0002191669],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8958776,0.008115756,0.002938896,0.01355726,0.003715599,0.001771201,0.000008742963,0.0006261393,0.07338879],"genre_scores_gemma":[0.9592,0.008140757,0.00924353,0.01127519,0.005153872,0.0001084751,0.00009189703,0.00008344474,0.006702859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6973296,"threshold_uncertainty_score":0.9997424,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309505072","doi":"10.1145/3572751.3572765","title":"Characterizing I/O in Machine Learning with MLPerf Storage","year":2022,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Focus (optics); Inference; Software; Machine learning; Computer data storage; Training set; Training (meteorology); Data access; Database; Artificial intelligence; Computer engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01743802220997948,"gpt":0.2339386751193323,"spread":0.2165006529093528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000303498,0.0001661452,0.0002088313,0.000274034,0.0002769139,0.0000608659,0.0022606,0.00003545777,0.00006351681],"category_scores_gemma":[0.0002332974,0.0001556783,0.00002655265,0.0008548382,0.00004315693,0.0007629736,0.002924161,0.0008144728,0.00001692425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000185581,"about_ca_system_score_gemma":0.00004243127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001153128,"about_ca_topic_score_gemma":0.00006550504,"domain_scores_codex":[0.9985131,0.0001065126,0.0001949622,0.0005379151,0.0002806019,0.0003668992],"domain_scores_gemma":[0.9984758,0.000149208,0.0001416564,0.001177834,0.00001730372,0.00003817587],"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":[0.0001183735,0.0002057347,0.04876668,0.0000283244,0.00003058917,0.00128705,0.002273113,0.006457198,0.01959151,0.005648853,0.0002984343,0.9152941],"study_design_scores_gemma":[0.004925001,0.005212383,0.02583426,0.0001641588,0.00002511443,0.0009254786,0.002896303,0.3193644,0.01059416,0.021403,0.6050707,0.003585052],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7306154,0.0003285848,0.2640077,0.002436004,0.0004486178,0.0003032401,0.00001459122,0.001414603,0.000431354],"genre_scores_gemma":[0.8922457,0.00003116179,0.1070344,0.0002293044,0.0000202573,0.0001030446,0.00001913596,0.00002211019,0.0002949711],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9117091,"threshold_uncertainty_score":0.6348374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388233567","doi":"10.1145/3631504.3631514","title":"Kùzu: A Database Management System For \"Beyond Relational\" Workloads","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Relational database; Relational database management system; Set (abstract data type); Database; Relational model; World Wide Web; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02996732447430424,"gpt":0.255841462335733,"spread":0.2258741378614287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007103569,0.000137793,0.0001448336,0.0002270578,0.0002334038,0.00008578198,0.001192424,0.00004915316,0.00001127117],"category_scores_gemma":[0.00006159464,0.0001284071,0.00010511,0.0009176602,0.00002417777,0.0003998011,0.0006336193,0.00008874113,0.0003570718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003440114,"about_ca_system_score_gemma":0.00001741404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003422942,"about_ca_topic_score_gemma":0.000001908424,"domain_scores_codex":[0.9986697,0.00006032976,0.0002336254,0.0004750018,0.0002282864,0.0003330397],"domain_scores_gemma":[0.9982482,0.0003979411,0.00008024726,0.001140429,0.00004741875,0.00008577703],"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":[0.00002268639,0.00003297928,0.0002295352,0.0001433047,0.00007044496,0.00006577102,0.0001718694,0.0001282321,0.00009502233,0.7446325,0.01296566,0.241442],"study_design_scores_gemma":[0.002741307,0.0003029315,0.002634933,0.0005546169,0.00009109327,0.00004697704,0.0006761572,0.2416692,0.00115419,0.5559715,0.1930029,0.001154198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008588446,0.00008449394,0.9823405,0.001204279,0.002352951,0.0006084575,0.00003349328,0.0008672356,0.003920113],"genre_scores_gemma":[0.2697581,0.00008025773,0.7141235,0.0005209984,0.0005141558,0.0007351487,0.0001816235,0.00005551919,0.01403074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2682171,"threshold_uncertainty_score":0.5236289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3217479643","doi":"10.1145/3503780.3503786","title":"VLDB Panel Summary","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Very large database; SQL; Database; Point (geometry); World Wide Web; Mathematics education; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.1235782994575026,"gpt":0.2886061652908584,"spread":0.1650278658333558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001564046,0.0001851073,0.0002067318,0.0001110971,0.0001559555,0.0003120909,0.0006677005,0.0001003286,0.003141706],"category_scores_gemma":[0.0006502579,0.0001708346,0.00009195141,0.0006814601,0.00004974085,0.001183246,0.0007927201,0.0001708036,0.001967227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001596032,"about_ca_system_score_gemma":0.00004007764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004288989,"about_ca_topic_score_gemma":0.0002606048,"domain_scores_codex":[0.9987527,0.000008603651,0.0002539431,0.0004211456,0.0002300591,0.0003335436],"domain_scores_gemma":[0.9986682,0.00008008221,0.0001135664,0.0008761868,0.0002470394,0.00001493957],"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":[0.0000566444,0.0002361245,0.05648873,0.0003135662,0.00006032643,0.0002520658,0.0000231458,0.00001030823,0.005230614,0.01069142,0.3154403,0.6111968],"study_design_scores_gemma":[0.0001791259,0.000004171625,0.006992421,0.00008053386,0.00004218773,0.00001125663,0.00009541077,0.0004697776,0.001328021,0.01254375,0.9779194,0.0003339428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6782633,0.002647293,0.00885981,0.01905807,0.01235596,0.0005743751,0.00004334922,0.00116537,0.2770325],"genre_scores_gemma":[0.9552903,0.0005047677,0.003836684,0.01215709,0.006810564,0.00004412513,0.000610951,0.0001038014,0.02064173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6624791,"threshold_uncertainty_score":0.9988099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406379941","doi":"10.1145/3712311.3712323","title":"A Roadmap to Graph Analytics","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Analytics; Data science; Graph; Data analysis; Product (mathematics); Task (project management); Data mining; Theoretical computer science; Engineering; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01397350786004826,"gpt":0.2632285770793657,"spread":0.2492550692193174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002708203,0.0001262863,0.0001616758,0.0003322798,0.0001252886,0.0001139525,0.001822955,0.00005417332,0.00001962983],"category_scores_gemma":[0.0001918718,0.0001151043,0.0001083379,0.001553385,0.00002711321,0.0001893231,0.0005960827,0.0001238513,0.0001085638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001720243,"about_ca_system_score_gemma":0.00004623424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002109256,"about_ca_topic_score_gemma":0.00001734634,"domain_scores_codex":[0.9989622,0.00005737215,0.0001850578,0.0003856609,0.0001315318,0.0002782033],"domain_scores_gemma":[0.9984187,0.0001642341,0.00003548166,0.001211445,0.00006256126,0.0001076118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001415234,0.00006241657,0.002449379,0.00001357012,0.00006642558,0.00002445761,0.0003517678,0.0001005181,0.0005883497,0.3772506,0.01228595,0.6067924],"study_design_scores_gemma":[0.0003213649,0.0001609648,0.002487912,0.00005450864,0.0000177531,0.000004697488,0.00004338375,0.00845452,0.003449964,0.938059,0.04662301,0.0003228948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.037514,0.0000815477,0.9480785,0.004462998,0.001429521,0.0001682563,0.000001843694,0.0002360075,0.008027376],"genre_scores_gemma":[0.783215,0.00002438905,0.2045303,0.004921357,0.0001078941,0.00003803755,0.000001804455,0.00001195142,0.007149213],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7457011,"threshold_uncertainty_score":0.4693817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083283415","doi":"10.1145/2694413.2694425","title":"Report on the First International Workshop on Exploratory Search in Databases and the Web (ExploreDB 2014)","year":2014,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Database; World Wide Web; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.0560095100511173,"gpt":0.2822348339987544,"spread":0.2262253239476371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739059,0.0001262834,0.0001206263,0.0001236242,0.0001565292,0.0002802448,0.001969316,0.00002157074,0.00003665454],"category_scores_gemma":[0.0006605427,0.00006990211,0.00003415035,0.0002118478,0.0001124929,0.0006259451,0.001384142,0.0002425584,0.0001158692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002244927,"about_ca_system_score_gemma":0.00001911973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004719088,"about_ca_topic_score_gemma":0.0001528846,"domain_scores_codex":[0.9986126,0.0001458217,0.000212692,0.0004454289,0.0003836838,0.0001997763],"domain_scores_gemma":[0.9969712,0.001297713,0.00007792749,0.001586046,0.00003110549,0.00003594085],"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":[0.0001903786,0.0002296219,0.01063961,0.00001558499,0.0000793345,0.0001625537,0.00094886,0.00014735,0.00001195235,0.2056757,0.283235,0.4986641],"study_design_scores_gemma":[0.001840392,0.0001208793,0.006468059,0.000207578,0.000008950099,0.00001494021,0.0003285399,0.1549595,0.0001524882,0.008227973,0.8272985,0.0003722734],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3832923,0.0003046912,0.1559819,0.4123456,0.009444051,0.002254919,0.00005010458,0.0005257194,0.03580076],"genre_scores_gemma":[0.979663,0.001195067,0.007211869,0.007940677,0.0009294991,0.0002576235,0.00008346357,0.00003314334,0.002685725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5963706,"threshold_uncertainty_score":0.3659512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3111316923","doi":"10.1145/376284.375749","title":"Exploiting constraint-like data characterizations in query optimization","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); York University","funders":"","keywords":"Computer science; Query optimization; Constraint (computer-aided design); Data integrity; Binary constraint; Exploit; Constraint programming; USable; Data mining; Database; Constraint satisfaction; Constraint logic programming; Mathematical optimization; Probabilistic logic; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0655448349157439,"gpt":0.2887837579054945,"spread":0.2232389229897506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002365926,0.0001263113,0.0001654884,0.000121113,0.0001079555,0.00005684235,0.0009954877,0.00004708711,0.00004716052],"category_scores_gemma":[0.0002920806,0.0001266233,0.00001910222,0.0005271022,0.00004398706,0.002538963,0.0008193166,0.0001108969,0.0000229347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003036839,"about_ca_system_score_gemma":0.00006297418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001071313,"about_ca_topic_score_gemma":0.0001304811,"domain_scores_codex":[0.9987296,0.00006633411,0.0003392528,0.0004802293,0.0001346868,0.0002499388],"domain_scores_gemma":[0.9979186,0.000135438,0.00009870174,0.001737902,0.00004851137,0.00006086853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003510591,0.0003135635,0.04338433,0.00008151082,0.00004912803,0.0003430985,0.001479422,0.0168451,0.005356949,0.1048692,0.002009794,0.8252329],"study_design_scores_gemma":[0.000903973,0.00007624306,0.002839084,0.0002934115,0.000008531505,0.0001974478,0.0004474768,0.8029865,0.000226284,0.001033749,0.1901867,0.0008006426],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01728578,0.00004918454,0.9805029,0.0006111087,0.0005738452,0.0001606806,0.00004284293,0.0001573347,0.0006163443],"genre_scores_gemma":[0.1453063,0.0003780377,0.8525288,0.0005191451,0.0002273453,0.00004627928,0.0006826666,0.00002443089,0.0002870111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8244322,"threshold_uncertainty_score":0.5163548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175620523","doi":"10.1145/3471485.3471506","title":"Scaling Dynamic Hash Tables on Real Persistent Memory","year":2021,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":3,"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":"Computer science; Hash function; Scalability; Emulation; Parallel computing; Hash table; Latency (audio); Embedded system; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02187522317510901,"gpt":0.2662600561580582,"spread":0.2443848329829492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002323949,0.0001475583,0.0001843525,0.00009593485,0.0002016175,0.0001746607,0.0009462096,0.00008180818,0.00003146817],"category_scores_gemma":[0.0002241819,0.0001456991,0.0001375659,0.0003427059,0.00002645404,0.0001656633,0.0005019506,0.0001425368,0.00003382133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008436527,"about_ca_system_score_gemma":0.0001021054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005211837,"about_ca_topic_score_gemma":0.00002475531,"domain_scores_codex":[0.9986489,0.0001079848,0.0002241977,0.0005060122,0.0002361732,0.0002767468],"domain_scores_gemma":[0.9984357,0.0002170797,0.00008790912,0.001043978,0.0001299273,0.00008544492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002917275,0.0003970078,0.0007342072,0.00006129863,0.0001240241,0.000203082,0.001327938,0.05275566,0.002912123,0.007122808,0.02273316,0.9115995],"study_design_scores_gemma":[0.0004126621,0.0002214519,0.0003953774,0.0001630324,0.00001618843,0.00005085101,0.0001061635,0.9780037,0.007481569,0.005334924,0.007308229,0.0005058943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07574878,0.0003380638,0.9008889,0.003023959,0.001053195,0.0001543884,0.000002948417,0.001202488,0.01758726],"genre_scores_gemma":[0.4593147,0.0004290503,0.5346201,0.0007828897,0.00009629053,0.00001424025,0.00001819306,0.00002257062,0.00470199],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.925248,"threshold_uncertainty_score":0.5941437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4379932427","doi":"10.1145/3604437.3604458","title":"Accurate Summary-based Cardinality Estimation Through the Lens of Cardinality Estimation Graphs","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Cardinality (data modeling); Computer science; Graph; Joins; Proxy (statistics); Context (archaeology); Theoretical computer science; Mathematical optimization; Mathematics; Statistics; Data mining; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0549768818470338,"gpt":0.3138872410875159,"spread":0.2589103592404821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009275511,0.0002013883,0.0003451258,0.0000850803,0.0002945802,0.00005615017,0.0007960548,0.00007211185,0.000005430308],"category_scores_gemma":[0.0006684253,0.0001474282,0.0001831798,0.001118967,0.0001380589,0.001381358,0.0003642257,0.0001560497,0.00003533327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004946824,"about_ca_system_score_gemma":0.0001118969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001330515,"about_ca_topic_score_gemma":0.00009272749,"domain_scores_codex":[0.9980202,0.000287449,0.0004959904,0.0004535309,0.0004324903,0.0003103695],"domain_scores_gemma":[0.9969392,0.0006347487,0.0003456441,0.001849227,0.0001879523,0.00004326838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001632323,0.0001612441,0.008898905,0.0009388243,0.0002871013,0.00004283312,0.003701478,0.2341279,0.00243529,0.4454966,0.02006919,0.2836775],"study_design_scores_gemma":[0.0008163397,0.0002362906,0.02449713,0.0002930757,0.00007687288,0.00001175849,0.0003085496,0.8316631,0.005788471,0.10429,0.03133191,0.0006865464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0446665,0.00008481925,0.9516091,0.001716023,0.0007298487,0.0003896639,0.00009830563,0.0003158227,0.0003899097],"genre_scores_gemma":[0.8352879,0.0000441725,0.1641794,0.0001268225,0.00005128274,0.00008498365,0.000134698,0.00001521006,0.00007558859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7906213,"threshold_uncertainty_score":0.601195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070556972","doi":"10.1145/2380776.2380784","title":"dbTrento","year":2012,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Universidad de Zaragoza; University of Alberta","keywords":"Citation; Computer science; Library science; Database; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03247796109390363,"gpt":0.278870893944344,"spread":0.2463929328504404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001314635,0.0001139089,0.0001139354,0.00008938865,0.00006987113,0.00004076471,0.002195623,0.00006665328,0.00003192193],"category_scores_gemma":[0.0004337749,0.0001000581,0.00003675201,0.0003239031,0.0000445381,0.00149254,0.001495388,0.0001354358,0.0004585843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004600213,"about_ca_system_score_gemma":0.00001201931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001481118,"about_ca_topic_score_gemma":0.000005737323,"domain_scores_codex":[0.9990487,0.0000193462,0.0001291305,0.0002453569,0.0001486051,0.000408875],"domain_scores_gemma":[0.9978678,0.0001201627,0.00006235661,0.001847459,0.00002236985,0.00007981791],"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":[0.000001935246,0.00005243778,0.006682184,0.000004127714,0.000008165423,0.000005910725,0.0001602102,0.000002079725,0.001155334,0.0539113,0.01343185,0.9245844],"study_design_scores_gemma":[0.0004480944,0.0001734934,0.007207872,0.00002372069,0.00001035298,0.00006237875,0.000115945,0.001334622,0.02346158,0.1404725,0.8258895,0.000799939],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0325573,0.0006155676,0.9596804,0.001446857,0.001426168,0.0001111439,0.000003152023,0.001520484,0.00263893],"genre_scores_gemma":[0.5277145,0.00004140399,0.471451,0.0002039402,0.0001105183,0.00001940994,0.000002639333,0.000009039448,0.0004476021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9237846,"threshold_uncertainty_score":0.5894327,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974306683","doi":"10.1145/335191.335495","title":"An approximate search engine for structural databases","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Parsing; Database; Information retrieval; XML; Set (abstract data type); Subgraph isomorphism problem; Graph database; Graph; Search engine; Heuristic; Data structure; XML database; Data mining; Theoretical computer science; World Wide Web; Programming language; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02029490765508899,"gpt":0.2866351295362456,"spread":0.2663402218811566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001417562,0.0001333773,0.000118322,0.0000204244,0.00009940639,0.00003142512,0.0003518902,0.00008455183,0.0001901565],"category_scores_gemma":[0.00001953291,0.0001169852,0.00006335578,0.00004274863,0.00003909939,0.000009282304,0.00007025463,0.0000731979,0.00001111509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000621971,"about_ca_system_score_gemma":0.00003049376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003117456,"about_ca_topic_score_gemma":0.00003669292,"domain_scores_codex":[0.9991969,0.00001809846,0.0001784519,0.0002436625,0.00006540068,0.0002974462],"domain_scores_gemma":[0.9991282,0.0000164185,0.0000297384,0.0006935118,0.00003727384,0.00009487552],"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":[0.0003488479,0.00003904158,0.0005537418,0.00005376433,0.00006862509,0.000001154669,0.0001162029,0.00125727,0.03807658,0.0001286172,0.007464588,0.9518915],"study_design_scores_gemma":[0.003903743,0.002591054,0.001834695,0.0000456989,0.00009029431,0.00008480745,0.0002464546,0.2603467,0.1165166,0.003930528,0.6087737,0.001635742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830652,0.0002548303,0.01544637,0.00009073723,0.0001665619,0.0003249246,0.0001649092,0.00002237736,0.000464121],"genre_scores_gemma":[0.9422075,0.0002511277,0.05355887,0.0003221637,0.0007385396,0.00003631278,0.001686299,0.00003274597,0.001166432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9502558,"threshold_uncertainty_score":0.4770517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008481019","doi":"10.1145/1107499.1107509","title":"In memoriam Alberto Oscar Mendelzon","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"TD Bank Group","funders":"","keywords":"Tribute; Battle; Friendship; Computer science; Intellect; Art history; Art; History; Ancient history; Theology; Philosophy; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.1644658386398347,"gpt":0.4286982494735129,"spread":0.2642324108336783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003284215,0.0001429732,0.0002778387,0.0003052166,0.00007003739,0.0001747027,0.001866507,0.00007488275,0.002879581],"category_scores_gemma":[0.003424542,0.0001125985,0.00008851728,0.0006586672,0.00004482466,0.0009826097,0.0007641051,0.0001475456,0.003971934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007287136,"about_ca_system_score_gemma":0.00002910265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005045992,"about_ca_topic_score_gemma":0.004773571,"domain_scores_codex":[0.9972386,0.0002383443,0.0006851894,0.0005895479,0.0009105221,0.0003378247],"domain_scores_gemma":[0.9969689,0.001078435,0.0001481688,0.001638559,0.00006128623,0.0001045994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003568772,0.0001096898,0.0008977993,0.000002855319,0.00001021092,0.0000117112,0.0004629116,0.0000607022,0.00007606635,0.005448979,0.5537364,0.439147],"study_design_scores_gemma":[0.0003930866,0.00004822501,0.001051275,0.000006660832,0.00000537195,0.000001767881,0.0003977203,0.0005730619,0.0002535525,0.05977349,0.9373393,0.0001565015],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5237374,0.0004581445,0.0132737,0.1587625,0.0169225,0.001531609,0.00008343689,0.0002719222,0.2849589],"genre_scores_gemma":[0.8595002,0.0001966003,0.02752791,0.0113401,0.002460931,0.00008043199,0.00002703894,0.00003744171,0.09882929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4389905,"threshold_uncertainty_score":0.9980319,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042832124","doi":"10.1145/1361348.1361361","title":"Report on the First International Workshop on Ranking in Databases (DBRank'07)","year":2007,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Conjunction (astronomy); Ranking (information retrieval); Computer science; Database; World Wide Web; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.04722377923604341,"gpt":0.3079342729547288,"spread":0.2607104937186854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001092906,0.0001607398,0.0001578977,0.0001513523,0.0001624667,0.00005501213,0.001038325,0.00003837749,0.00006182746],"category_scores_gemma":[0.001263745,0.0001114793,0.00005599395,0.0003251596,0.00004569866,0.0005528295,0.0005029353,0.0002611364,0.00008666124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008059531,"about_ca_system_score_gemma":0.00003037861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001606284,"about_ca_topic_score_gemma":0.001092436,"domain_scores_codex":[0.9983657,0.00003700014,0.0004094291,0.0005005529,0.0003937024,0.0002936336],"domain_scores_gemma":[0.9967948,0.001331154,0.000180698,0.001600117,0.00004695064,0.00004632888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003491399,0.000385595,0.03483474,0.00003166625,0.00007866987,0.003046339,0.001013172,0.0006521854,0.0002932586,0.5194373,0.0256414,0.4142365],"study_design_scores_gemma":[0.0004562431,0.00006265964,0.01028805,0.0005155718,0.000002637358,0.000112433,0.000140169,0.001590158,0.001662848,0.001641047,0.9831972,0.0003309644],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08901243,0.00007875641,0.8889608,0.008580266,0.003655876,0.0003772704,0.00002213911,0.0001719984,0.00914041],"genre_scores_gemma":[0.919357,0.00009075432,0.07447849,0.003542198,0.0009264928,0.00006303233,0.0000858291,0.00003479174,0.001421437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9575558,"threshold_uncertainty_score":0.4545993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3111145856","doi":"10.1145/3444831.3444841","title":"Advice from SIGMOD/PODS 2020","year":2020,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Conferences and Exhibitions Management","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Notice; Computer science; Advice (programming); Component (thermodynamics); World Wide Web; Political science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04673422380066231,"gpt":0.3025489882476701,"spread":0.2558147644470078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001774407,0.000121791,0.000175316,0.00002687709,0.0003581965,0.0001435011,0.0007104331,0.00008089108,0.005710443],"category_scores_gemma":[0.0005039172,0.0001226265,0.00009753609,0.0003948344,0.00009311691,0.0002180655,0.0002749815,0.0001488028,0.0007894631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004629073,"about_ca_system_score_gemma":0.0001021482,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01410978,"about_ca_topic_score_gemma":0.008421801,"domain_scores_codex":[0.9986671,0.0001224507,0.0002045236,0.000380237,0.0003187809,0.0003068835],"domain_scores_gemma":[0.999083,0.000209446,0.00007817905,0.0003297266,0.00006376854,0.0002358489],"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":[0.00008385578,0.0001248204,0.01159755,0.00002399687,0.0001247311,0.0000507925,0.02387894,0.00002242993,0.0003293869,0.02580635,0.35645,0.5815071],"study_design_scores_gemma":[0.0002375459,0.00008056794,0.001614492,0.00001642836,0.00003386882,6.385851e-8,0.005668127,0.000846641,0.00002660419,0.01226526,0.9789848,0.0002255504],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3429245,0.0005091628,0.003934124,0.2130836,0.002152636,0.0008741147,0.00007873692,0.001037025,0.4354061],"genre_scores_gemma":[0.9885836,0.0004308353,0.003320603,0.003441238,0.001562283,0.0000273863,0.00002891977,0.00001463756,0.002590443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6456591,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4379800102","doi":"10.1145/3604437.3604444","title":"Efficiently Making Cross-Engine Transactions Consistent","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":1,"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":"Computer science; Limiting; Isolation (microbiology); Correctness; Database; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03259407237871086,"gpt":0.3036519960292631,"spread":0.2710579236505523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003200895,0.0001530557,0.00020237,0.0001313406,0.0002649525,0.0002840123,0.001068054,0.00007790377,0.00004367768],"category_scores_gemma":[0.00008024217,0.0001439982,0.0001370526,0.001071254,0.00004518336,0.0002938156,0.0001090608,0.0001632657,0.0005153113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004571556,"about_ca_system_score_gemma":0.00004885331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002774609,"about_ca_topic_score_gemma":0.00001672142,"domain_scores_codex":[0.9984889,0.00004128854,0.0003207665,0.0004487098,0.0002781482,0.0004221774],"domain_scores_gemma":[0.9985861,0.0001647235,0.00008272111,0.0009784476,0.00009833936,0.00008965893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002977757,0.0002511721,0.003601923,0.0001508291,0.0001441437,0.0002840674,0.00147777,0.02525762,0.002377853,0.009261461,0.01764819,0.9395152],"study_design_scores_gemma":[0.00157991,0.0002223146,0.02016613,0.0002609461,0.00002468209,0.0001231558,0.0001555697,0.6503775,0.001354226,0.002407763,0.3223399,0.0009880241],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07454263,0.0001059291,0.9185564,0.00115424,0.00271125,0.0002212661,0.0000345577,0.0009160537,0.001757669],"genre_scores_gemma":[0.9903199,0.00001508316,0.006793787,0.0001483476,0.00008537357,0.00004348385,0.000008715587,0.00001432399,0.002570975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9385272,"threshold_uncertainty_score":0.6623456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396883491","doi":"10.1145/3665252.3665266","title":"Technical Perspective: Synthetic Data Needs a Reproducibility Benchmark","year":2024,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Perspective (graphical); Reproducibility; Data mining; Data science; Database; Artificial intelligence; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2209871303754449,"gpt":0.4407284741139029,"spread":0.219741343738458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02619974,0.0002010179,0.0003126135,0.0006347472,0.0002334209,0.001572976,0.007071964,0.00007990532,0.001771189],"category_scores_gemma":[0.06861946,0.000143177,0.0001436447,0.003349209,0.0002468397,0.0007824716,0.007319225,0.0003361301,0.00159456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344499,"about_ca_system_score_gemma":0.0001481231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002851028,"about_ca_topic_score_gemma":0.0001135288,"domain_scores_codex":[0.992431,0.0003109316,0.0007699945,0.004559235,0.001523517,0.0004053491],"domain_scores_gemma":[0.9643829,0.004099552,0.0001280736,0.03087793,0.0003232709,0.0001882631],"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":[0.00001541384,0.00007628812,0.0006581307,0.000008819616,0.0000161159,0.00002669464,0.0002264695,0.000007613108,0.000139815,0.003120524,0.4692768,0.5264273],"study_design_scores_gemma":[0.0001194759,0.00009639403,0.00333063,0.0000909988,0.00005857412,0.00004767972,0.002127489,0.06341286,0.00006242527,0.1908135,0.7394693,0.0003707499],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2805924,0.00853009,0.2811883,0.09557384,0.04660543,0.003059756,0.001045012,0.004376065,0.2790291],"genre_scores_gemma":[0.9724417,0.00002305956,0.01762886,0.0001553593,0.0004794348,0.00001349098,0.00004664752,0.00002023447,0.009191191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6918494,"threshold_uncertainty_score":0.9994635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033301070","doi":"10.1145/1107499.1107519","title":"Christos Faloutsos speaks out","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Very large database; Computer science; Library science; Database; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02296878735220468,"gpt":0.2434831067099527,"spread":0.220514319357748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002158304,0.0001656801,0.0002294666,0.00009609454,0.0001624203,0.0001734098,0.001525331,0.0000671437,0.0002694828],"category_scores_gemma":[0.0001292497,0.0001447559,0.0001618774,0.0002764258,0.00003298362,0.0005487937,0.0005645697,0.0001621403,0.0008717024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004714103,"about_ca_system_score_gemma":0.00003174552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008852494,"about_ca_topic_score_gemma":0.0002501342,"domain_scores_codex":[0.9986048,0.00003346146,0.0003106479,0.0004433507,0.0002324832,0.0003752359],"domain_scores_gemma":[0.9984251,0.00008006499,0.000131854,0.00118035,0.0000610626,0.00012156],"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":[0.000004163061,0.00003847606,0.00109091,0.000004137613,0.00003032607,0.000009129928,0.0007289101,0.0001142805,0.0005369437,0.00195514,0.007238774,0.9882488],"study_design_scores_gemma":[0.0004576549,0.0001791417,0.001636394,0.00002937563,0.00003011822,0.00002719876,0.00008479002,0.1544994,0.002018787,0.003055339,0.8373469,0.0006349387],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1214443,0.0008627436,0.7963814,0.01170484,0.001712638,0.0003563991,0.000005758041,0.0009057125,0.06662625],"genre_scores_gemma":[0.8464334,0.00003427576,0.1453943,0.0006015163,0.0006789101,0.000009021901,0.000003285718,0.00001794249,0.006827367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876139,"threshold_uncertainty_score":0.9999062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}