{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1256,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1256,"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":"e0fdac2723aa","filters":{"topic":"Data Management and Algorithms"}},"results":[{"id":"W2140190241","doi":"10.5860/choice.49-3305","title":"Data mining: concepts and techniques","year":2012,"lang":"en","type":"article","venue":"Choice Reviews Online","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28877,"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 science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1554244839230521,"gpt":0.4082003367705969,"spread":0.2527758528475448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007649604,0.0001177521,0.0002156469,0.00004231069,0.00004924489,0.00009890888,0.001454958,0.00002534248,0.00001413486],"category_scores_gemma":[0.0001949131,0.00008989431,0.00002016935,0.0002102834,0.00003611534,0.002008201,0.001551176,0.00007055743,0.0000410507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006861064,"about_ca_system_score_gemma":0.00000750793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005192965,"about_ca_topic_score_gemma":0.000006492617,"domain_scores_codex":[0.9990689,0.00005609054,0.0002318434,0.0003038955,0.0001082607,0.0002309953],"domain_scores_gemma":[0.9983847,0.00006124462,0.0001051607,0.001329164,0.00001552573,0.000104193],"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":[1.154218e-7,0.00005427059,0.0009560496,0.00006677691,0.00000437172,6.745558e-7,0.00002904417,2.095665e-9,0.00003149962,0.0008744557,0.03148053,0.9665022],"study_design_scores_gemma":[0.00005905697,0.00001299728,0.001127941,0.000110595,0.00001287652,0.000004289898,0.000005576689,0.0009061066,0.00003352288,0.00001887593,0.9975883,0.0001198064],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003958783,0.4587623,0.5137571,0.007445876,0.001812181,0.002467812,0.0005779041,0.00129931,0.009918681],"genre_scores_gemma":[0.0009151367,0.04151119,0.9520352,0.002240842,0.001247629,0.00002279444,0.000641721,0.00001441284,0.001371054],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9663824,"threshold_uncertainty_score":0.3665784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740924709","doi":"10.1145/3068335","title":"DBSCAN Revisited, Revisited","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2625,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Computer science; DBSCAN; Data mining; Heuristics; Information retrieval; Algorithm; Artificial intelligence; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.03953632886572851,"gpt":0.2875278022523509,"spread":0.2479914733866224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006144177,0.0002252727,0.0002661171,0.0002213446,0.0009985981,0.001539914,0.004366743,0.00005183652,0.00005963134],"category_scores_gemma":[0.00009353485,0.0002058787,0.0001001066,0.0002482905,0.00005747504,0.002527788,0.0001537182,0.000221946,0.0007398337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004367424,"about_ca_system_score_gemma":0.00002565339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002883952,"about_ca_topic_score_gemma":0.000009941318,"domain_scores_codex":[0.9981027,0.00009774519,0.0003376088,0.0006808286,0.0004349471,0.0003461763],"domain_scores_gemma":[0.9919556,0.00007793935,0.0002232246,0.007518143,0.00006713059,0.0001579147],"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":[0.00006677807,0.0008432174,0.0005105551,0.001121147,0.0006515729,0.0006140335,0.0002967126,0.0004647869,0.001302744,0.1313978,0.1103469,0.7523836],"study_design_scores_gemma":[0.001965684,0.0002117781,0.001192581,0.001360079,0.000142762,0.00009623524,0.0001187038,0.07697163,0.001076651,0.0004371409,0.9151763,0.001250455],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001650468,0.0001816538,0.9903804,0.001266618,0.001291853,0.0004778403,0.0007400021,0.0003441889,0.005152375],"genre_scores_gemma":[0.8985859,0.001068342,0.08268696,0.000776584,0.0007595212,0.0002479835,0.0007591086,0.00008249852,0.01503308],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9076934,"threshold_uncertainty_score":0.9994966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166470254","doi":"10.1145/1963192.1963217","title":"CELF++","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":857,"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":"Heuristics; Computer science; Maximization; Greedy algorithm; Simple (philosophy); Node (physics); Set (abstract data type); Mathematical optimization; Monte Carlo method; Quadratic equation; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04872163073464558,"gpt":0.1971299117888966,"spread":0.148408281054251,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004872841,0.00002441119,0.00002039879,0.00002196288,0.00001713502,0.00003756449,0.0005351137,0.000005105352,0.0002486898],"category_scores_gemma":[0.000001271664,0.00001873673,0.000009752651,0.00008222902,0.000005233599,0.0004579038,0.0002187811,0.00001267087,0.000715249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001372881,"about_ca_system_score_gemma":0.000002020328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001999093,"about_ca_topic_score_gemma":0.000001322238,"domain_scores_codex":[0.9997487,0.000003254745,0.00003304797,0.00009297311,0.00004951479,0.00007250725],"domain_scores_gemma":[0.9997102,0.000002136898,0.000006843453,0.0002552817,0.00000550455,0.00002001926],"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":[1.266518e-7,0.00001649136,0.0001811904,7.235735e-7,0.000002359427,0.000006640309,0.0001040223,2.143924e-8,0.000006903993,0.8744549,0.01483375,0.1103928],"study_design_scores_gemma":[0.0006266869,0.0001838809,0.04376187,0.000006930983,0.000008161841,0.000008519365,0.0001024546,0.0606114,0.01261699,0.1443296,0.737066,0.0006775148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001147437,0.000003018766,0.5677342,0.00007751989,0.0001082519,0.00001350534,8.160696e-8,0.0001051136,0.4318435],"genre_scores_gemma":[0.1889662,0.000005849206,0.7824069,0.001047035,0.00003992463,0.000003684767,0.000001263837,0.000002955758,0.02752623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7301253,"threshold_uncertainty_score":0.9193318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009688537","doi":"10.1145/1391729.1391730","title":"A survey of top- <i>k</i> query processing techniques in relational database systems","year":2008,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":834,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relational database; Database; Information retrieval; Dimension (graph theory); XML database; XML; Query optimization; Query language; Sargable; Domain (mathematical analysis); View; Database design; Web search query; World Wide Web; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.1129110638023711,"gpt":0.3416350848872731,"spread":0.228724021084902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008689558,0.0004616565,0.001571798,0.0006787431,0.0001253996,0.0002137751,0.003401317,0.0002076833,0.000001196612],"category_scores_gemma":[0.0009861628,0.0004258358,0.0001561739,0.002297869,0.00007935177,0.0007813933,0.002751528,0.000521948,0.00001673395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043435,"about_ca_system_score_gemma":0.0005221019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002063928,"about_ca_topic_score_gemma":0.00007610735,"domain_scores_codex":[0.9934343,0.003159388,0.00142691,0.0009299129,0.0006038774,0.0004456061],"domain_scores_gemma":[0.9949809,0.001844033,0.001064992,0.001812557,0.0002288516,0.00006866248],"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":[3.27311e-7,0.00006666249,0.00113323,0.004273173,0.00002753642,0.00004080028,0.00002777581,0.00001389368,3.906163e-8,0.0003118459,0.001129432,0.9929753],"study_design_scores_gemma":[0.00053994,0.0001182864,0.01535866,0.07257771,0.0000979016,0.0001832429,0.000009900727,0.06961157,0.000002406185,0.0000817785,0.838744,0.002674629],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004057278,0.6972283,0.3013265,0.000005235876,0.0003641534,0.0005163227,0.0001177112,0.0001908009,0.0002469081],"genre_scores_gemma":[0.0001624547,0.9486727,0.04917621,0.00001392062,0.0001327059,0.00002374276,0.001683554,0.0000448648,0.00008986609],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9903007,"threshold_uncertainty_score":0.9998193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110557355","doi":"10.1007/s007780100049","title":"Approximate query processing using wavelets","year":2001,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":477,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Wavelet; Query optimization; Data mining; Tuple; Histogram; Algorithm; Artificial intelligence; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0412518917975479,"gpt":0.2701677799750619,"spread":0.228915888177514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007493352,0.00009056483,0.00008441041,0.00008444262,0.0005128147,0.0009499458,0.001141741,0.00001699722,0.00002060897],"category_scores_gemma":[0.0000121465,0.00005534851,0.00004212929,0.0003404355,0.00003490358,0.001317469,0.0002929477,0.0002087694,0.00002641726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002807431,"about_ca_system_score_gemma":0.00004292195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005049121,"about_ca_topic_score_gemma":5.986842e-7,"domain_scores_codex":[0.9990727,0.00005246469,0.0001716359,0.0001342281,0.0002787817,0.0002901625],"domain_scores_gemma":[0.9994665,0.00001441307,0.0001321268,0.0002799736,0.00004499448,0.00006192979],"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":[0.000007267495,0.00006096278,0.0003815775,0.00001414783,0.00003065054,0.0003072062,0.0007430015,0.0004504626,0.0008754768,0.005079004,0.002284011,0.9897662],"study_design_scores_gemma":[0.0003753398,0.00002968619,0.0007612113,0.00008624982,0.00001984909,0.002526341,0.0001360168,0.9563392,0.0002813176,0.01412985,0.0250828,0.0002321147],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03452689,0.0003038282,0.9598022,0.001952763,0.000404683,0.00006060367,3.262983e-7,0.00006685733,0.002881845],"genre_scores_gemma":[0.7274629,0.0004251382,0.2656185,0.002018119,0.001999093,0.000003669013,0.000001990776,0.00003561674,0.00243496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9895341,"threshold_uncertainty_score":0.9160349,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993378086","doi":"10.1145/2806416.2806493","title":"A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Nvidia","keywords":"Computer science; Encoder; Generative grammar; Context (archaeology); Artificial intelligence; Generative model; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.06969257043282508,"gpt":0.3021491390428253,"spread":0.2324565686100002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003847002,0.0001259146,0.0001336572,0.00008065117,0.00008246014,0.0002395072,0.0005677685,0.00004116348,0.00001502514],"category_scores_gemma":[0.00007027773,0.0001008059,0.00005351002,0.0001501428,0.00003483609,0.0007575096,0.0002902498,0.00008385667,0.00007087895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004468984,"about_ca_system_score_gemma":0.00007680606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002322277,"about_ca_topic_score_gemma":0.00006038155,"domain_scores_codex":[0.9988868,0.00005849691,0.0001817978,0.0003953283,0.0002330493,0.0002445053],"domain_scores_gemma":[0.9992329,0.00007664128,0.00004770684,0.0003518482,0.0001396042,0.0001513246],"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":[0.00002418011,0.0001353123,0.00007618005,0.00001153578,0.0000284632,0.000007128306,0.0007109414,0.00005514019,0.00001246686,0.3477867,0.1959947,0.4551572],"study_design_scores_gemma":[0.001171336,0.0003744389,0.0001243108,0.00001884746,0.000009870576,0.000004625809,0.0001801444,0.8198113,0.0006389715,0.03228803,0.1450619,0.0003161908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006145616,0.00007965519,0.9909656,0.004758885,0.0007622896,0.0003480267,0.00001464004,0.0001778692,0.002278459],"genre_scores_gemma":[0.2737749,0.0000405075,0.7069955,0.004361628,0.0008534031,0.0003814082,0.0003161615,0.00003034789,0.01324617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8197562,"threshold_uncertainty_score":0.4110745,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999824796","doi":"10.1145/1102351.1102385","title":"Near-optimal sensor placements in Gaussian processes","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"Mutual information; Computer science; Gaussian; Entropy (arrow of time); Gaussian process; Algorithm; Global Positioning System; Variance (accounting); Task (project management); Mathematical optimization; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01448665043394406,"gpt":0.2504545708919586,"spread":0.2359679204580145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001186223,0.00008159206,0.00007013007,0.00006745386,0.00004726427,0.000309576,0.0005690153,0.00001706989,0.0001146102],"category_scores_gemma":[0.00001301647,0.00006853581,0.00001137635,0.0003813377,0.00001602946,0.001239286,0.0002675127,0.00004921423,0.0004408071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001842054,"about_ca_system_score_gemma":0.00003007971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002260139,"about_ca_topic_score_gemma":0.00006483469,"domain_scores_codex":[0.9992027,0.00001070798,0.0001284585,0.000256002,0.0001719496,0.0002302086],"domain_scores_gemma":[0.9996354,0.00001363265,0.00002502436,0.0002664204,0.00001604005,0.00004346139],"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":[0.00003673561,0.001329127,0.02085227,0.0002233893,0.0000713027,0.0002113385,0.003485087,0.008521357,0.0001461558,0.06634755,0.07726006,0.8215156],"study_design_scores_gemma":[0.001319833,0.00009721264,0.005733456,0.00003314807,0.000004186474,0.000006726998,0.0001530771,0.6246287,0.001497673,0.0001958938,0.3658744,0.0004557745],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06958906,0.00009968692,0.7743844,0.01012269,0.000283337,0.0004906587,0.000005547049,0.0005709617,0.1444536],"genre_scores_gemma":[0.3678836,0.00002135365,0.6110561,0.001319109,0.0001172973,0.00001856067,0.00001117132,0.00000885475,0.01956392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8210598,"threshold_uncertainty_score":0.566583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138414767","doi":"","title":"Probabilistic skylines on uncertain data","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":461,"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":"Skyline; Uncertain data; Probabilistic logic; Computer science; Data mining; Benchmark (surveying); Object (grammar); Set (abstract data type); Data set; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08583155124540513,"gpt":0.3233955027557575,"spread":0.2375639515103523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006411989,0.00006988704,0.00005630785,0.00006137609,0.0000470421,0.0001468828,0.002171938,0.00001414691,0.00004485955],"category_scores_gemma":[0.00006804802,0.00005160321,0.00001010635,0.0002531714,0.00001806592,0.0006240432,0.0009366519,0.00004271211,0.0002662777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000101092,"about_ca_system_score_gemma":0.00001078279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002901453,"about_ca_topic_score_gemma":0.00004272193,"domain_scores_codex":[0.9991243,0.000009050982,0.0001169567,0.0003646647,0.0001918067,0.0001932588],"domain_scores_gemma":[0.9983793,0.00008046534,0.0000232213,0.001453012,0.00001790096,0.0000461372],"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":[0.000002585664,0.00008044307,0.00007761976,0.000008433713,0.000006923238,0.00003423418,0.00001992877,0.00003154247,0.000009140207,0.5389985,0.04012878,0.4206018],"study_design_scores_gemma":[0.0003858369,0.0001356821,0.003170526,0.0000197403,0.000007252711,0.000004274955,0.00003584955,0.4864686,0.0002352285,0.01968494,0.4894945,0.0003575455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004147673,0.0000100146,0.9239557,0.001491659,0.000356351,0.0001280737,0.000006778682,0.0002293453,0.07340735],"genre_scores_gemma":[0.1851854,0.00002088536,0.7600481,0.006577786,0.0008801012,0.000008926755,0.0004382062,0.00002393198,0.04681667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5193136,"threshold_uncertainty_score":0.4036037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138447845","doi":"10.1016/s0925-7721(02)00093-7","title":"Computing contour trees in all dimensions","year":2002,"lang":"en","type":"article","venue":"Computational Geometry","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"University of North Carolina at Chapel Hill; Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Simple (philosophy); Computer science; Contour line; Algorithm; Mathematics; Artificial intelligence; Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04481388461551654,"gpt":0.2730690683067274,"spread":0.2282551836912108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002183801,0.0001190157,0.0001421536,0.0004092315,0.00008513018,0.0001717898,0.0006404943,0.00003081738,0.00007584593],"category_scores_gemma":[0.0000432064,0.0001214339,0.00004544437,0.0009000767,0.00002952453,0.0005299794,0.0004102468,0.0001180692,0.0003292527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003409707,"about_ca_system_score_gemma":0.000008454937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001505558,"about_ca_topic_score_gemma":0.000005472115,"domain_scores_codex":[0.9987751,0.00004161935,0.0002504945,0.0003462973,0.0003191667,0.0002673184],"domain_scores_gemma":[0.99932,0.0002462297,0.00006861821,0.0002457312,0.00004731237,0.00007208247],"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":[0.000003897768,0.0008228574,0.01497465,0.00002670604,0.0001110886,0.0002819338,0.00118367,0.3001992,0.000058649,0.2780895,0.05567625,0.3485716],"study_design_scores_gemma":[0.0004547244,0.00002395047,0.04074008,0.00001620316,0.000002570825,0.000007598008,0.00002037995,0.9464344,0.000004625564,0.006095005,0.006039745,0.0001607266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06715496,0.0005112275,0.9234913,0.002107088,0.0005319049,0.0001758325,0.000008289673,0.0002456546,0.005773721],"genre_scores_gemma":[0.9149833,0.000009772241,0.08348027,0.0009890697,0.00006904097,0.000002462988,0.00003085957,0.000006405765,0.0004287857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8478284,"threshold_uncertainty_score":0.4951931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138271690","doi":"10.1109/icde.2007.367935","title":"Top-k Query Processing in Uncertain Databases","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":428,"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":"Tuple; Computer science; Semantics (computer science); Probabilistic logic; Construct (python library); Database; Query language; Materialized view; Query optimization; Space (punctuation); Theoretical computer science; Information retrieval; Data mining; View; Programming language; Artificial intelligence; Mathematics; Database design","retraction":null,"screen_n_in":null,"score":{"opus":0.03869003660168605,"gpt":0.307185340866784,"spread":0.2684953042650979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005302543,0.00005955322,0.00005747219,0.0001330769,0.00003442206,0.0001217715,0.000502771,0.00000976198,0.00002040494],"category_scores_gemma":[0.00001757769,0.00004988068,0.00001041895,0.0004544273,0.00001328644,0.001316826,0.0003038165,0.00004822501,0.0000360913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001706418,"about_ca_system_score_gemma":0.00001982825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002062513,"about_ca_topic_score_gemma":0.0002084077,"domain_scores_codex":[0.99928,0.000008432109,0.0001287747,0.0002237635,0.0001395542,0.0002194816],"domain_scores_gemma":[0.9996189,0.00002285375,0.00002304977,0.0002890231,0.00001234319,0.00003376393],"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":[0.000001880339,0.00005846588,0.005434789,0.00001858347,0.000001230951,0.0001071578,0.0001210956,0.00001343974,0.00007655337,0.08948026,0.002798395,0.9018881],"study_design_scores_gemma":[0.001698389,0.0001049689,0.1039185,0.0002454463,0.000008893512,0.0000193786,0.001279555,0.4352568,0.00663045,0.008504734,0.4409523,0.001380536],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003271708,0.00007169449,0.9645491,0.0004120504,0.0001041247,0.00006128152,7.99864e-7,0.0001204624,0.03140878],"genre_scores_gemma":[0.371998,0.00001616641,0.6217703,0.001690682,0.0001246292,0.000005038353,0.00002751134,0.000007381337,0.004360364],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9005076,"threshold_uncertainty_score":0.2034075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135843591","doi":"10.1145/511446.511489","title":"Probabilistic query expansion using query logs","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":427,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Sargable; Query optimization; Query expansion; Computer science; Probabilistic logic; Query language; RDF query language; Web search query; Web query classification; Query by Example; Boolean conjunctive query; Information retrieval; Data mining; Artificial intelligence; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.0558195065342248,"gpt":0.2403360045591247,"spread":0.1845164980248999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000148081,0.00009972078,0.00009290075,0.00008504734,0.00009094848,0.0002224846,0.0006067568,0.00002752833,0.0001967262],"category_scores_gemma":[0.00002270999,0.00008266822,0.00003500229,0.0002847383,0.00002745757,0.001089655,0.0003993222,0.00005815739,0.0002963671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002772803,"about_ca_system_score_gemma":0.00000760684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006007712,"about_ca_topic_score_gemma":0.00000657602,"domain_scores_codex":[0.9990689,0.00002819952,0.00014816,0.0003259031,0.0001998511,0.000228975],"domain_scores_gemma":[0.9992971,0.00002931114,0.000036909,0.0005547972,0.0000261559,0.00005573449],"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":[0.000002819276,0.0005573573,0.0006746617,0.0001160064,0.00004078471,0.0001957031,0.0006535296,0.001095215,0.001391906,0.3830292,0.07395373,0.5382891],"study_design_scores_gemma":[0.0001470614,0.00002877509,0.0002290605,0.00001837944,0.000005292507,0.00000876488,0.00001826598,0.9871587,0.0001759914,0.003652158,0.008366163,0.0001914051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01494381,0.0001028247,0.9581107,0.0007604071,0.0005768429,0.0001993364,0.000001240973,0.0003985696,0.02490629],"genre_scores_gemma":[0.5838065,0.00006205705,0.3950646,0.001989489,0.0003056869,0.0000165507,0.000009734143,0.00002454301,0.0187209],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9860635,"threshold_uncertainty_score":0.3809298,"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":"W1544455437","doi":"","title":"Proceedings of the 17th ACM conference on Information and knowledge management","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.02828568575252903,"gpt":0.2294291208878653,"spread":0.2011434351353363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009066393,0.0000488699,0.00004440659,0.00005334584,0.00006897993,0.00007265985,0.0007592576,0.000009595195,0.000004992412],"category_scores_gemma":[0.000007537385,0.00003011543,0.00001158317,0.0001870488,0.00003560893,0.001034432,0.0008828584,0.00002877859,0.00002930252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005418495,"about_ca_system_score_gemma":0.000006201631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002851229,"about_ca_topic_score_gemma":5.635493e-7,"domain_scores_codex":[0.9996141,0.000002275749,0.00009639665,0.00008473195,0.0001296731,0.00007285095],"domain_scores_gemma":[0.9996825,0.000006168552,0.00004640946,0.0002031481,0.00004527574,0.00001643277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001033099,0.00001999123,0.0004492637,0.00003062981,0.000006054399,1.715594e-7,0.000522493,2.661469e-7,0.000006451094,0.92224,0.0124672,0.0642565],"study_design_scores_gemma":[0.003225361,0.0005653178,0.4379986,0.0003425254,0.00004339842,0.0000289898,0.00230245,0.1450688,0.009349854,0.04432895,0.3557614,0.0009843983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04133134,0.00001065129,0.02207536,0.001631538,0.0001884278,0.0003826808,0.000001664585,0.00009547486,0.9342828],"genre_scores_gemma":[0.9723914,0.0001104735,0.02167672,0.0003251559,0.00001177263,0.000009655253,0.000001247808,0.000001623828,0.005471915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9310601,"threshold_uncertainty_score":0.1410902,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143682328","doi":"10.1007/s00778-004-0128-2","title":"Supporting top-k join queries in relational databases","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Joins; Computer science; Join (topology); Sort-merge join; Query optimization; Ranking (information retrieval); Hash join; Database; Relational database; Heuristic; Query language; Sargable; Information retrieval; Rank (graph theory); Heuristics; Relational algebra; Query expansion; Theoretical computer science; Web search query; Search engine; Programming language; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04003804845750331,"gpt":0.2958259358899701,"spread":0.2557878874324668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000942455,0.0000639756,0.0000673653,0.00009654262,0.00020542,0.0002267427,0.0006272252,0.000009518862,0.00005282147],"category_scores_gemma":[0.00007608397,0.0000422743,0.0000299244,0.0002441867,0.00003421716,0.001437122,0.0002795435,0.0002170816,0.00004982662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003481286,"about_ca_system_score_gemma":0.00007023131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000367678,"about_ca_topic_score_gemma":0.0000262904,"domain_scores_codex":[0.9991531,0.00004155225,0.0002306436,0.0001125839,0.0002492864,0.0002128277],"domain_scores_gemma":[0.9995353,0.00004372435,0.0001168578,0.0002441402,0.00002114298,0.0000387867],"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":[0.00001151408,0.0001209135,0.01438272,0.000009410037,0.00003461154,0.0004154485,0.002238633,0.004176923,0.000236198,0.8991257,0.008121914,0.07112599],"study_design_scores_gemma":[0.004895445,0.0002619804,0.2190561,0.0004689346,0.00004181938,0.002477039,0.001827708,0.03179492,0.003169,0.4493948,0.2854472,0.001164986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08592413,0.000247782,0.8941901,0.01591039,0.000657874,0.00009341004,0.000006407854,0.00005626861,0.002913599],"genre_scores_gemma":[0.7763634,0.0001651284,0.2193082,0.001698347,0.0008088802,0.000005820883,0.00002283884,0.00001440199,0.001613016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6904392,"threshold_uncertainty_score":0.2186486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1517348552","doi":"","title":"Maximal vector computation in large data sets","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Curse of dimensionality; Convex hull; Computer science; Set (abstract data type); Computation; Field (mathematics); Algorithm; Running time; Mathematics; Regular polygon; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04080861114137971,"gpt":0.2986350357834028,"spread":0.2578264246420231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002628432,0.00005266187,0.00005425516,0.0000696682,0.00002648897,0.0001506677,0.001092632,0.00001299803,0.00005265505],"category_scores_gemma":[0.000007971152,0.00004790743,0.000007173015,0.0002163807,0.00000511193,0.001847123,0.001032616,0.0000426986,0.0003411532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000133973,"about_ca_system_score_gemma":0.000009024919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000182047,"about_ca_topic_score_gemma":0.0001264258,"domain_scores_codex":[0.9993061,0.00001640658,0.0001067215,0.0002735519,0.0001327665,0.0001643842],"domain_scores_gemma":[0.999422,0.00001603277,0.0000201376,0.0005079319,0.000008233742,0.00002563535],"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":[0.000002104352,0.0002253023,0.001546902,0.000008638945,0.000008417017,0.00002590965,0.0001571281,0.0002514786,0.00001493555,0.0633448,0.07750443,0.8569099],"study_design_scores_gemma":[0.0002783189,0.000008634313,0.0157086,0.000002725458,8.078006e-7,9.866077e-7,0.000007640045,0.9338709,0.00001771451,0.0003062685,0.04972308,0.00007440292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002567556,0.00002471494,0.9867389,0.002818303,0.0001416307,0.00008419077,0.00001913218,0.0001233629,0.007482164],"genre_scores_gemma":[0.5380526,0.000006126891,0.4599163,0.0009182369,0.00008396469,0.000002277373,0.0002868621,0.000004224294,0.0007294466],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9336193,"threshold_uncertainty_score":0.4384948,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117379916","doi":"10.1109/icde.2005.92","title":"Monitoring k-Nearest Neighbor Queries over Moving Objects","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":307,"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":"Search engine indexing; Computer science; Scalability; k-nearest neighbors algorithm; Grid; Data mining; Tree (set theory); Best bin first; Nearest neighbor search; R-tree; Object (grammar); Spatial database; Artificial intelligence; Spatial analysis; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01336887839657592,"gpt":0.2457943660586419,"spread":0.232425487662066,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001077251,0.00009752669,0.00007681076,0.00006842743,0.0001057309,0.0004774391,0.0006724987,0.00002086751,0.00009619522],"category_scores_gemma":[0.00001573373,0.00008516241,0.0000297754,0.0002106976,0.00001579864,0.002239634,0.0005255559,0.0000621896,0.00031481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002633714,"about_ca_system_score_gemma":0.0000133792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006412081,"about_ca_topic_score_gemma":0.00002033954,"domain_scores_codex":[0.9991605,0.0000113102,0.0001149771,0.0002601796,0.0002084845,0.0002445522],"domain_scores_gemma":[0.9994337,0.00002825843,0.00003001871,0.0004318919,0.00001854353,0.00005760579],"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":[0.000002071062,0.00006526091,0.01268947,0.00001650027,0.00002573828,0.00002913919,0.0006249039,0.0001511573,0.000571659,0.09421487,0.004724487,0.8868847],"study_design_scores_gemma":[0.001346576,0.0001509617,0.1756628,0.0001432385,0.00002102945,0.00001176657,0.0005178123,0.3960638,0.04298736,0.002656728,0.3789272,0.001510781],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06814007,0.0003470975,0.7357662,0.002599268,0.002241099,0.0002806033,0.000002319812,0.001491088,0.1891323],"genre_scores_gemma":[0.8051842,0.00004032377,0.1847251,0.0003425222,0.0006811144,0.000008043694,0.000001546075,0.000009283793,0.009007884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.885374,"threshold_uncertainty_score":0.4603956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168503413","doi":"10.1109/icde.2000.839397","title":"DB2 advisor: an optimizer smart enough to recommend its own indexes","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; IBM (Canada)","funders":"","keywords":"Knapsack problem; Computer science; Index (typography); Selection (genetic algorithm); Quality (philosophy); Relational database management system; Interface (matter); Data mining; World Wide Web; Algorithm; Artificial intelligence; Relational database; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.04929654506499023,"gpt":0.2521579843231119,"spread":0.2028614392581217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002138799,0.0001513321,0.0001363713,0.0001405607,0.0001157895,0.0004683013,0.001415039,0.00003616901,0.001665899],"category_scores_gemma":[0.00001697482,0.0001282067,0.00003792553,0.0004132712,0.00001082562,0.001986221,0.0006889788,0.00008397025,0.001902443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810227,"about_ca_system_score_gemma":0.000004241367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003056044,"about_ca_topic_score_gemma":0.00001866378,"domain_scores_codex":[0.9986973,0.00004042665,0.0001855295,0.000485622,0.0002368848,0.0003542748],"domain_scores_gemma":[0.9989279,0.00002755999,0.00003584665,0.0007898107,0.00003488719,0.0001840304],"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":[0.00000346319,0.0003197302,0.0001172497,0.000008363098,0.00002903732,0.00002631025,0.0007964229,0.0001548528,0.00005064817,0.04821375,0.3957033,0.5545768],"study_design_scores_gemma":[0.0003722578,0.0002069396,0.0003441851,0.000008810971,0.000005269779,0.000003939368,0.00003697878,0.1478977,0.0005442376,0.0003534729,0.849864,0.0003622395],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002972534,0.0001204838,0.6672298,0.04779606,0.00152489,0.0006573445,0.00001907266,0.001033188,0.2786466],"genre_scores_gemma":[0.1260354,0.0001393521,0.7338761,0.01429244,0.0003352802,0.0000572551,0.00003105546,0.0000335324,0.1251996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5542146,"threshold_uncertainty_score":0.9992467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110610722","doi":"10.1145/872757.872798","title":"Mapping data in peer-to-peer systems","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":253,"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; Semantic mapping; Data mapping; Semantics (computer science); Peer-to-peer; Information retrieval; Data sharing; Listing (finance); Data exchange; Theoretical computer science; Data mining; Database; Programming language; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06195602089747872,"gpt":0.281265200726068,"spread":0.2193091798285893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001207493,0.00007282377,0.00008860135,0.000154685,0.00003174205,0.0004332499,0.001978225,0.00001671101,0.00002314152],"category_scores_gemma":[0.0001228354,0.00006341123,0.000008211057,0.000588191,0.000005327082,0.001080462,0.0009203865,0.00005244734,0.0004450813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158673,"about_ca_system_score_gemma":0.00001529964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001390356,"about_ca_topic_score_gemma":0.00002268903,"domain_scores_codex":[0.9987854,0.00003738936,0.0001518724,0.0003993561,0.0004030286,0.0002229864],"domain_scores_gemma":[0.9984459,0.00002278596,0.00002024643,0.001409828,0.00004461053,0.00005664132],"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":[5.025433e-7,0.0000752147,0.002581767,0.00003368857,0.00001631465,0.00007122175,0.0004225404,0.0001918114,0.00003757754,0.5762867,0.3871346,0.03314806],"study_design_scores_gemma":[0.0001425777,0.000007544777,0.0008403894,0.00001491424,6.498743e-7,0.00000285466,0.0001944371,0.1143396,0.00001633175,0.0002633396,0.8840454,0.0001318947],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004324687,0.00003161267,0.9044908,0.00258363,0.0007433607,0.0001700643,0.000007247388,0.0001024792,0.09143838],"genre_scores_gemma":[0.2903966,0.00001008858,0.4898344,0.00230044,0.0001852898,0.00003292553,0.000163553,0.00002121737,0.2170555],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5760234,"threshold_uncertainty_score":0.5720768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127782281","doi":"","title":"Catching the best views of skyline: a semantic approach based on decisive subspaces","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":245,"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":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Set (abstract data type); Theoretical computer science; Object (grammar); Space (punctuation); Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03357830335054178,"gpt":0.2713407237238883,"spread":0.2377624203733466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004512719,0.0001058892,0.000126486,0.00008450995,0.00008504308,0.0001455674,0.001232118,0.00001788277,0.0000155346],"category_scores_gemma":[0.00003409429,0.00006032281,0.00005774896,0.0003357008,0.00003178728,0.0003889984,0.0002225287,0.0000783971,0.0000887288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001043915,"about_ca_system_score_gemma":0.00001775069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005429008,"about_ca_topic_score_gemma":0.00005668971,"domain_scores_codex":[0.9990354,0.00003688594,0.0001842924,0.000265467,0.0003101297,0.0001678198],"domain_scores_gemma":[0.9989717,0.0001501121,0.0000783744,0.0007276163,0.00003987653,0.00003231172],"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":[0.00001135055,0.0007523359,0.0005365241,0.00005495291,0.00004384923,0.000006739563,0.001085274,0.01589442,0.00005913345,0.0981432,0.01932735,0.8640849],"study_design_scores_gemma":[0.0002392533,0.00004951479,0.0003034934,0.00002205018,0.000009570465,0.000001012391,0.0001642424,0.9811926,0.0004038267,0.0003001938,0.0172065,0.0001077259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003422966,0.00007002037,0.9620369,0.003573406,0.00008923886,0.0002161502,0.00000203507,0.00004861804,0.03054066],"genre_scores_gemma":[0.5880015,0.00002023645,0.4083267,0.002078846,0.0001102346,0.00001627479,0.000006984249,0.000007310392,0.001431856],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9652982,"threshold_uncertainty_score":0.2459893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991782162","doi":"10.1111/1467-9671.00127","title":"A Perspective on the Fundamentals of Fuzzy Sets and their Use in Geographic Information Systems","year":2003,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":188,"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":"Fuzzy logic; Data mining; Computer science; Geographic information system; Fuzzy set; Sophistication; Perspective (graphical); Relation (database); AM/FM/GIS; Fuzzy set operations; GIS applications; Defuzzification; Artificial intelligence; Fuzzy number; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02144806511388659,"gpt":0.235941126157451,"spread":0.2144930610435644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002814663,0.000062927,0.00007520088,0.0002760401,0.00004808343,0.000120536,0.0001576792,0.00001959609,0.000005557078],"category_scores_gemma":[0.000007872765,0.00004398376,0.00002069935,0.0005063284,0.00003836382,0.001193031,0.000006495645,0.00008471059,0.0000031274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003750468,"about_ca_system_score_gemma":0.000008686942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008601722,"about_ca_topic_score_gemma":0.000161487,"domain_scores_codex":[0.9995058,0.00007008051,0.0001466788,0.00009742986,0.00008829559,0.00009177611],"domain_scores_gemma":[0.9996276,0.00008724687,0.00003889585,0.0002136698,0.0000196583,0.00001296391],"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":[0.00003246336,0.0006478591,0.007280992,0.0001199746,0.0001471306,0.000005746071,0.04541002,0.009029078,0.0001087302,0.8764462,0.0002520432,0.0605197],"study_design_scores_gemma":[0.009571858,0.001400301,0.3031932,0.001315,0.00008512701,0.0000861748,0.1766946,0.4171944,0.003749261,0.0353087,0.04917874,0.002222726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4794706,0.00024256,0.5006421,0.0012092,0.0005368791,0.001288984,0.00009450938,0.00008425765,0.01643095],"genre_scores_gemma":[0.9992419,0.00006953037,0.0005661797,0.000053775,0.000001254798,0.00002751051,0.000001347376,0.000001633114,0.00003681393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8411376,"threshold_uncertainty_score":0.1793606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003043371","doi":"10.1080/03461230601110447","title":"On composite lognormal-Pareto models","year":2007,"lang":"en","type":"article","venue":"Scandinavian Actuarial Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pareto principle; Log-normal distribution; Mathematics; Econometrics; Composite number; Pareto distribution; Statistics; Applied mathematics; Computer science; Mathematical optimization; Mathematical economics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01729185838393545,"gpt":0.2500035017044091,"spread":0.2327116433204737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001069458,0.0001960198,0.0001928164,0.0003266898,0.0004011352,0.000929139,0.001434369,0.00006652263,0.00006391273],"category_scores_gemma":[0.00001833878,0.0001650599,0.0001161525,0.0003286633,0.00004427903,0.001870313,0.0002694727,0.000421366,0.0001250372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000120712,"about_ca_system_score_gemma":0.0000351983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001594712,"about_ca_topic_score_gemma":0.000006405129,"domain_scores_codex":[0.9981447,0.00004923697,0.0003617515,0.0003014703,0.0005556761,0.0005871738],"domain_scores_gemma":[0.9989195,0.00008383387,0.0001829759,0.0004292194,0.00006334735,0.0003210934],"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":[0.0003519218,0.0003666038,0.0008432838,0.00001235098,0.0001730737,0.001642925,0.001003014,0.002051557,0.0003959095,0.5098782,0.03636065,0.4469206],"study_design_scores_gemma":[0.0117697,0.002813715,0.02135844,0.0005642454,0.0001365537,0.002418301,0.0002866682,0.1807383,0.0040909,0.7323725,0.0406429,0.002807786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01186032,0.00003291849,0.9555722,0.0006047809,0.002812142,0.000114328,0.00000519835,0.0001004115,0.0288977],"genre_scores_gemma":[0.9748145,0.00002937364,0.02244881,0.0009569952,0.001137085,0.000001153172,0.000009565527,0.00001522347,0.000587289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629542,"threshold_uncertainty_score":0.8959709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751694342","doi":"10.14778/3137628.3137630","title":"Trajectory similarity join in spatial networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":179,"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":"Beijing Nova Program; King Abdullah University of Science and Technology; National Natural Science Foundation of China; Innovationsfonden","keywords":"Join (topology); Computer science; Pruning; Similarity (geometry); Trajectory; Nearest neighbor search; Heuristic; Matching (statistics); Data mining; Scheduling (production processes); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.01795752554889163,"gpt":0.2326463657509419,"spread":0.2146888402020503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004762782,0.0001147106,0.000147587,0.00005779784,0.0002043526,0.0003233687,0.002783312,0.0000347733,0.000006704161],"category_scores_gemma":[0.00006288499,0.00008335499,0.00006796947,0.00009639008,0.00007470499,0.0008001223,0.001557235,0.0001495145,0.000003372309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004123908,"about_ca_system_score_gemma":0.00001220457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002954345,"about_ca_topic_score_gemma":0.00005232555,"domain_scores_codex":[0.9989737,0.000005084467,0.0002060454,0.0002776475,0.0002881765,0.0002493987],"domain_scores_gemma":[0.9992309,0.00001206393,0.0002590413,0.0004156951,0.00004380436,0.00003855012],"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":[0.00008183008,0.001203579,0.2482929,0.0003980296,0.0001467031,0.00001722348,0.002130505,0.0006340799,0.005901243,0.2337164,0.03370338,0.4737741],"study_design_scores_gemma":[0.002774164,0.0001968186,0.7102966,0.0003220814,0.00004247234,0.000006086137,0.0001228642,0.2255824,0.03072217,0.01845042,0.01079493,0.0006890012],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.611132,0.0006899948,0.1207894,0.0340441,0.009884554,0.005164852,0.00003494446,0.0006155878,0.2176446],"genre_scores_gemma":[0.9957062,0.00003447791,0.003697341,0.0001359032,0.0001067913,0.00002028274,4.767567e-7,0.000005522338,0.0002929757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4730851,"threshold_uncertainty_score":0.5172132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126431245","doi":"10.1007/s00778-006-0029-7","title":"Algorithms and analyses for maximal vector computation","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Curse of dimensionality; Computation; Field (mathematics); Computer science; Running time; Divide and conquer algorithms; Algorithm; Mathematics; Discrete mathematics; Theoretical computer science; Combinatorics; Artificial intelligence; Data mining; Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04801050073090831,"gpt":0.3160797680561167,"spread":0.2680692673252084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004068899,0.00007566806,0.0000847071,0.00007739468,0.0003167111,0.0006135868,0.0004253392,0.00001412199,0.000004271776],"category_scores_gemma":[0.00001015548,0.00004752437,0.00004640043,0.0001598302,0.00003464094,0.0005260815,0.0001131309,0.0000810377,0.000006367097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001266851,"about_ca_system_score_gemma":0.00001373697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001825488,"about_ca_topic_score_gemma":0.000002583654,"domain_scores_codex":[0.9993457,0.00003552895,0.0001548348,0.0001251866,0.000169162,0.0001695929],"domain_scores_gemma":[0.999611,0.00007719451,0.00009888702,0.0001250817,0.00005290908,0.00003495907],"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":[0.00002304832,0.0001189074,0.000401876,0.00002106186,0.000131258,0.00004166208,0.000282913,0.002337911,0.001185608,0.04524256,0.04910811,0.9011051],"study_design_scores_gemma":[0.001025395,0.0001734617,0.01984459,0.00001668204,0.00005730529,0.0002369784,0.00006151869,0.8637421,0.0005723418,0.09827954,0.01576512,0.0002249852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007514936,0.0002853627,0.988992,0.002406414,0.0003157703,0.00009388038,0.00000458361,0.00003417216,0.0003528726],"genre_scores_gemma":[0.5305412,0.0000774954,0.465851,0.0004869022,0.001773518,0.00001134447,0.00002047521,0.0000174165,0.001220642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9008801,"threshold_uncertainty_score":0.5916832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806337402","doi":"10.1016/j.patcog.2018.05.030","title":"A fast clustering algorithm based on pruning unnecessary distance computations in DBSCAN for high-dimensional data","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"State Key Laboratory of Computer Aided Design and Computer Graphics; National Laboratory of Pattern Recognition; Fujian Provincial Department of Science and Technology; Zhejiang University; Huaqiao University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"DBSCAN; Computer science; Pruning; Computation; Cluster analysis; Noise (video); Dimension (graph theory); Algorithm; Search engine indexing; Pattern recognition (psychology); Data mining; Mathematics; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Combinatorics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0527162703613487,"gpt":0.285088083781462,"spread":0.2323718134201133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003565673,0.00013486,0.0001220751,0.00019661,0.000158266,0.0001989416,0.000703599,0.00003141949,0.00002071235],"category_scores_gemma":[0.00002504603,0.0001412653,0.00002046307,0.00029478,0.00003574783,0.000940343,0.0003676299,0.00008518115,0.0000651057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004135518,"about_ca_system_score_gemma":0.00002293476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009584895,"about_ca_topic_score_gemma":0.0002939348,"domain_scores_codex":[0.9986662,0.00005386156,0.0002299299,0.0005719177,0.0002272155,0.0002508695],"domain_scores_gemma":[0.9990994,0.0001415437,0.0001022934,0.0005301538,0.0000798124,0.00004681476],"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":[0.000008688505,0.00009568091,0.0001961983,0.00002768021,0.000006878696,0.000007424597,0.00005127994,0.0005045374,0.000008911801,0.00002897568,0.0007217252,0.998342],"study_design_scores_gemma":[0.0008582362,0.000125416,0.002813788,0.000224276,0.000007137425,0.00000137838,0.00001487956,0.9942054,0.0001003468,0.001132352,0.0003241886,0.0001925826],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00311879,0.000004673942,0.9943472,0.0007311655,0.0005553772,0.0003389852,0.0006363722,0.0001027165,0.0001647717],"genre_scores_gemma":[0.5817257,0.00000203262,0.4111517,0.001401996,0.0003542075,0.00007778685,0.005231484,0.0000205035,0.00003458771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9981495,"threshold_uncertainty_score":0.5760633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119462844","doi":"10.1109/icde.2001.914848","title":"Spatial clustering in the presence of obstacles","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":161,"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":"Cluster analysis; Computer science; Data stream clustering; Pruning; CURE data clustering algorithm; Function (biology); Canopy clustering algorithm; Data mining; Scalability; Space (punctuation); Correlation clustering; Obstacle; Artificial intelligence; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.03443696842166376,"gpt":0.2332489990852773,"spread":0.1988120306636136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001340558,0.00003079236,0.00003685263,0.00003230968,0.00001569447,0.00006179162,0.0008839418,0.000006459981,0.00004477863],"category_scores_gemma":[0.00001198881,0.00001936647,0.00001107723,0.0001573642,0.00001450364,0.0003536749,0.0002555869,0.00002719684,0.00001842136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000205552,"about_ca_system_score_gemma":9.256234e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671892,"about_ca_topic_score_gemma":0.0001175845,"domain_scores_codex":[0.9995933,0.00002120815,0.00008042263,0.00009376122,0.0001291727,0.00008220679],"domain_scores_gemma":[0.9996327,0.00004554743,0.00001864097,0.0002904496,0.000005553937,0.000007089842],"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":[0.000001107577,0.0001431218,0.00277506,0.00002602715,0.000006031446,0.00002891709,0.003230664,0.0002542153,0.0001242875,0.06729084,0.009649236,0.9164705],"study_design_scores_gemma":[0.0001123641,0.00002083207,0.007906994,0.000007525179,6.766779e-7,0.000001047092,0.00008061543,0.986537,0.0001805192,0.0005772325,0.004526147,0.00004908045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004986909,0.00004705246,0.9543904,0.001354291,0.0001350412,0.0001027341,6.977811e-7,0.00003102811,0.03895184],"genre_scores_gemma":[0.9842347,0.00001484578,0.0149398,0.0001409971,0.00001787181,0.000002713118,3.060432e-7,9.516515e-7,0.0006478333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9862828,"threshold_uncertainty_score":0.1642599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338354263","doi":"","title":"Toward better support for spatial decision making: defining the characteristics of spatial on-line analytical processing (solap)","year":2019,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Online analytical processing; Exploit; Data warehouse; Computer science; Spatial analysis; Line (geometry); Decision support system; Data mining; Data science; Geography; Cartography; Mathematics; Remote sensing","retraction":null,"screen_n_in":null,"score":{"opus":0.02906984507809188,"gpt":0.2903889626372823,"spread":0.2613191175591905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000511753,0.0001486337,0.0002644238,0.00009050298,0.00009000809,0.0002409272,0.0009124479,0.0000469886,0.00008547348],"category_scores_gemma":[0.0001680386,0.0001015169,0.0000850344,0.000155179,0.00004330498,0.0002732065,0.0004037002,0.0001026656,0.000148645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001588788,"about_ca_system_score_gemma":0.00004846451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007730299,"about_ca_topic_score_gemma":0.000002046351,"domain_scores_codex":[0.9984824,0.00002329964,0.0004405639,0.0003248606,0.0004289964,0.0002998553],"domain_scores_gemma":[0.9987505,0.0003285528,0.0002151038,0.0005798267,0.00008522508,0.00004080694],"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":[0.00004754439,0.00008713395,0.001949361,0.0001389939,0.00002593662,0.000006467394,0.0002478349,0.00003346957,0.000009959131,0.01293594,0.000698656,0.9838187],"study_design_scores_gemma":[0.0004818131,0.0003890411,0.01351067,0.0001734888,0.00003739817,0.000004184174,0.00001979746,0.9776957,0.0001023853,0.003200792,0.004203648,0.0001810718],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03150706,0.00000426063,0.9656096,0.0009318023,0.0004079986,0.00035786,0.00003001604,0.00004582399,0.001105629],"genre_scores_gemma":[0.9133058,8.355618e-7,0.08559673,0.0008187372,0.0001440014,0.00001382434,0.00003334947,0.00001212602,0.00007464667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9836376,"threshold_uncertainty_score":0.4139739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017733151","doi":"10.1109/iccit.2007.148","title":"Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers","year":2007,"lang":"en","type":"article","venue":"2007 International Conference on Convergence Information Technology (ICCIT 2007)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; k-nearest neighbors algorithm; Computer science; Machine learning; Bayes error rate; Classifier (UML); Bayes classifier; Random subspace method; Pattern recognition (psychology); Bayesian probability; Bayes' theorem; Data mining; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.02490013171729916,"gpt":0.2604650408833423,"spread":0.2355649091660431,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008000145,0.0002155596,0.0001780277,0.0006637947,0.0002310276,0.0002067805,0.001698264,0.0001760831,0.000231968],"category_scores_gemma":[0.0002303654,0.0001761392,0.00004273883,0.0006547805,0.0005508193,0.002674911,0.0004361249,0.0003947424,0.0001762815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018246,"about_ca_system_score_gemma":0.0001079189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002652344,"about_ca_topic_score_gemma":0.000007847227,"domain_scores_codex":[0.9981056,0.00002151417,0.0006687075,0.0002748464,0.0005676798,0.0003616686],"domain_scores_gemma":[0.9984016,0.0001032873,0.0005095959,0.0004442615,0.0004537514,0.0000874744],"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":[0.00002218383,0.00003279325,0.03007096,0.0000339751,0.00006304773,0.000003141577,0.0003942575,0.0000544426,0.0003340449,0.7916552,0.003320423,0.1740155],"study_design_scores_gemma":[0.001071234,0.0004974811,0.05739089,0.0002540375,0.00002033225,0.00003877027,0.003352001,0.8694682,0.01101956,0.008314503,0.04786939,0.000703607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3773804,0.00008348643,0.5219361,0.0138929,0.004943113,0.0008704689,0.00005337735,0.0006370599,0.08020312],"genre_scores_gemma":[0.988596,0.0002730399,0.009461794,0.001168319,0.00006174424,0.00002063884,0.00003425639,0.000006366062,0.0003778098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8694137,"threshold_uncertainty_score":0.7182748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133246278","doi":"10.14778/1453856.1453895","title":"Efficient search for the top-k probable nearest neighbors in uncertain databases","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":149,"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; Data mining; Query optimization; Online aggregation; k-nearest neighbors algorithm; Query language; Semantics (computer science); Information retrieval; Sargable; Object (grammar); Point (geometry); Database; Feature (linguistics); Web query classification; Web search query; Search engine; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05346318793657699,"gpt":0.2715280562480217,"spread":0.2180648683114447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006452869,0.0001281898,0.0001361242,0.00008646279,0.000266293,0.00009554292,0.001869526,0.00001552029,0.000005675796],"category_scores_gemma":[0.00006846619,0.00007130609,0.00006995328,0.0006123806,0.0001055648,0.0002618988,0.001130636,0.0001058427,0.000005242524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006247049,"about_ca_system_score_gemma":0.00004495695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001971336,"about_ca_topic_score_gemma":0.000007067521,"domain_scores_codex":[0.9985974,0.000007216346,0.0002319851,0.0003326134,0.0004692359,0.0003615712],"domain_scores_gemma":[0.9993073,0.0001152242,0.0001000381,0.0003355957,0.0001031643,0.00003867878],"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":[0.0001579421,0.001646169,0.07907028,0.0006771564,0.0001951438,0.000008744637,0.006120609,0.02463807,0.003978821,0.796243,0.04499962,0.04226441],"study_design_scores_gemma":[0.004220396,0.0003902789,0.04706459,0.0004220211,0.00006859218,0.00002580775,0.001528066,0.7831204,0.0797512,0.002918605,0.07962988,0.0008601595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8509537,0.00151265,0.08600765,0.03346977,0.002081388,0.0124648,0.0001696182,0.0003754961,0.01296495],"genre_scores_gemma":[0.9737758,0.00007928286,0.02437377,0.0003293639,0.00009826134,0.0002922222,0.000005310293,0.00001474321,0.001031264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7933244,"threshold_uncertainty_score":0.3474076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W151938044","doi":"10.1137/1.9781611972757.5","title":"Summarizing and Mining Skewed Data Streams","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Crohn's and Colitis Foundation of Canada","keywords":"Skew; Skewness; Data stream mining; Computer science; Data mining; Data stream; Space (punctuation); Zipf's law; Point (geometry); Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04579868955532916,"gpt":0.2686245177712225,"spread":0.2228258282158933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026451,0.00005756654,0.0000540783,0.00004031153,0.00006110873,0.000330291,0.0010925,0.00001147723,0.00002198918],"category_scores_gemma":[0.00001266172,0.0000488531,0.000005466548,0.0001062785,0.00001338355,0.001967144,0.001929257,0.00002837288,0.00003660934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004024475,"about_ca_system_score_gemma":0.000006114422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002468114,"about_ca_topic_score_gemma":0.00004325037,"domain_scores_codex":[0.9993622,0.000008854534,0.00008190328,0.0003043716,0.0001027786,0.0001399483],"domain_scores_gemma":[0.9991279,0.0000291149,0.00001982877,0.0007748941,0.000006672959,0.00004156562],"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":[2.220974e-7,0.00001033342,0.0004825184,0.000002221369,0.000005895839,0.000003096078,0.00005524644,0.000002017159,0.00001438571,0.01633627,0.01541376,0.967674],"study_design_scores_gemma":[0.0002047455,0.00001271237,0.001026583,0.000007382549,0.000004415238,0.000002643644,0.00005997378,0.7330445,0.00008643216,0.0002002541,0.2652194,0.0001309703],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01252767,0.0002389159,0.9074159,0.00546939,0.0002432125,0.0001230983,0.00001470605,0.0003971092,0.07356995],"genre_scores_gemma":[0.1009138,0.00005545361,0.892353,0.0008377933,0.000178527,0.000001478033,0.00007296902,0.00000543188,0.005581575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9675431,"threshold_uncertainty_score":0.3185004,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141296717","doi":"10.1145/1989734.1989741","title":"MoveMine","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":133,"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":"Army Research Laboratory; Air Force Office of Scientific Research; Division of Computing and Communication Foundations; National Science Foundation","keywords":"Computer science; Data mining; Object (grammar); Swarm behaviour; Focus (optics); Trajectory; Cluster analysis; Data stream mining; Movement (music); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03626296199891101,"gpt":0.2355153862271245,"spread":0.1992524242282135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001041678,0.0001149101,0.000131651,0.0004180202,0.0001103095,0.00005267391,0.0008721337,0.00009555619,0.00003468819],"category_scores_gemma":[0.000008462785,0.00009915229,0.00002611284,0.0004733841,0.00006597867,0.0002272478,0.00004325113,0.0001382742,0.0001172853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001363374,"about_ca_system_score_gemma":0.000006417642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009115322,"about_ca_topic_score_gemma":0.000006941615,"domain_scores_codex":[0.9992013,0.00001212311,0.0001894694,0.0003150428,0.00009249586,0.0001895439],"domain_scores_gemma":[0.9989673,0.00002186569,0.00004534723,0.0008865892,0.00003542918,0.00004349762],"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":[0.000004054457,0.000173114,0.0001444453,0.00002551055,0.00007834333,0.00002563018,0.0002027873,0.000009418904,0.000090878,0.3843445,0.0002899057,0.6146114],"study_design_scores_gemma":[0.001965903,0.003785569,0.0008232212,0.0004955689,0.0001875275,0.0007141052,0.004480657,0.06831716,0.1290991,0.2453701,0.5420275,0.002733578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001279148,0.0002734441,0.9945652,0.0006355307,0.0006271501,0.0001746764,0.000004820776,0.000415658,0.0020243],"genre_scores_gemma":[0.9724383,0.0003942311,0.02445271,0.00007686701,0.00001856957,0.00008845296,0.000001573652,0.00001040609,0.002518905],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9711592,"threshold_uncertainty_score":0.4043313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162783807","doi":"10.14778/2021017.2021025","title":"Keyword search in graphs","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Substructure; Clique; Computer science; Graph; Combinatorics; Theoretical computer science; Time complexity; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.03651081320407087,"gpt":0.2195111061961708,"spread":0.1830002929920999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004017705,0.00008809684,0.0001010769,0.0001424784,0.00004286028,0.00005669384,0.001791588,0.00001831342,0.00001677695],"category_scores_gemma":[0.00001333902,0.00006020477,0.00005333316,0.0005919952,0.00004607272,0.000541179,0.001069795,0.00009520025,0.0000154169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002281415,"about_ca_system_score_gemma":0.000009097477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255494,"about_ca_topic_score_gemma":0.000003667571,"domain_scores_codex":[0.9990399,0.000004473394,0.0001784105,0.0002336189,0.000306961,0.0002365752],"domain_scores_gemma":[0.9996407,0.000007751302,0.00007084211,0.000193883,0.00005158335,0.00003522365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001416894,0.0003261295,0.03940989,0.00008708902,0.0000343614,0.000002583907,0.003961796,0.00000168828,0.002874808,0.9028099,0.003258864,0.04721879],"study_design_scores_gemma":[0.002839522,0.0005142487,0.2403772,0.0004110273,0.00004117369,0.00001632068,0.001511221,0.01001033,0.4510853,0.2804068,0.01185708,0.00092981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6515311,0.0002331193,0.003539546,0.003061783,0.001140578,0.001670766,0.000006637375,0.0002657971,0.3385507],"genre_scores_gemma":[0.9822847,0.00003951294,0.01686749,0.0001187717,0.00001440654,0.00002554233,2.550495e-7,0.000005443708,0.0006438605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.622403,"threshold_uncertainty_score":0.3329246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071465809","doi":"10.1016/j.jmva.2007.01.013","title":"From moments of sum to moments of product","year":2007,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Product (mathematics); Random variable; Moment (physics); Identity (music); Quadratic equation; Multivariate statistics; Applied mathematics; Algebra of random variables; Sum of normally distributed random variables; Multivariate random variable; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01762470161886203,"gpt":0.2967131886920912,"spread":0.2790884870732292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001498703,0.0001260255,0.0005322044,0.001096678,0.00002922011,0.00004942199,0.001216282,0.00002725781,0.0000446091],"category_scores_gemma":[0.0001130723,0.000100727,0.0002968042,0.002083868,0.00001943285,0.0006821048,0.0003423106,0.00009667327,0.000005729077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004342832,"about_ca_system_score_gemma":0.00002582553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005043523,"about_ca_topic_score_gemma":0.00001741285,"domain_scores_codex":[0.9978025,0.00005611447,0.0009331161,0.000240223,0.0007525686,0.0002154642],"domain_scores_gemma":[0.9978877,0.00008122808,0.0009791099,0.000559092,0.0003594288,0.0001334532],"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":[0.0008384211,0.006483383,0.2342979,0.000163201,0.05165912,0.0005144032,0.01589174,0.0277859,0.241451,0.002733401,0.009907651,0.4082738],"study_design_scores_gemma":[0.004249436,0.0007964085,0.7776753,0.0002287927,0.004420012,0.000004368923,0.0007477946,0.06335957,0.1378511,0.002167716,0.007722359,0.0007771848],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3511045,0.0000623125,0.6477848,0.0003966119,0.0003044035,0.00008568848,0.00001947295,0.000006984744,0.0002352665],"genre_scores_gemma":[0.9004146,0.00001846793,0.0989939,0.00004825876,0.0001304279,4.446441e-7,0.00000712062,0.000005238956,0.0003814987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5493101,"threshold_uncertainty_score":0.4107529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160152607","doi":"10.14778/1687627.1687754","title":"Efficient method for maximizing bichromatic reverse nearest neighbor","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; k-nearest neighbors algorithm; Point (geometry); Best bin first; Exponential function; Algorithm; Exponential growth; Theoretical computer science; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01458119393423405,"gpt":0.2572641271071092,"spread":0.2426829331728751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006653243,0.00015014,0.0001924429,0.00009486605,0.0001523825,0.0001758173,0.001484499,0.00002654132,0.000004913277],"category_scores_gemma":[0.00009940144,0.0001026985,0.0001301104,0.0004159688,0.00002353691,0.000234822,0.0004301501,0.00006970707,0.000006988207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005380619,"about_ca_system_score_gemma":0.00001566073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456355,"about_ca_topic_score_gemma":2.686304e-7,"domain_scores_codex":[0.9987003,0.000006684613,0.0002858811,0.0003376298,0.0003645704,0.0003049485],"domain_scores_gemma":[0.9992753,0.00004986282,0.0002402601,0.0002728761,0.0001051833,0.0000565302],"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":[0.00003504273,0.0005335892,0.0001066098,0.0003703237,0.00008671777,0.000001635318,0.001463111,0.0008019512,0.0363678,0.7219895,0.02968973,0.208554],"study_design_scores_gemma":[0.002142952,0.000513093,0.003280138,0.0003813149,0.0001333378,0.00001635071,0.0003618814,0.8581399,0.08078135,0.02961672,0.02408257,0.0005503957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02502903,0.0002592309,0.9225783,0.02990946,0.001468002,0.003988468,0.00002602421,0.0004478864,0.01629365],"genre_scores_gemma":[0.23785,0.00001037679,0.760218,0.001074257,0.0001026116,0.00006662645,0.00000152704,0.00001157998,0.0006650704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.857338,"threshold_uncertainty_score":0.4187925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057058417","doi":"10.1145/1132863.1132873","title":"Approximation and streaming algorithms for histogram construction problems","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":127,"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":"Histogram; Computer science; Algorithm; Approximation algorithm; Artificial intelligence; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02572179603381434,"gpt":0.2438775195296402,"spread":0.2181557234958259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003257952,0.0001719808,0.0001653084,0.0002337342,0.0003266283,0.0003559052,0.00045043,0.00004942121,0.000002858158],"category_scores_gemma":[0.00001121009,0.0001676252,0.00004774965,0.0003028538,0.00005349738,0.001253511,0.00002414208,0.00009314338,0.0000100557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005504927,"about_ca_system_score_gemma":0.00001819841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005349753,"about_ca_topic_score_gemma":0.000037662,"domain_scores_codex":[0.9986616,0.00004307375,0.0003151014,0.000501683,0.0002345163,0.0002440513],"domain_scores_gemma":[0.9987986,0.0001018533,0.0001238786,0.0008604085,0.00005872776,0.00005650604],"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":[0.00001291384,0.0003195914,0.00004943895,0.0005670656,0.00007484596,0.000005080026,0.000114559,0.002690375,0.00092593,0.06531347,0.001597979,0.9283288],"study_design_scores_gemma":[0.002109596,0.0002747613,0.0001615306,0.0002851017,0.0001027844,0.0001048039,0.000372088,0.8973469,0.001300105,0.00344912,0.09376732,0.0007258623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004014214,0.0001422532,0.9964413,0.0002278275,0.0008999204,0.0009294755,0.0004267578,0.0002805655,0.0002504644],"genre_scores_gemma":[0.139638,0.0000806913,0.8568093,0.00004423344,0.0002879324,0.0008354313,0.001154732,0.00003623059,0.001113385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9276029,"threshold_uncertainty_score":0.6835557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1875872827","doi":"10.1007/978-3-540-24627-5_7","title":"Skyline Cardinality for Relational Processing","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Cardinality (data modeling); Computer science; Online analytical processing; Tuple; Extension (predicate logic); Data mining; Theoretical computer science; Database; Mathematics; Discrete mathematics; Data warehouse; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03096591432089721,"gpt":0.2674929519471953,"spread":0.2365270376262981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000990411,0.0003697866,0.0003653405,0.0004887002,0.0003199993,0.0006441493,0.002489825,0.0001740674,0.00001148246],"category_scores_gemma":[0.00006740363,0.0003428007,0.0001304507,0.0004393552,0.0003675202,0.001217356,0.001089718,0.0003963101,0.00001841915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003079119,"about_ca_system_score_gemma":0.0006152728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009014041,"about_ca_topic_score_gemma":0.00001233074,"domain_scores_codex":[0.9968857,0.00001068473,0.0004171893,0.001349392,0.0008373492,0.0004996792],"domain_scores_gemma":[0.9983243,0.000174526,0.0002427455,0.0008958811,0.0002586668,0.0001038732],"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":[0.000003159159,0.00001818004,0.00001400572,0.00007369548,0.000008028291,0.0000192746,0.0001346913,0.01978937,0.00000890502,0.1888046,0.00002770207,0.7910984],"study_design_scores_gemma":[0.0003257581,0.00007711728,0.00009268715,0.0002729121,0.000009788178,0.00001209168,4.598045e-8,0.4848498,0.0001455725,0.5071308,0.006632118,0.0004513405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003759309,0.0002875864,0.9924081,0.001313496,0.001103422,0.0004836117,0.0000186942,0.0001478388,0.004233516],"genre_scores_gemma":[0.01457932,0.00001271075,0.9829345,0.0008998832,0.0007646158,0.00001715844,0.00004578768,0.00002426511,0.0007218109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.790647,"threshold_uncertainty_score":0.9999024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041121499","doi":"10.1198/016214508000000517","title":"Combining Registration and Fitting for Functional Models","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Computer science; Econometrics; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03196521524814722,"gpt":0.2525504152852148,"spread":0.2205852000370676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005283893,0.00004406555,0.0001158593,0.00003152079,0.0001731164,0.00006998187,0.0001727391,0.000009868454,6.6258e-7],"category_scores_gemma":[0.000505104,0.0000320143,0.00003588004,0.0001284684,0.00003925631,0.000482283,0.00005509544,0.0000822599,4.651433e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008002228,"about_ca_system_score_gemma":0.00003740751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009125267,"about_ca_topic_score_gemma":0.000001089483,"domain_scores_codex":[0.9992286,0.00005770032,0.0002251765,0.0000762269,0.0003162179,0.00009606931],"domain_scores_gemma":[0.9984734,0.0005023759,0.0007783519,0.00007256844,0.000142385,0.00003088703],"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":[0.0001179115,0.0002139873,0.03407361,0.00002793207,0.0003022953,0.00001657495,0.0009712116,0.003073898,0.0004553354,0.6393197,0.1261423,0.1952853],"study_design_scores_gemma":[0.0008885217,0.0003718004,0.2530319,0.00002290405,0.00005528922,0.0000554229,0.0001054899,0.6498563,0.00004850493,0.09336506,0.002048657,0.0001502111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01969114,0.000008612787,0.9773465,0.002528155,0.0001955134,0.00004977213,0.00001076558,0.000007416973,0.0001621333],"genre_scores_gemma":[0.8298379,0.00002183208,0.1692952,0.0004041245,0.0001403045,0.000001937891,0.000003548307,0.000003451487,0.0002917937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8101467,"threshold_uncertainty_score":0.1331489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130696419","doi":"10.1145/1189769.1189774","title":"Towards multidimensional subspace skyline analysis","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":117,"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":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Theoretical computer science; Space (punctuation); Object (grammar); Online analytical processing; Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01799995614887762,"gpt":0.2517425082751469,"spread":0.2337425521262693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000442132,0.000218095,0.000277959,0.000581536,0.0002489216,0.0002174444,0.001143695,0.00004820434,0.00006639199],"category_scores_gemma":[0.00001385601,0.0001959469,0.0001778493,0.001811904,0.0000345658,0.0009259198,0.0000625519,0.0001581216,0.0002534667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005408035,"about_ca_system_score_gemma":0.00003568397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002906037,"about_ca_topic_score_gemma":0.0002966779,"domain_scores_codex":[0.9979758,0.0001000853,0.0003542599,0.0006358626,0.000608272,0.000325754],"domain_scores_gemma":[0.9972777,0.0001026223,0.0000992791,0.002343736,0.00007541582,0.0001011834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000150196,0.005940149,0.001520793,0.0005038513,0.006224702,0.0009295337,0.0004159285,0.416884,0.005562076,0.2939969,0.0696414,0.1982305],"study_design_scores_gemma":[0.001350702,0.0001050237,0.002603453,0.00007437368,0.000650168,0.0000260555,0.0001121046,0.8680071,0.002409834,0.00019709,0.1236247,0.0008394453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001200779,0.0001298834,0.9949945,0.0008265504,0.0007773786,0.0002435752,0.0007570244,0.000305299,0.000764971],"genre_scores_gemma":[0.7547597,0.00005672727,0.236852,0.0001851726,0.0002512998,0.0001127214,0.001610635,0.00002807265,0.006143742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7581426,"threshold_uncertainty_score":0.7990481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028769163","doi":"10.1145/1044731.1044733","title":"Determining approximate shortest paths on weighted polyhedral surfaces","year":2005,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Data Management and Algorithms","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":"Carleton University","funders":"","keywords":"Discretization; Combinatorics; Face (sociological concept); Mathematics; Shortest path problem; Surface (topology); Euclidean geometry; Polyhedron; Computational geometry; Discrete mathematics; Algorithm; Geometry; Graph; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.02130323145929961,"gpt":0.2520038338114481,"spread":0.2307006023521485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004439159,0.00009198208,0.0001270387,0.00007778984,0.0001047051,0.0002321623,0.004236207,0.00002063312,0.00001079294],"category_scores_gemma":[0.0001162318,0.00005285782,0.00009481102,0.0001844286,0.0000217672,0.0008828015,0.001047022,0.0001703974,0.00002409198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002704311,"about_ca_system_score_gemma":0.00002218592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001059641,"about_ca_topic_score_gemma":0.000001464663,"domain_scores_codex":[0.9990523,0.00004560131,0.0002573789,0.0001120772,0.0003534268,0.0001792294],"domain_scores_gemma":[0.9986002,0.00006623324,0.0002741267,0.0009678056,0.00003860577,0.00005306943],"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":[0.00003468089,0.000399767,0.01094942,0.00001715825,0.0001671662,0.0001760756,0.001164781,0.001487994,0.002850664,0.006540814,0.04739069,0.9288208],"study_design_scores_gemma":[0.002884259,0.001106672,0.09487472,0.0005770454,0.0001377226,0.0006029592,0.0002157908,0.7346602,0.02731827,0.02594073,0.1106665,0.001015081],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9505292,0.000191753,0.01864709,0.02603155,0.001947276,0.0001368691,0.000004280348,0.00006228362,0.002449702],"genre_scores_gemma":[0.8871483,0.00002930897,0.1110038,0.0008633644,0.0004185106,5.500274e-7,3.295994e-7,0.000007507972,0.0005282615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9278057,"threshold_uncertainty_score":0.7871997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1481798977","doi":"10.1007/11424857_20","title":"A New and Efficient K-Medoid Algorithm for Spatial Clustering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Medoid; k-medoids; Cluster analysis; Computer science; Algorithm; Canopy clustering algorithm; Computation; CURE data clustering algorithm; Correlation clustering; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01332726406476602,"gpt":0.2370497392728519,"spread":0.2237224752080859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006386556,0.0004859373,0.0004385605,0.0006634208,0.0002466392,0.0009927596,0.002542776,0.0001798408,0.00001565815],"category_scores_gemma":[0.00002845256,0.0004550478,0.00009990099,0.000295788,0.000260932,0.0005189678,0.002517433,0.000365403,0.00001436469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000155158,"about_ca_system_score_gemma":0.000259454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005094153,"about_ca_topic_score_gemma":0.000109887,"domain_scores_codex":[0.9966031,0.00001153746,0.000416465,0.001582484,0.0007084379,0.0006779604],"domain_scores_gemma":[0.9982614,0.0002272809,0.0001992292,0.0009815919,0.00009719721,0.0002333241],"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":[0.000001949231,0.00001022051,0.0000010369,0.00001955277,0.000007551521,0.00001738566,0.0001810988,0.009804449,0.000007813091,0.002515119,0.00006211079,0.9873717],"study_design_scores_gemma":[0.0004835192,0.0001435877,0.00002058597,0.000166048,0.00001006883,0.00002930067,8.951086e-8,0.9722916,0.0001399361,0.01282417,0.01335852,0.0005325092],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002211133,0.0004083125,0.9951372,0.000808775,0.001930863,0.0006645876,0.00002257543,0.0001466457,0.0008788111],"genre_scores_gemma":[0.0005931628,0.00004153615,0.9959029,0.0008023038,0.001420941,0.00001090848,0.00001294262,0.00003029198,0.001184991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9868392,"threshold_uncertainty_score":0.9997901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154768509","doi":"10.14778/1453856.1453934","title":"Efficient network aware search in collaborative tagging sites","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"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; Popularity; Cluster analysis; Seekers; Context (archaeology); Upper and lower bounds; Heuristic; Space (punctuation); Information retrieval; Data mining; Machine learning; Artificial intelligence; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01881665465521546,"gpt":0.234770653360951,"spread":0.2159539987057356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004507724,0.000127004,0.0001617635,0.0001044174,0.000209384,0.00008293162,0.001223513,0.00002281735,0.000006480933],"category_scores_gemma":[0.00002787121,0.00009111875,0.00004750331,0.001356482,0.00008518548,0.0002350158,0.001141363,0.0001244018,0.000012019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007358609,"about_ca_system_score_gemma":0.00003586738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002436385,"about_ca_topic_score_gemma":0.000002508333,"domain_scores_codex":[0.9986108,0.00001107836,0.0002300781,0.0003123915,0.0004804363,0.0003552412],"domain_scores_gemma":[0.999478,0.00003446865,0.0001174334,0.0001795552,0.0001457147,0.00004486928],"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":[0.0001379444,0.002117882,0.3075927,0.0006833361,0.0003070988,0.00007817216,0.03836222,0.07795362,0.01675978,0.4020542,0.1266204,0.02733276],"study_design_scores_gemma":[0.003544638,0.0004587737,0.06893806,0.0007742585,0.00003844188,0.00003655937,0.003186815,0.8175385,0.08590493,0.0046848,0.0136972,0.001197056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747671,0.0003598276,0.00432007,0.004400143,0.0004886439,0.001326805,0.000009366853,0.000155966,0.01417211],"genre_scores_gemma":[0.9895294,0.00004859355,0.00972097,0.0001813168,0.00006970335,0.00003373873,0.000001108805,0.000007004335,0.0004082226],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7395849,"threshold_uncertainty_score":0.3715715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134161546","doi":"10.1007/s10707-005-4576-7","title":"Continuous Query Processing of Spatio-Temporal Data Streams in PLACE","year":2005,"lang":"en","type":"article","venue":"GeoInformatica","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Scalability; Spatial query; Data stream mining; Variety (cybernetics); Query language; Global Positioning System; Temporal database; Sliding window protocol; Semantics (computer science); Database; Distributed computing; Window (computing); Web search query; Web query classification; Data mining; Information retrieval; Operating system; Search engine; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01986281270201904,"gpt":0.2529512089406807,"spread":0.2330883962386616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004513852,0.00009384772,0.0001610318,0.0001272542,0.0000346394,0.0001630368,0.001527491,0.00002588277,0.00002632041],"category_scores_gemma":[0.00002945278,0.00008384218,0.00001507366,0.0002916933,0.00003131181,0.00475447,0.0008895231,0.00007689879,0.00008387247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000167651,"about_ca_system_score_gemma":0.0000632593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000771324,"about_ca_topic_score_gemma":0.0001629269,"domain_scores_codex":[0.9989293,0.00001317823,0.0004270783,0.000156401,0.0002486278,0.0002253917],"domain_scores_gemma":[0.9988804,0.00002677072,0.0001745968,0.0008497949,0.00002832389,0.00004006964],"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":[0.000005276937,0.00007203919,0.001298197,0.0001237867,0.000006756917,0.000004643025,0.001448011,0.0002207812,7.107738e-7,0.003186567,0.008885921,0.9847473],"study_design_scores_gemma":[0.0003847859,0.00002458659,0.0007021584,0.00007149982,0.000003572743,0.000003649289,0.0002283062,0.9380546,0.0000390476,0.0001449811,0.06021825,0.000124553],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07240374,0.0003420929,0.83838,0.003918424,0.0003448457,0.001032842,0.0001534804,0.0004567607,0.08296779],"genre_scores_gemma":[0.6926134,0.00001875248,0.3058066,0.0003264841,0.00007165219,0.000008017111,0.0004709648,0.000007322409,0.0006767943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9846228,"threshold_uncertainty_score":0.3446876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006806998","doi":"10.1016/s0306-4379(03)00038-3","title":"Extending object-oriented databases for fuzzy information modeling","year":2003,"lang":"en","type":"article","venue":"Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Fuzzy logic; Object (grammar); Database; Data mining; Measure (data warehouse); Database model; Data model (GIS); Database design; Theoretical computer science; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0335790971528764,"gpt":0.263758301456974,"spread":0.2301792043040976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008120558,0.0001243634,0.0001291714,0.0003277934,0.0002192514,0.0008189568,0.0003710365,0.00003063488,0.000002130737],"category_scores_gemma":[0.0001541685,0.0001162195,0.00004298429,0.0003852165,0.000007090305,0.02446281,0.00009421431,0.000052358,0.0002232347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005437505,"about_ca_system_score_gemma":0.00004210456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003744769,"about_ca_topic_score_gemma":6.616924e-7,"domain_scores_codex":[0.9986676,0.00003107971,0.000603824,0.0001037958,0.0003454776,0.000248217],"domain_scores_gemma":[0.9989797,0.00004189296,0.0002515236,0.0004447003,0.00022267,0.00005948216],"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":[0.000003536002,0.000008521586,0.00003516394,0.0001796598,0.00001838586,2.032277e-7,0.001007204,0.01818222,0.000003646406,0.9558955,0.00376899,0.02089691],"study_design_scores_gemma":[0.0003328686,0.00001335306,0.000004748631,0.00003197039,0.00000380231,0.00000525088,0.0007185534,0.6574239,0.00003486315,0.0001196223,0.3411925,0.0001184696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003322554,0.00003896721,0.9755082,0.00002967883,0.001597189,0.0006388617,0.0000653522,0.0002401749,0.02154936],"genre_scores_gemma":[0.8806694,0.00003602224,0.1159289,0.0006087103,0.0001599707,0.0004465043,0.001842923,0.00001183953,0.0002957573],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9557759,"threshold_uncertainty_score":0.9891815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145352743","doi":"10.1002/jcc.20484","title":"An algorithm for three‐dimensional Voronoi S‐network","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Alexander von Humboldt-Stiftung","keywords":"Voronoi diagram; Delaunay triangulation; SPHERES; Algorithm; Realization (probability); Centroidal Voronoi tessellation; Computer science; Bowyer–Watson algorithm; Computational geometry; Mathematics; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.008499045044182228,"gpt":0.2404819980159642,"spread":0.231982952971782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004104216,0.0001190543,0.0001679586,0.00003641671,0.0001136205,0.0001591717,0.000714277,0.00004333065,0.00002303293],"category_scores_gemma":[0.000007940484,0.0001103314,0.0001178871,0.0001494206,0.00003100046,0.0007411228,0.00007842429,0.0001135107,0.00000398212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003907659,"about_ca_system_score_gemma":0.0001157759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000255859,"about_ca_topic_score_gemma":6.399558e-7,"domain_scores_codex":[0.9987334,0.00001246683,0.0004145912,0.0001800794,0.0004621361,0.0001973147],"domain_scores_gemma":[0.9989218,0.0001274685,0.0003435204,0.0001658032,0.0003567336,0.00008468616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001494619,0.0002551624,0.0001590195,0.00002322108,0.00006682366,0.00003906386,0.000007427825,0.7948957,0.0003100274,0.003866729,0.03079047,0.1695714],"study_design_scores_gemma":[0.0006877973,0.00006958794,0.001942656,0.00002061118,0.00001444166,0.00009191257,0.000001937859,0.8024555,0.0004667201,0.1873064,0.006793465,0.0001489051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008978055,0.0001476597,0.9897296,0.0004048954,0.0003125215,0.0000607951,0.00001464619,0.00002886003,0.0003230035],"genre_scores_gemma":[0.0655343,8.351581e-7,0.9315661,0.0001686655,0.002375565,0.000003693006,0.0001168261,0.00001184903,0.0002222272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1834397,"threshold_uncertainty_score":0.4499184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076172709","doi":"10.1145/765568.765571","title":"The height of a random binary search tree","year":2003,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":100,"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":"Binary search tree; Combinatorics; Binary number; Random binary tree; Mathematics; Binary tree; Tree (set theory); Self-balancing binary search tree; Optimal binary search tree; Discrete mathematics; K-ary tree; Arithmetic; Tree structure","retraction":null,"screen_n_in":null,"score":{"opus":0.02206708586160027,"gpt":0.2553730957915877,"spread":0.2333060099299874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001478314,0.00004746895,0.0001008195,0.00004450654,0.0001241491,0.00009874679,0.004501902,0.00001164279,0.00000712571],"category_scores_gemma":[0.0004264396,0.0000203547,0.0001194968,0.0002579943,0.00004724506,0.0003242248,0.0008085978,0.000135176,0.000006126872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001104224,"about_ca_system_score_gemma":0.00004523672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001720146,"about_ca_topic_score_gemma":0.000001116862,"domain_scores_codex":[0.9990746,0.0001683022,0.0002154212,0.00005652305,0.0003646413,0.000120477],"domain_scores_gemma":[0.9984182,0.0002177744,0.0001828403,0.001079906,0.00007186519,0.00002940086],"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":[0.0003445711,0.000575363,0.004336374,0.00005822267,0.0007046391,0.0001873757,0.002089868,0.0006688822,0.005586187,0.13886,0.4725634,0.3740251],"study_design_scores_gemma":[0.01123443,0.001006423,0.03005316,0.0002885969,0.0001470185,0.0004886622,0.0006552438,0.01818152,0.03175936,0.1864914,0.7192405,0.0004536259],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5000078,0.0114885,0.2049857,0.2108533,0.01335265,0.001242321,0.00001023626,0.00006983639,0.05798969],"genre_scores_gemma":[0.9264168,0.000895759,0.06336858,0.0006312403,0.0003536248,0.000002075007,2.137212e-7,0.0000141077,0.00831763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.426409,"threshold_uncertainty_score":0.836573,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010342401","doi":"10.1080/13658810601079759","title":"A shortest path algorithm with novel heuristics for dynamic transportation networks","year":2007,"lang":"en","type":"article","venue":"International Journal of Geographical Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"MRF Geosystems (Canada)","funders":"","keywords":"Heuristics; Computer science; Shortest path problem; Path (computing); Process (computing); Yen's algorithm; Algorithm; Object (grammar); Mathematical optimization; Dijkstra's algorithm; K shortest path routing; Artificial intelligence; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.007295755120132437,"gpt":0.2433534698424764,"spread":0.236057714722344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001132692,0.0001312025,0.0001823535,0.0005622077,0.00006505796,0.0005285217,0.0008810156,0.00006847645,0.000001291578],"category_scores_gemma":[0.00002763062,0.0001023565,0.0001196985,0.0003835444,0.00003964318,0.002994156,0.00002565175,0.0001677312,0.000001646663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000482639,"about_ca_system_score_gemma":0.00003827648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000178221,"about_ca_topic_score_gemma":0.000008736007,"domain_scores_codex":[0.9978664,0.00001078008,0.0009652195,0.0001011712,0.0008531038,0.0002033177],"domain_scores_gemma":[0.9974645,0.0001347093,0.0007749897,0.0001459796,0.001366314,0.000113516],"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":[0.0005360306,0.0006340458,0.007637694,0.00009865034,0.001490186,0.0001438927,0.001248185,0.08311204,0.000041316,0.2241549,0.002523779,0.6783792],"study_design_scores_gemma":[0.00167535,0.0003362386,0.01432316,0.0001418626,0.00003263214,0.0001776413,0.0002417399,0.9446917,0.000006356968,0.0001934782,0.03797676,0.0002030524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001033639,0.00005104262,0.9962364,0.0002679429,0.001916517,0.000234178,0.0001079573,0.00003735425,0.0001149299],"genre_scores_gemma":[0.8882428,0.00005499391,0.1108124,0.0002641257,0.0003250289,0.00001025126,0.0002649839,0.000007756958,0.00001767752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8872091,"threshold_uncertainty_score":0.5096546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005048938","doi":"10.1145/1516360.1516459","title":"Interactive query refinement","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":99,"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; Query optimization; Information retrieval; Query language","retraction":null,"screen_n_in":null,"score":{"opus":0.009324530882337508,"gpt":0.2442648592033287,"spread":0.2349403283209912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007443153,0.00004791686,0.00004276696,0.00004658719,0.00002749492,0.0001314596,0.0004698603,0.000007209279,0.0000740078],"category_scores_gemma":[0.000004874655,0.00003765149,0.00001849133,0.0001227278,0.000003840445,0.0007216673,0.0001390679,0.00003306181,0.0002259766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001223862,"about_ca_system_score_gemma":0.000004580034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000913398,"about_ca_topic_score_gemma":0.000001843699,"domain_scores_codex":[0.9995552,0.000007825028,0.00006962896,0.0001605467,0.0001011085,0.0001056964],"domain_scores_gemma":[0.9996372,0.000008690227,0.00001869151,0.0002952942,0.00001374547,0.00002630991],"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":[9.982082e-7,0.00005088663,0.00001276702,5.988696e-7,0.000004961929,0.00001031111,0.00005849389,0.000001941848,0.00007099347,0.3480905,0.04738291,0.6043146],"study_design_scores_gemma":[0.0008340034,0.000543172,0.01846896,0.00002943279,0.000008675007,0.000007892687,0.0001318641,0.09581538,0.005298777,0.05847356,0.8197877,0.0006005774],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003040586,0.0000100605,0.7424025,0.006622258,0.0001925445,0.00005036411,3.447432e-7,0.0001724067,0.2502455],"genre_scores_gemma":[0.563673,0.00002690812,0.3836044,0.01602366,0.0001744124,0.000007429423,0.0000137849,0.000004460883,0.03647195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724048,"threshold_uncertainty_score":0.2904547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100235843","doi":"10.5555/1182635.1164146","title":"Relaxing join and selection queries","year":2006,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":95,"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":"Joins; Computer science; Traverse; Query optimization; Theoretical computer science; Relaxation (psychology); Join (topology); Lattice (music); Selection (genetic algorithm); Information retrieval; Data mining; Mathematics; Combinatorics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.008028305870935474,"gpt":0.1763056307184854,"spread":0.1682773248475499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009123666,0.00002806875,0.00003436602,0.00008066445,0.0001167176,0.00002461565,0.0001123149,0.00001575673,0.000007620805],"category_scores_gemma":[0.000006414773,0.00003438256,0.00001110586,0.0001485797,0.00003614108,0.0005893648,0.00007965569,0.00002802055,0.000002270064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002432455,"about_ca_system_score_gemma":0.00002017846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001296901,"about_ca_topic_score_gemma":0.00004349259,"domain_scores_codex":[0.9996643,0.000007859306,0.00003561772,0.00009568469,0.0001526766,0.00004384522],"domain_scores_gemma":[0.9998308,0.00001535202,0.00003918761,0.00002756111,0.00007761714,0.000009437704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000004825794,0.00004078533,0.005019847,0.00001445846,0.00001200862,0.000006532012,0.0001570729,0.0001645971,0.0008094828,0.9677135,0.01263304,0.0134239],"study_design_scores_gemma":[0.001631025,0.0001361912,0.4583706,0.0000732574,0.00002638253,0.00003037355,0.0005675244,0.1775815,0.001697956,0.1203758,0.2389967,0.0005126712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1677205,0.00008997609,0.7456872,0.003312232,0.000121704,0.0001225918,0.00001752293,0.0001955905,0.08273268],"genre_scores_gemma":[0.9268519,0.000006852325,0.07117795,0.0000244156,0.00002816197,2.164057e-8,0.00001627881,0.000001333657,0.001893075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8473377,"threshold_uncertainty_score":0.140208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162148987","doi":"","title":"Clusterability: A Theoretical Study","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":94,"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":"Cluster analysis; Generality; Computer science; Pairwise comparison; Set (abstract data type); Property (philosophy); Data mining; Theoretical computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.00920970011625449,"gpt":0.2564770682758922,"spread":0.2472673681596377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002887145,0.00005430112,0.00006150042,0.00003293614,0.00003944238,0.0002103299,0.0007069951,0.000008713888,0.00009171462],"category_scores_gemma":[0.00001369501,0.00003882143,0.00001954342,0.000170507,0.00002004255,0.0004108245,0.0002176414,0.00003930908,0.0001209558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005714468,"about_ca_system_score_gemma":0.000004348112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001718255,"about_ca_topic_score_gemma":8.532194e-7,"domain_scores_codex":[0.9993573,0.00003459194,0.00008857797,0.0002316717,0.0001588538,0.0001290443],"domain_scores_gemma":[0.9993793,0.00002036629,0.000009186921,0.0005388156,0.00001328127,0.00003906351],"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":[8.877527e-7,0.0002590455,0.0002517033,3.235739e-7,0.000002617627,0.000008987085,0.0001275681,4.939085e-7,0.00000226502,0.8442063,0.001049453,0.1540904],"study_design_scores_gemma":[0.001379631,0.001914261,0.06152329,0.000004676641,0.00001495508,0.00000629249,0.0003849275,0.3069928,0.00009563561,0.6178994,0.009316547,0.0004676284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01149149,0.00000353971,0.8928131,0.004831449,0.0001148775,0.0002346719,2.14753e-7,0.0002666713,0.09024399],"genre_scores_gemma":[0.9761204,4.136777e-7,0.02189187,0.001314742,0.00002731553,0.000002223728,5.300022e-7,9.853896e-7,0.0006415224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646289,"threshold_uncertainty_score":0.2028216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020493833","doi":"10.1145/1989323.1989390","title":"BE-tree","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":93,"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; Tree (set theory); Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.06173774393611898,"gpt":0.2255523000344625,"spread":0.1638145560983435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005848269,0.00003080614,0.00002590645,0.00002721721,0.00002016991,0.00004599031,0.0006458277,0.000006563796,0.0002630822],"category_scores_gemma":[0.000002060875,0.00002383699,0.00001242863,0.00009533997,0.000007532848,0.0005333499,0.000288393,0.00001577359,0.0004766418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000178213,"about_ca_system_score_gemma":0.000002665495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002865104,"about_ca_topic_score_gemma":0.000007973335,"domain_scores_codex":[0.9996898,0.000003995966,0.00003996703,0.0001127903,0.00006685532,0.00008663256],"domain_scores_gemma":[0.9996457,0.000003290454,0.000008004569,0.000311846,0.000006912825,0.00002430657],"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":[1.981663e-7,0.00002107505,0.0002348852,8.91778e-7,0.00000374424,0.000008756841,0.0001189963,2.268482e-8,0.000008270868,0.7875208,0.04103621,0.1710462],"study_design_scores_gemma":[0.0005546322,0.0001644178,0.04014451,0.000006124927,0.00000868158,0.000006417101,0.00009073158,0.04752416,0.007423393,0.07293081,0.830592,0.0005541428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.0001116142,0.000003250144,0.4969133,0.0002500297,0.0001134536,0.00001731121,1.670614e-7,0.0001131579,0.5024777],"genre_scores_gemma":[0.1084447,0.000008412688,0.8392987,0.002641769,0.00005731411,0.000005457841,0.00000298114,0.000004517378,0.04953611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7895558,"threshold_uncertainty_score":0.6126425,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001088180","doi":"10.5555/338219.338659","title":"Computing contour trees in all dimensions","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":90,"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":"Simple (philosophy); Computer science; Contour line; Algorithm; Artificial intelligence; Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02725043140270391,"gpt":0.2643550684760672,"spread":0.2371046370733632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001376232,0.00005954881,0.00007245342,0.00005604124,0.00003407008,0.0001139981,0.0004945314,0.00001303776,0.0002137135],"category_scores_gemma":[0.00000339826,0.00004997453,0.00001873672,0.0001894407,0.000009967276,0.0004209614,0.0001664424,0.00004499267,0.0003024696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000824174,"about_ca_system_score_gemma":0.000004270727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001600268,"about_ca_topic_score_gemma":0.0001308686,"domain_scores_codex":[0.9993854,0.00001940581,0.0001145654,0.000199778,0.00009914985,0.0001817202],"domain_scores_gemma":[0.999644,0.00003155571,0.00001245511,0.0002714116,0.000005106138,0.00003551516],"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":[0.000001666524,0.0001211863,0.001623484,0.000001976323,0.0000124377,0.00007150655,0.0004008122,0.0007739856,0.00008414172,0.08970599,0.01937151,0.8878313],"study_design_scores_gemma":[0.0005933759,0.00003533677,0.02384985,0.00001642508,0.000002493536,0.000003312316,0.0000389602,0.8527355,0.00009526572,0.002068003,0.1203479,0.0002135834],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2224335,0.0001478598,0.378153,0.006433509,0.0004629271,0.0003740953,0.000002867947,0.0008202019,0.3911721],"genre_scores_gemma":[0.9248204,0.00002232252,0.0639893,0.00170735,0.00003937667,0.000001475823,0.000005480886,0.000003737191,0.009410578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8876177,"threshold_uncertainty_score":0.3887735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}