{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":40,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":40,"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":"84a422687fe3","filters":{"venue":"ACM SIGKDD Explorations Newsletter"}},"results":[{"id":"W2011376672","doi":"10.1145/1007730.1007737","title":"Class imbalances versus small disjuncts","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":681,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Focus (optics); Classifier (UML); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.068174256664078,"gpt":0.279847161916715,"spread":0.211672905252637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002052662,0.0002469015,0.0001971132,0.0002012451,0.000272908,0.0004478452,0.002610336,0.0001151364,0.00002557672],"category_scores_gemma":[0.0003292368,0.0002341337,0.00008341561,0.0007420649,0.000113523,0.002011453,0.0005548025,0.0002468015,0.001054363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001650662,"about_ca_system_score_gemma":0.0001370464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110094,"about_ca_topic_score_gemma":0.00007739377,"domain_scores_codex":[0.9981174,0.00006877974,0.0003845946,0.0006315607,0.0003687071,0.000428922],"domain_scores_gemma":[0.9968916,0.0001860733,0.0001557384,0.002498135,0.0001435885,0.0001248217],"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":[0.00007889464,0.0005443797,0.0008210528,0.00003678228,0.0001209024,0.00008160621,0.003674977,0.0008715389,0.0477502,0.6932518,0.2174866,0.03528124],"study_design_scores_gemma":[0.006100406,0.0007120852,0.00541481,0.0001284391,0.00006049424,0.00004207194,0.0004895467,0.002268243,0.2297273,0.1501286,0.6026062,0.002321754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008144988,0.00005157474,0.9044271,0.08279607,0.000939207,0.0003462788,0.00001435182,0.001199726,0.00208074],"genre_scores_gemma":[0.5063142,0.00007157026,0.4810038,0.01114897,0.0004498782,0.0004912788,0.0001699971,0.00003931447,0.0003109741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5431231,"threshold_uncertainty_score":0.9997234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040010062","doi":"10.1145/1007730.1007736","title":"Learning from imbalanced data sets with boosting and data generation","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":606,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Machine learning; Computer science; Artificial intelligence; Benchmarking; Classifier (UML); Training set; Gradient boosting; Ensemble learning; Data mining; Random forest","retraction":null,"screen_n_in":null,"score":{"opus":0.145876779440151,"gpt":0.3158766600273255,"spread":0.1699998805871745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003222386,0.0001980615,0.0001673559,0.0001056951,0.0003836424,0.0006368018,0.003432518,0.00007286271,0.000008761832],"category_scores_gemma":[0.0004966659,0.0001807002,0.000008969001,0.0003690996,0.00007639533,0.006221595,0.002521853,0.000273184,0.00006503921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000469216,"about_ca_system_score_gemma":0.0001044384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001276227,"about_ca_topic_score_gemma":0.0001409449,"domain_scores_codex":[0.9978958,0.00009588418,0.0003138723,0.001135965,0.0003055945,0.000252875],"domain_scores_gemma":[0.9935837,0.0001469891,0.0001909034,0.005908929,0.00009191391,0.0000775059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004995339,0.0004140445,0.01311982,0.00004740396,0.0002928872,0.0001422116,0.009118505,0.006061779,0.5167028,0.01936595,0.2208476,0.2138371],"study_design_scores_gemma":[0.00466569,0.0005391771,0.01449964,0.000338661,0.0001584736,0.0001302773,0.0007180895,0.7545464,0.08538315,0.01743417,0.1187609,0.002825395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02282449,0.00006450046,0.9509304,0.02507789,0.0000963905,0.0002634567,0.0001226905,0.0005454391,0.00007473868],"genre_scores_gemma":[0.3785406,0.0000515419,0.6110542,0.002644182,0.0002326781,0.00004877903,0.007379863,0.00002236726,0.00002580333],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7484846,"threshold_uncertainty_score":0.7368741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997102766","doi":"10.1145/1882471.1882478","title":"A brief survey on sequence classification","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":552,"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; Sequence (biology); Feature selection; Artificial intelligence; Feature vector; Task (project management); Feature (linguistics); Machine learning; Pattern recognition (psychology); One-class classification; Support vector machine; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1153428195483115,"gpt":0.3164656778829131,"spread":0.2011228583346016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000309192,0.0001670044,0.0001248814,0.0001311076,0.0003014723,0.0003905984,0.001622319,0.0001018411,0.00005738358],"category_scores_gemma":[0.0004714458,0.0001459261,0.00004387678,0.0004782535,0.00006592059,0.001579198,0.0003574228,0.0003864329,0.0006626029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001728727,"about_ca_system_score_gemma":0.00007111704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001528657,"about_ca_topic_score_gemma":0.0001443024,"domain_scores_codex":[0.9984847,0.0001274977,0.0002609176,0.0005394504,0.0003320378,0.0002554012],"domain_scores_gemma":[0.9969554,0.0003475122,0.0001081661,0.002364704,0.0001134299,0.0001107791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002166147,0.000342248,0.004535983,0.000006223268,0.0000227202,0.00002629025,0.0009542956,0.0001100088,0.4519017,0.08969273,0.3611196,0.09126659],"study_design_scores_gemma":[0.001638819,0.0004179095,0.4225212,0.00007307317,0.00001995684,0.00004848029,0.00005968312,0.1549614,0.05240729,0.0209223,0.3450294,0.001900528],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09228618,0.000009077189,0.8682058,0.03535791,0.001794282,0.0003715891,0.00007363215,0.0004644681,0.001437004],"genre_scores_gemma":[0.8942145,0.000008327051,0.09627791,0.008443297,0.0003719966,0.00009980443,0.0003324892,0.00001980526,0.0002319422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8019282,"threshold_uncertainty_score":0.8516641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977843657","doi":"10.1145/1540276.1540279","title":"A brief survey on anonymization techniques for privacy preserving publishing of social network data","year":2008,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":419,"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":"Data publishing; Computer science; Publishing; Social network (sociolinguistics); Information privacy; Data science; k-anonymity; Data anonymization; Graph; Cluster analysis; Internet privacy; Privacy protection; World Wide Web; Data mining; Social media; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1723603973409118,"gpt":0.3270708739991915,"spread":0.1547104766582797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001252914,0.000244349,0.0003201296,0.0002659801,0.0006265719,0.0005322439,0.04230956,0.0002417302,0.00001129602],"category_scores_gemma":[0.06553122,0.0002531084,0.00006436601,0.001347957,0.0001505883,0.00844533,0.06816664,0.0003458058,0.000006897821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005591632,"about_ca_system_score_gemma":0.0001503939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594054,"about_ca_topic_score_gemma":0.00008246764,"domain_scores_codex":[0.9972332,0.0002720589,0.0006140196,0.0008864873,0.0005006174,0.00049366],"domain_scores_gemma":[0.9828647,0.00131476,0.0004082392,0.0150492,0.0003119466,0.00005119694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001747726,0.00007464342,0.00219155,0.00001530638,0.00002869883,0.000002797473,0.0002767125,0.00005511204,0.0006282325,0.002215168,0.9900916,0.004402713],"study_design_scores_gemma":[0.002805154,0.0007730193,0.06549464,0.000372461,0.00008122946,0.00003425672,0.00009752735,0.301464,0.04426176,0.3320733,0.2498801,0.002662564],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003912271,0.00003127927,0.8810375,0.112542,0.0002644544,0.0007330213,0.0002884924,0.0009386131,0.0002523132],"genre_scores_gemma":[0.1628633,0.00004144316,0.8304577,0.003224985,0.0005591472,0.0002291416,0.002523898,0.00004817267,0.00005217192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7402114,"threshold_uncertainty_score":0.9999921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1984606279","doi":"10.1145/380995.381002","title":"Mining frequent patterns by pattern-growth","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":275,"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":"Citation; Computer science; Data science; Library science","retraction":null,"screen_n_in":null,"score":{"opus":0.02117662248008691,"gpt":0.2413436073438028,"spread":0.2201669848637159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001337912,0.000235291,0.0001748075,0.00009736033,0.0003345378,0.0005016177,0.001836581,0.00007490819,0.0006879782],"category_scores_gemma":[0.0000368924,0.0002305778,0.00007552326,0.0004317098,0.00004315566,0.001498268,0.0002511895,0.0001751079,0.001428403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004303619,"about_ca_system_score_gemma":0.00003181505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000163711,"about_ca_topic_score_gemma":0.00002027323,"domain_scores_codex":[0.9981863,0.00006391955,0.0003811106,0.0006405247,0.0003131201,0.0004150621],"domain_scores_gemma":[0.9978808,0.0001293277,0.00008151095,0.001689697,0.00006922123,0.0001495148],"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":[0.000001098402,0.0001653768,0.001909585,0.000007263568,0.00003179656,0.00001531345,0.001698599,0.00002624251,0.001900048,0.0009622696,0.6575571,0.3357253],"study_design_scores_gemma":[0.001724706,0.0002854518,0.005215254,0.0001398676,0.00006732356,0.00008239965,0.0004449874,0.04450148,0.01916495,0.004605372,0.9215177,0.002250486],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07965271,0.00005708705,0.8564917,0.0613567,0.0002068905,0.0002710413,0.0001347595,0.000449278,0.001379858],"genre_scores_gemma":[0.6903612,0.0002021086,0.2510507,0.05034975,0.0009176899,0.001192986,0.001130294,0.0001006725,0.004694556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6107085,"threshold_uncertainty_score":0.9993491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101549186","doi":"10.1145/2594473.2594476","title":"Ensembles for unsupervised outlier detection","year":2014,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Anomaly detection; Outlier; Cluster analysis; Artificial intelligence; Focus (optics); Machine learning; Unsupervised learning; Core (optical fiber); Ensemble learning; Data mining; Pattern recognition (psychology); Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.02540533101613996,"gpt":0.2520752218889637,"spread":0.2266698908728237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002037994,0.0001521059,0.0001334638,0.0001559724,0.0004438764,0.0002128534,0.0007566311,0.00009119418,0.00001824386],"category_scores_gemma":[0.0001409847,0.0001477945,0.0001117287,0.000391161,0.00003353989,0.0007242203,0.0001409663,0.0001021698,0.0001875552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003474229,"about_ca_system_score_gemma":0.0000180736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195514,"about_ca_topic_score_gemma":0.0000237652,"domain_scores_codex":[0.9988793,0.00005357308,0.0002717203,0.0004144664,0.0001409117,0.000240003],"domain_scores_gemma":[0.9982935,0.0002054691,0.00008592643,0.001194462,0.0001464683,0.00007421961],"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":[0.00001991529,0.000216295,0.0001805154,0.00003215574,0.0000530397,8.287622e-7,0.00127778,0.0003665082,0.2771104,0.1591019,0.07778127,0.4838594],"study_design_scores_gemma":[0.0005373735,0.0002329572,0.0003771846,0.000009045884,0.00002084021,0.000008951378,0.0000529794,0.0540096,0.2320339,0.0600204,0.6522449,0.0004518847],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006314207,0.000008645937,0.9750851,0.01672688,0.0001876455,0.0004738663,0.000003235797,0.0006554846,0.0005449311],"genre_scores_gemma":[0.786473,0.000006516992,0.2056405,0.005538486,0.0003625349,0.001402254,0.00001536998,0.00002361638,0.0005376377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7801588,"threshold_uncertainty_score":0.6026887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2044306058","doi":"10.1145/568574.568580","title":"Constrained frequent pattern mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","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":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Sequential Pattern Mining; Constraint (computer-aided design); K-optimal pattern discovery; Context (archaeology); Process (computing); Association rule learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06108663403363127,"gpt":0.2512890157389533,"spread":0.190202381705322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001138303,0.0001748334,0.0001434762,0.0001262098,0.0002943637,0.0003668533,0.001360178,0.00005798034,0.0003432265],"category_scores_gemma":[0.00009434052,0.0001708867,0.00006384825,0.0004552482,0.00007311427,0.00113206,0.0003261844,0.000139108,0.001443906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003089265,"about_ca_system_score_gemma":0.00001664689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002311195,"about_ca_topic_score_gemma":0.00001082536,"domain_scores_codex":[0.9986045,0.0000450845,0.0003184624,0.0004731903,0.0002360303,0.0003227288],"domain_scores_gemma":[0.9979687,0.0001610654,0.00009386214,0.00158909,0.0000705095,0.0001167965],"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":[3.931375e-7,0.0001954708,0.0006060497,0.00000670203,0.00004190476,0.00003819834,0.004244871,0.0000655331,0.003211679,0.00869386,0.4552676,0.5276277],"study_design_scores_gemma":[0.001695735,0.0002245147,0.001534649,0.00009238216,0.00005395117,0.0001511498,0.000771306,0.4653555,0.004850512,0.00536006,0.5182254,0.001684847],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007530511,0.00006043923,0.9163356,0.07278986,0.0002771979,0.0002006276,0.00002885289,0.0003774131,0.002399456],"genre_scores_gemma":[0.4898718,0.00003339096,0.4882841,0.0195328,0.0005169626,0.0004371201,0.0001027082,0.00003444347,0.001186702],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5259429,"threshold_uncertainty_score":0.9993336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069116068","doi":"10.1145/507515.507523","title":"KDD Cup 2001 report","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Imperial Bank of Commerce (Canada)","funders":"National Science Foundation","keywords":"Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03648866402031892,"gpt":0.2723488489952492,"spread":0.2358601849749303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001616701,0.0001813945,0.0001263133,0.00006850316,0.0001618763,0.00006956306,0.0003778904,0.0001424874,0.0008425448],"category_scores_gemma":[0.0007396833,0.0001742422,0.00009063919,0.0001494745,0.00006699174,0.00002338724,0.0002032578,0.0001780216,0.0009980784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001452035,"about_ca_system_score_gemma":0.00001779696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009239325,"about_ca_topic_score_gemma":0.00001354434,"domain_scores_codex":[0.9988,0.00005226003,0.0003749913,0.0002807268,0.000185376,0.0003065941],"domain_scores_gemma":[0.9983925,0.00002402311,0.0001412375,0.001262724,0.00008701246,0.00009253453],"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":[0.000005581297,0.00005974116,0.004385849,0.00000917409,0.00003892383,0.0000332745,0.0002333277,0.0003191782,0.03570089,0.00006012698,0.9573221,0.001831859],"study_design_scores_gemma":[0.000342795,0.00009709546,0.0007456791,0.000007566597,0.00002035222,0.000221526,0.00006188864,0.001610284,0.01148792,0.0001074671,0.984975,0.0003224004],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7355424,0.0005940037,0.07506728,0.08697352,0.001600189,0.001088335,0.00004132806,0.0003766677,0.09871628],"genre_scores_gemma":[0.8407871,0.0002831094,0.07345465,0.03020592,0.002573693,0.0002461803,0.001464755,0.0001303525,0.05085421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1052447,"threshold_uncertainty_score":0.9997798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2945319864","doi":"10.1145/3331651.3331653","title":"Urban Human Mobility","year":2019,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Multidisciplinary approach; Data science; Context (archaeology); Mobility model; Perspective (graphical); Field (mathematics); Global Positioning System; Urban computing; Human dynamics; Human–computer interaction; Artificial intelligence; Telecommunications; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.0367557887767918,"gpt":0.3235828484170946,"spread":0.2868270596403028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000755789,0.0001328216,0.0001863057,0.0001349575,0.0009389145,0.000177043,0.0005797626,0.0001153629,0.006482612],"category_scores_gemma":[0.0003641611,0.0001370425,0.0001490339,0.0005422241,0.0002499291,0.0006297766,0.00006828739,0.0001923431,0.003427998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000147623,"about_ca_system_score_gemma":0.0001389289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003406378,"about_ca_topic_score_gemma":0.008887506,"domain_scores_codex":[0.9982098,0.0003483635,0.000322301,0.0003983428,0.000399513,0.0003216358],"domain_scores_gemma":[0.9982471,0.0002633596,0.00008716308,0.001108595,0.0001708903,0.0001228999],"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":[0.00002379759,0.001114691,0.2847053,0.00006205781,0.0002091369,0.000006407106,0.0949783,0.0008138325,0.01459353,0.1441785,0.4529069,0.006407578],"study_design_scores_gemma":[0.0005513287,0.00008723201,0.0157579,0.00002321368,0.00008721892,2.091609e-7,0.01112741,0.0001943996,0.0008783243,0.01440172,0.9562712,0.0006197932],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9322181,0.00003819474,0.001855172,0.03522222,0.0002957495,0.0007142736,0.000009557358,0.0002681871,0.02937852],"genre_scores_gemma":[0.9841303,0.000004961251,0.0002128028,0.003686559,0.0005213185,0.0001134349,0.00008086752,0.00001352906,0.01123623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5033644,"threshold_uncertainty_score":0.997348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160036998","doi":"10.1145/1233321.1233324","title":"Utility-based anonymization for privacy preservation with less information loss","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":78,"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":"Chinese University of Hong Kong; National Natural Science Foundation of China","keywords":"Computer science; Data anonymization; Microdata (statistics); Categorical variable; Data mining; Identifier; Information loss; Heuristic; Set (abstract data type); Data quality; Information privacy; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04348191414472581,"gpt":0.2574041941641516,"spread":0.2139222800194258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.000285429,0.0002380252,0.0001788607,0.0003404341,0.0003498292,0.0005911413,0.01014754,0.0001528042,0.00001092357],"category_scores_gemma":[0.00507517,0.0002182925,0.00005420535,0.0009909652,0.0001039717,0.009924433,0.005933374,0.0001685765,0.00004259977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007718174,"about_ca_system_score_gemma":0.0001462626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007058292,"about_ca_topic_score_gemma":0.00006767079,"domain_scores_codex":[0.9981841,0.00006765687,0.0005025461,0.0004445557,0.000425443,0.0003757299],"domain_scores_gemma":[0.9917091,0.000319205,0.0002885451,0.007208849,0.0004338577,0.00004049365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008173741,0.000220117,0.01680055,0.0001205185,0.0000318828,0.000003986421,0.0002729395,0.004644601,0.001047443,0.02045552,0.9409957,0.01532503],"study_design_scores_gemma":[0.001932351,0.0001765167,0.006290177,0.00005882166,0.00002683932,0.00000425732,0.00004666052,0.6446371,0.02282024,0.2002786,0.1230975,0.000630921],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01698777,0.000009203228,0.8351662,0.1457968,0.0001362703,0.0008398555,0.00004322151,0.0008591102,0.0001616273],"genre_scores_gemma":[0.3270649,0.000002279433,0.668196,0.002693144,0.0001099472,0.0005565311,0.001320923,0.00001928932,0.00003701146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8178982,"threshold_uncertainty_score":0.995208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983506100","doi":"10.1145/568574.568581","title":"Exploiting succinct constraints using FP-trees","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":76,"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; Pruning; Focus (optics); Succinctness; Set (abstract data type); Constraint (computer-aided design); Tree (set theory); Data mining; Search tree; Theoretical computer science; Algorithm; Search algorithm; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1028758920195478,"gpt":0.27695920445099,"spread":0.1740833124314422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001622011,0.0002107489,0.0001793139,0.0001721231,0.0005220603,0.0005072649,0.001364399,0.00006757799,0.0003183651],"category_scores_gemma":[0.0001679623,0.0002119119,0.00007756783,0.000653903,0.0001254407,0.002028766,0.000453727,0.0001911681,0.0008853036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004921568,"about_ca_system_score_gemma":0.00002651149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003029323,"about_ca_topic_score_gemma":0.00001164897,"domain_scores_codex":[0.9983338,0.00006214681,0.0003820605,0.0005448626,0.0002730034,0.0004041172],"domain_scores_gemma":[0.9978729,0.0002036635,0.0001311268,0.001567461,0.00009758143,0.0001272803],"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":[0.000002548039,0.0006549568,0.002313134,0.00002598022,0.0001555339,0.0001347888,0.01042992,0.001513744,0.05311049,0.0605361,0.284113,0.5870098],"study_design_scores_gemma":[0.001302465,0.0001173687,0.00107487,0.0001351538,0.00006768561,0.0002432443,0.001198638,0.8644307,0.01012638,0.00726872,0.1123828,0.00165192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03246481,0.00007545909,0.9444664,0.02026837,0.000286302,0.0002432002,0.00002710666,0.0004313502,0.001737037],"genre_scores_gemma":[0.4756786,0.00002079952,0.5189343,0.004430177,0.0004357209,0.00012621,0.00003822991,0.00002941601,0.0003064811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8629169,"threshold_uncertainty_score":0.9998927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972132022","doi":"10.1145/1046456.1046468","title":"Subspace clustering for high dimensional categorical data","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Categorical variable; Correlation clustering; CURE data clustering algorithm; Data mining; Subspace topology; Canopy clustering algorithm; Data stream clustering; Focus (optics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1123055424811128,"gpt":0.3448912619355348,"spread":0.232585719454422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002888907,0.0002237184,0.0002080637,0.0001738008,0.0004106516,0.0003026644,0.003262907,0.00008812359,0.00001300624],"category_scores_gemma":[0.0004711494,0.0002156771,0.00005059941,0.0005390499,0.0000772248,0.002463814,0.003044442,0.0002583137,0.0002306217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001766332,"about_ca_system_score_gemma":0.0001602932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008112521,"about_ca_topic_score_gemma":0.00007934668,"domain_scores_codex":[0.9976661,0.00005096177,0.0003247646,0.0008815498,0.0004971441,0.000579497],"domain_scores_gemma":[0.9959775,0.0003470546,0.00007833023,0.003250398,0.0001798864,0.000166896],"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":[0.0001931697,0.00113489,0.0001282362,0.0001860862,0.0003356656,0.0004963474,0.004846421,0.5114476,0.06080486,0.1426964,0.1548861,0.1228442],"study_design_scores_gemma":[0.006744563,0.0006695507,0.0006657018,0.0000906792,0.00004962123,0.0002637311,0.0001640765,0.7211635,0.01955274,0.1915259,0.05702209,0.002087855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002734174,0.0000377446,0.9214948,0.07449408,0.0005146203,0.0004209795,0.00002487672,0.0002542343,0.00002443746],"genre_scores_gemma":[0.2055515,0.000007963334,0.7900522,0.003010029,0.0005358455,0.0002541639,0.000236514,0.00004121936,0.0003105326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2097159,"threshold_uncertainty_score":0.8795058,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3165211483","doi":"10.1145/3468507.3468511","title":"On the Applicability of Machine Learning Fairness Notions","year":2021,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Subjectivity; Set (abstract data type); Computer science; Artificial intelligence; Machine learning; Fairness measure; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.08874008202605167,"gpt":0.3517598061059928,"spread":0.2630197240799412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008833834,0.00008786815,0.0001339955,0.00003427558,0.001290887,0.000146,0.000349783,0.0001107878,0.00071201],"category_scores_gemma":[0.007598529,0.00006976276,0.000103876,0.0004801631,0.0003835852,0.0003079131,0.00009804974,0.0004431492,0.00009998494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004842909,"about_ca_system_score_gemma":0.0002037127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006765447,"about_ca_topic_score_gemma":0.002637025,"domain_scores_codex":[0.998441,0.0005586323,0.0002142887,0.0001888182,0.0003874413,0.0002097984],"domain_scores_gemma":[0.9970053,0.001919084,0.00009096908,0.0004975414,0.000418792,0.00006829362],"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":[0.000008483336,0.0002577631,0.002038853,0.00001010824,0.00004744386,0.000004412921,0.04671756,0.0004465157,0.004283778,0.9249121,0.01955873,0.001714279],"study_design_scores_gemma":[0.0005400453,0.0001329377,0.003265596,0.00006611514,0.00008160824,9.582085e-7,0.04374628,0.0002453691,0.009189707,0.5769877,0.3651673,0.0005764677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2567955,0.00005106695,0.004071072,0.6982925,0.0002642717,0.0003407085,0.00002150168,0.00009424293,0.04006916],"genre_scores_gemma":[0.9909679,0.00005428437,0.0003993142,0.007053758,0.0002240301,0.00005031566,0.00002258578,0.00001064908,0.001217138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7341724,"threshold_uncertainty_score":0.9928589,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993415883","doi":"10.1145/1809400.1809407","title":"FpVAT","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Process (computing); Knowledge extraction; Representation (politics); Data mining; Simple (philosophy); Visualization; Information retrieval; Visual analytics; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03376557419937707,"gpt":0.2960755426787169,"spread":0.2623099684793399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001290463,0.0001112552,0.00009055741,0.000131184,0.0001761132,0.0003949959,0.001330981,0.00005821497,0.0002497289],"category_scores_gemma":[0.0002528138,0.0001025777,0.00004687771,0.0004979389,0.00004457647,0.001493659,0.0003539959,0.000192637,0.001691322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000759566,"about_ca_system_score_gemma":0.00004111803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005639026,"about_ca_topic_score_gemma":0.0000359033,"domain_scores_codex":[0.9990789,0.00002889149,0.0002042153,0.0002830449,0.0002083378,0.0001966588],"domain_scores_gemma":[0.9981973,0.00007614224,0.00005660593,0.00148216,0.00009410874,0.00009364242],"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":[9.040673e-7,0.0000997407,0.0008720043,0.00000408263,0.00001583574,0.00001236544,0.0007884739,0.00003808741,0.03705276,0.3988489,0.5530311,0.009235666],"study_design_scores_gemma":[0.0003062673,0.00002716609,0.0005831405,0.000004921413,0.000008884928,0.00001350413,0.00004168684,0.01972173,0.01044563,0.0141991,0.9543052,0.0003427349],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008213704,0.00000556226,0.9294605,0.05797812,0.0009444174,0.0001073558,0.000006484903,0.0003552847,0.002928566],"genre_scores_gemma":[0.6315231,0.0000184716,0.2953888,0.06708454,0.001089169,0.00008303439,0.0002087067,0.00004150371,0.004562652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6340716,"threshold_uncertainty_score":0.999086,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968064480","doi":"10.1145/2031331.2031336","title":"Trajectory anonymity in publishing personal mobility data","year":2011,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":68,"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; Data publishing; Identifier; Anonymity; Global Positioning System; TRACE (psycholinguistics); Location-based service; Computer security; Object (grammar); World Wide Web; GSM; Mobile device; Location data; Personally identifiable information; k-anonymity; Internet privacy; Data science; Publishing; Computer network; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.2671506687550872,"gpt":0.3419145920846799,"spread":0.07476392332959275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002478458,0.0001369464,0.0001875562,0.0002231005,0.0006256219,0.0003379635,0.001477296,0.0001509059,0.003375072],"category_scores_gemma":[0.002935007,0.00014523,0.00007853329,0.0008327702,0.0003825201,0.004363537,0.0002149604,0.0003698817,0.0001816376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001820772,"about_ca_system_score_gemma":0.0004000894,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02843385,"about_ca_topic_score_gemma":0.1776752,"domain_scores_codex":[0.9975594,0.0006625482,0.0003899609,0.0005807514,0.0004390621,0.0003683274],"domain_scores_gemma":[0.9977989,0.0004100869,0.0000944612,0.001412874,0.0001475437,0.0001361956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00009717864,0.002528793,0.3501081,0.00005812378,0.0001652586,0.0000435212,0.4483981,0.000118484,0.0006883172,0.006954949,0.148655,0.04218414],"study_design_scores_gemma":[0.002792158,0.0001692662,0.4852721,0.0001340699,0.0003572935,0.000002332785,0.1830886,0.009371085,0.0006780588,0.04019123,0.2752893,0.002654481],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.930638,0.0001181379,0.008889571,0.03879985,0.0003861545,0.0007443435,0.0001061492,0.0002575268,0.02006026],"genre_scores_gemma":[0.9945859,0.00001566566,0.001562661,0.002786205,0.0003928163,0.00008858523,0.0002618563,0.00001123385,0.0002950359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2653096,"threshold_uncertainty_score":0.997536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039552226","doi":"10.1145/2207243.2207248","title":"Mapping question items to skills with non-negative matrix factorization","year":2012,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Non-negative matrix factorization; Matrix decomposition; Task (project management); Variance (accounting); Machine learning; Process (computing); Matrix (chemical analysis); Artificial intelligence; Automation; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.02240098912766123,"gpt":0.2745934823823906,"spread":0.2521924932547293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003212735,0.0002145944,0.0001769905,0.0002825498,0.000308026,0.0002982607,0.0005205843,0.00007046193,0.00001855726],"category_scores_gemma":[0.0002153938,0.000181545,0.00004566347,0.0007647304,0.00001728649,0.002462961,0.0001737878,0.0001870994,0.0008543778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322679,"about_ca_system_score_gemma":0.00003412978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007741132,"about_ca_topic_score_gemma":0.000007282661,"domain_scores_codex":[0.9984357,0.0001304405,0.0003026733,0.0003497715,0.0003480504,0.0004333366],"domain_scores_gemma":[0.9986187,0.0001825056,0.0001504977,0.0006758757,0.0002141025,0.0001582837],"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":[0.00004640735,0.0008319368,0.1440743,0.0001391844,0.0003685424,0.00002596708,0.2370605,0.04386597,0.1791833,0.3235664,0.0520613,0.01877621],"study_design_scores_gemma":[0.0015052,0.000870163,0.08026609,0.001182965,0.00005271263,0.00007895455,0.005121108,0.008711734,0.102313,0.002340025,0.7943868,0.00317127],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04080229,0.00001429557,0.9532901,0.003892508,0.001011222,0.0004223181,0.000001766766,0.0002000857,0.0003654064],"genre_scores_gemma":[0.8864707,0.000002108466,0.1071907,0.001195016,0.001238252,0.0001489863,0.00001445886,0.00002628781,0.003713462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8460994,"threshold_uncertainty_score":0.9999236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128899929","doi":"10.1145/2207243.2207247","title":"Social network analysis and mining to support the assessment of on-line student participation","year":2012,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Automatic summarization; Computer science; Toolbox; Social network analysis; Identification (biology); Visualization; Data science; World Wide Web; Exploit; Social media; Online discussion; Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.076759501794539,"gpt":0.4074878988997948,"spread":0.3307283971052558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004013715,0.0001298186,0.0002480144,0.0001228552,0.0002568244,0.00005848309,0.000203572,0.00002182486,0.000255218],"category_scores_gemma":[0.000008619527,0.0001006696,0.0001322421,0.0008063135,0.00003651984,0.0001677879,0.0001713968,0.00009505467,0.000009949673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002206436,"about_ca_system_score_gemma":0.00001407093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002695778,"about_ca_topic_score_gemma":0.00003980912,"domain_scores_codex":[0.998857,0.0001274935,0.0003507907,0.0001687837,0.000232877,0.000263008],"domain_scores_gemma":[0.9990801,0.0002003988,0.0001575611,0.0004295937,0.00006789473,0.00006451679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000570051,0.0002454426,0.9170595,0.000001642886,0.0009081322,1.472199e-7,0.003428632,0.01274873,0.0002315046,0.01080037,0.04620362,0.008366523],"study_design_scores_gemma":[0.0004105443,0.0003061965,0.9670236,0.00001530777,0.002798065,1.34839e-7,0.001513675,0.006417985,0.001116838,0.002559435,0.0173352,0.0005030606],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8210824,0.000005436405,0.1699336,0.007808117,0.00004802203,0.0002770594,0.000007667259,0.00002909047,0.0008085485],"genre_scores_gemma":[0.9906008,7.384612e-7,0.006781733,0.001132843,0.001062515,0.0002463987,0.0001025312,0.0000115267,0.00006096267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1695183,"threshold_uncertainty_score":0.4105188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034607275","doi":"10.1145/1046456.1046459","title":"Learning important models for web page blocks based on layout and content analysis","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":40,"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; Web page; Block (permutation group theory); Information retrieval; Partition (number theory); Page view; Static web page; Data mining; World Wide Web; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.07156513468895788,"gpt":0.263723749372729,"spread":0.1921586146837712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003536036,0.0002002775,0.0002997896,0.0004805945,0.0003528921,0.0003548443,0.0005988899,0.00006687111,0.00001193282],"category_scores_gemma":[0.0002069578,0.0001754638,0.0002084373,0.0008906577,0.00004138863,0.0007449358,0.0001484178,0.0001644543,0.00001490417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004178306,"about_ca_system_score_gemma":0.00007187721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006150408,"about_ca_topic_score_gemma":0.0000766659,"domain_scores_codex":[0.9983951,0.00005916821,0.0003922141,0.0005910995,0.0002661491,0.0002962322],"domain_scores_gemma":[0.9983237,0.0002316802,0.0001560139,0.001065966,0.0001071866,0.0001154421],"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":[0.00003270999,0.0002920232,0.006642864,0.0000169159,0.0008355855,0.00004607904,0.003073836,0.9574893,0.01300381,0.008258896,0.005671036,0.004637022],"study_design_scores_gemma":[0.0008253599,0.0001712054,0.000175635,0.0000185297,0.0003128498,0.000001281562,0.0002350106,0.9943652,0.0007692239,0.001617438,0.001228807,0.0002794721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1240727,0.00003243297,0.851975,0.0234238,0.00005197617,0.000171194,0.00003146431,0.0001541,0.00008732],"genre_scores_gemma":[0.9279734,0.000009580306,0.06680482,0.004679256,0.00007397772,0.0001224311,0.0001640408,0.00001373546,0.0001587926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8039007,"threshold_uncertainty_score":0.7155205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155709205","doi":"10.1145/846183.846209","title":"WEBKDD'99","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; DePaul University","keywords":"Computer science; Profiling (computer programming); Knowledge extraction; Data science; World Wide Web; Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02750424736256481,"gpt":0.2548875557424921,"spread":0.2273833083799272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001513042,0.000143201,0.0001139515,0.00008192117,0.0003013666,0.0003589886,0.001598908,0.00005100293,0.0007927378],"category_scores_gemma":[0.00005009361,0.0001365763,0.00005650573,0.0005589038,0.00004791706,0.001465265,0.0001981412,0.0001385421,0.006251722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002216752,"about_ca_system_score_gemma":0.00003870443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000023702,"about_ca_topic_score_gemma":0.000008108878,"domain_scores_codex":[0.9987972,0.00005004189,0.0002417119,0.0004297064,0.0002060006,0.0002753455],"domain_scores_gemma":[0.9978099,0.0001212065,0.00004068217,0.001882193,0.00004697452,0.00009907814],"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":[0.000002132382,0.0001140386,0.00006102648,0.000002484849,0.00001750858,0.0000101396,0.0009587732,0.000135929,0.001239397,0.01790708,0.5515742,0.4279773],"study_design_scores_gemma":[0.0002414497,0.00003562868,0.0006781511,0.000008945807,0.000008039963,0.00001690621,0.00002965789,0.01368712,0.001233662,0.006872381,0.9768925,0.0002955806],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02067245,0.00009545448,0.8225923,0.1385896,0.0003401046,0.000386307,0.00003834398,0.0009320123,0.01635345],"genre_scores_gemma":[0.08157098,0.0001234543,0.8721437,0.03206619,0.0009617493,0.0006888611,0.0002196891,0.00004927284,0.01217605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4276817,"threshold_uncertainty_score":0.994522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2736013904","doi":"10.1145/1809400.1809425","title":"Efficient algorithms for the mining of constrained frequent patterns from uncertain data","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Association rule learning; Data mining; K-optimal pattern discovery; Database transaction; Uncertain data; Data stream mining; Knowledge extraction; Geodetic datum; Data science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1036399997101661,"gpt":0.321903110243897,"spread":0.2182631105337309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004154315,0.0001709559,0.0001762773,0.00007159861,0.0003302856,0.000232138,0.00385701,0.00006809274,0.00004755396],"category_scores_gemma":[0.0003659344,0.0001277766,0.00006314999,0.0002591011,0.0001426454,0.0003631421,0.0008965662,0.0001950499,0.00002657113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001190511,"about_ca_system_score_gemma":0.0001024406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003000304,"about_ca_topic_score_gemma":0.0001333821,"domain_scores_codex":[0.9984226,0.00003562773,0.0004187734,0.0005906566,0.0002649604,0.000267368],"domain_scores_gemma":[0.9941629,0.001399686,0.0001932652,0.004030576,0.0001394933,0.00007414871],"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":[0.00001703593,0.0008670771,0.001339472,0.0000412675,0.0004615174,0.00001443032,0.0118718,0.004629269,0.1216272,0.04939465,0.2059901,0.6037462],"study_design_scores_gemma":[0.0005061816,0.00003839501,0.0006240113,0.00002151979,0.00004854193,0.000004921725,0.0004754431,0.9605882,0.003306099,0.00127548,0.03285878,0.000252436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04013851,0.00002451756,0.9213535,0.03570633,0.0005976473,0.0004769861,0.001590127,0.00008451256,0.00002789818],"genre_scores_gemma":[0.2417206,0.000005384976,0.7544978,0.00190759,0.000465042,0.0003774209,0.0009701215,0.00001897064,0.00003702473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9559589,"threshold_uncertainty_score":0.7167348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965269329","doi":"10.1145/1147234.1147235","title":"Introduction to the special issue on successful real-world data mining applications","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data science; Field (mathematics); Database transaction; Transaction data; Knowledge extraction; Data discovery; Data stream mining; Data mining; World Wide Web; Database; Metadata","retraction":null,"screen_n_in":null,"score":{"opus":0.03975452893360564,"gpt":0.2972189779695197,"spread":0.257464449035914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003546719,0.0002024797,0.0001568693,0.0002466287,0.0007448525,0.0006953455,0.003949926,0.00003456088,0.0001086793],"category_scores_gemma":[0.00008774236,0.0001662633,0.00003728142,0.001879205,0.00007766521,0.001248393,0.001043929,0.0001907737,0.002825303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006296162,"about_ca_system_score_gemma":0.00004966343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003789725,"about_ca_topic_score_gemma":0.00193278,"domain_scores_codex":[0.9978976,0.00007364622,0.0003980643,0.0009443877,0.0003587788,0.0003274993],"domain_scores_gemma":[0.9939038,0.0002453262,0.0001431863,0.005519689,0.0001066958,0.00008136641],"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":[0.000001872839,0.00007182093,0.00008404116,0.000001264712,0.000006797445,8.364476e-7,0.0001813392,0.0004366445,0.0001074886,0.01551713,0.8766944,0.1068964],"study_design_scores_gemma":[0.00009453623,0.0000288613,0.001245743,0.000005073036,0.00001332454,0.000002843598,0.00008860134,0.004151499,0.0004977924,0.0009199587,0.9927419,0.0002098994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009316785,0.000006594875,0.5161722,0.4758727,0.0006168491,0.0006963137,0.0001309938,0.0002681296,0.005304523],"genre_scores_gemma":[0.01123594,0.00003559257,0.7524106,0.02244364,0.193267,0.003242639,0.003873649,0.00009291311,0.01339802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4534291,"threshold_uncertainty_score":0.9979511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034271075","doi":"10.1145/3262579","title":"Session details: Special issue on learning from imbalanced datasets","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Canadian Imperial Bank of Commerce (Canada)","funders":"","keywords":"Computer science; Session (web analytics); Machine learning; Data science; Artificial intelligence; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03792720065423506,"gpt":0.2847760692288678,"spread":0.2468488685746328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001771154,0.000269209,0.0002263328,0.0002108909,0.0003954597,0.0004211233,0.001940947,0.000132221,0.0002467125],"category_scores_gemma":[0.0004430811,0.0002575046,0.00006415012,0.0005451894,0.00006758717,0.002362134,0.0005267443,0.0004505376,0.003194243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611897,"about_ca_system_score_gemma":0.00008072608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005048356,"about_ca_topic_score_gemma":0.00002547557,"domain_scores_codex":[0.9978307,0.000144205,0.0004186302,0.0007807023,0.0004615321,0.0003642523],"domain_scores_gemma":[0.9970075,0.0002081739,0.0002068361,0.002386504,0.0000756632,0.0001152549],"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":[0.00003970685,0.0003707968,0.0006314472,0.000009276623,0.00004477851,0.00007641559,0.002581791,0.002342058,0.07868935,0.01897678,0.8267455,0.06949207],"study_design_scores_gemma":[0.001095908,0.0001858827,0.002625772,0.0001054614,0.00001462124,0.000006345567,0.000133567,0.001201242,0.1647456,0.02192472,0.8072844,0.0006764143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008008929,0.00001909062,0.9382573,0.0492662,0.000906585,0.0004581319,0.0001421827,0.001169885,0.00177165],"genre_scores_gemma":[0.3337857,0.000125884,0.6144258,0.03159259,0.01121325,0.0005770806,0.007502315,0.0001098386,0.0006674482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3257768,"threshold_uncertainty_score":0.9999877,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085995514","doi":"10.1145/772862.772888","title":"WEBKDD 2002","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Conjunction (astronomy); Theme (computing); Knowledge extraction; Data science; Web mining; Data mining; Information retrieval; World Wide Web; Web service","retraction":null,"screen_n_in":null,"score":{"opus":0.06108137065648202,"gpt":0.2461904553370433,"spread":0.1851090846805613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009465607,0.0001505933,0.0001189137,0.0001215448,0.0003057473,0.0003658219,0.001617141,0.00005447474,0.0007991404],"category_scores_gemma":[0.00009062627,0.0001446471,0.00005844124,0.0006305951,0.00004911833,0.001512245,0.000381909,0.000152786,0.009211446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002449341,"about_ca_system_score_gemma":0.00001138933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000108312,"about_ca_topic_score_gemma":0.000006044756,"domain_scores_codex":[0.9987568,0.00003602663,0.0002511246,0.0004347814,0.0002260598,0.0002952624],"domain_scores_gemma":[0.9977036,0.0001094073,0.00006701175,0.001946212,0.0000668754,0.0001068808],"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":[1.868557e-7,0.00008768721,0.00003695604,0.000001690308,0.00001032779,0.000006700977,0.000670363,0.00002796179,0.0008553639,0.01512966,0.92101,0.06216308],"study_design_scores_gemma":[0.0002687613,0.00003955209,0.0002452775,0.00000933591,0.000009227774,0.00002029936,0.00004427474,0.07408132,0.001107783,0.002997768,0.9208354,0.0003410088],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001291348,0.0001632901,0.8694026,0.1176638,0.0003627053,0.0002279175,0.00002049369,0.0005433065,0.01032452],"genre_scores_gemma":[0.06436531,0.0001276969,0.8908682,0.0266546,0.0009823841,0.0006612905,0.00006880781,0.00005019302,0.01622154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09100924,"threshold_uncertainty_score":0.99156,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112993176","doi":"10.1145/1294301.1294305","title":"Introduction to the special issue on data mining for health informatics","year":2007,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"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 British Columbia","funders":"","keywords":"Personalized medicine; Computer science; Profiling (computer programming); Computational biology; Informatics; Metabolite profiling; Biomedicine; Data science; Oligonucleotide; Bioinformatics; Data mining; DNA; Biology; Metabolomics; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.05493152489629841,"gpt":0.3437162114384144,"spread":0.288784686542116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005604005,0.0001012757,0.00007592058,0.00007044816,0.0002500872,0.00005445051,0.0005033108,0.00005763962,0.00004741026],"category_scores_gemma":[0.0003795569,0.00007887703,0.00002845154,0.0001601211,0.0000211305,0.00001936734,0.0001613916,0.0000635561,0.0001090033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002527639,"about_ca_system_score_gemma":0.00005855213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002192512,"about_ca_topic_score_gemma":0.00008418597,"domain_scores_codex":[0.9990582,0.00003044915,0.0003263451,0.0002481222,0.0001350444,0.0002018274],"domain_scores_gemma":[0.9982943,0.00002909588,0.0001194108,0.001417757,0.00007075322,0.00006871221],"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":[0.00006640516,0.00002003923,0.00001499914,0.00000444396,0.000008475768,3.801105e-8,0.0006578343,0.0001732659,0.01558871,0.00004720006,0.9356904,0.0477282],"study_design_scores_gemma":[0.0001905629,0.000171549,0.0001580005,0.000005031522,0.000004831381,0.00000125802,0.001047709,0.00006601208,0.02381059,0.0000157478,0.9744355,0.00009319271],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.02347354,0.00005669362,0.3767184,0.5946853,0.002612405,0.001210437,0.00009268802,0.00003489921,0.001115613],"genre_scores_gemma":[0.1340279,0.0002681687,0.1603102,0.3410676,0.3383193,0.0008189677,0.0124946,0.0001546923,0.0125386],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.3357069,"threshold_uncertainty_score":0.3216512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122949122","doi":"10.1145/507515.507524","title":"MDM/KDD","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data science; Work (physics); Information retrieval; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0716650625786421,"gpt":0.2493575275794745,"spread":0.1776924650008325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001073522,0.0001450254,0.0001177242,0.0001437717,0.0002113543,0.0002640724,0.0012926,0.00007210408,0.0004231503],"category_scores_gemma":[0.0001324147,0.0001320395,0.00007644011,0.0006322605,0.00005557168,0.001468727,0.000246093,0.0001595399,0.002736395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003592918,"about_ca_system_score_gemma":0.00001162563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005314058,"about_ca_topic_score_gemma":0.000001520781,"domain_scores_codex":[0.99879,0.00005861926,0.000261313,0.0003661195,0.0002716326,0.0002522772],"domain_scores_gemma":[0.9982014,0.00009051853,0.00007829085,0.001439534,0.0001095962,0.00008070119],"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":[0.000003980286,0.0002898091,0.0002878362,0.00001554628,0.00002823356,0.00003078793,0.002775087,0.000006505215,0.02073398,0.07439851,0.7228773,0.1785525],"study_design_scores_gemma":[0.0006055161,0.0001728338,0.000700852,0.00003621768,0.000015708,0.00004015054,0.0001064139,0.03625016,0.1314373,0.02181254,0.8079756,0.0008467101],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001131045,0.0001449001,0.9039397,0.08787797,0.0002367311,0.0002121407,0.000002014776,0.0008634162,0.005592132],"genre_scores_gemma":[0.7835759,0.0001899976,0.1844002,0.02437182,0.0005221269,0.0003437634,0.00001891499,0.00003775714,0.006539471],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7824449,"threshold_uncertainty_score":0.9980401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067575620","doi":"10.1145/772862.772886","title":"MDM/KDD2002","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Conjunction (astronomy); Knowledge extraction; Data science; Series (stratigraphy); Information retrieval; Data mining; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.07236190396419816,"gpt":0.2474651348445299,"spread":0.1751032308803317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001142234,0.0001557669,0.0001268699,0.0001568725,0.000228612,0.0002985442,0.001345063,0.00007549529,0.0005656892],"category_scores_gemma":[0.0001509358,0.0001423514,0.00008067198,0.0006894075,0.00006056528,0.001545212,0.0002481885,0.0001639668,0.003491788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003957392,"about_ca_system_score_gemma":0.00001174652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004358265,"about_ca_topic_score_gemma":0.000001325864,"domain_scores_codex":[0.9987206,0.0000660103,0.0002792117,0.0003779939,0.000282468,0.0002736851],"domain_scores_gemma":[0.9981063,0.00009717185,0.00008348512,0.001506623,0.0001186136,0.00008779445],"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":[0.000001764165,0.0002348674,0.0001995057,0.000009302689,0.00002405492,0.00002532238,0.001645082,0.000007452173,0.02335216,0.05892117,0.8011663,0.114413],"study_design_scores_gemma":[0.0004169506,0.0001163728,0.0004524107,0.00001908618,0.00001387986,0.00003517533,0.00005936665,0.02726513,0.1082865,0.01763752,0.8450298,0.0006677849],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005972741,0.0001507461,0.8977689,0.0923724,0.0002306683,0.0001998777,0.000002228663,0.0008684323,0.00780953],"genre_scores_gemma":[0.68299,0.0002748656,0.2653696,0.03554424,0.0007013411,0.0004246057,0.00002360602,0.00005287576,0.01461898],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6823927,"threshold_uncertainty_score":0.9972841,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024539262","doi":"10.1145/1294301.1294307","title":"Novel approaches for small biomolecule classification and structural similarity search","year":2007,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Nearest neighbor search; Classifier (UML); Minkowski distance; Pruning; Similarity (geometry); Artificial intelligence; Data mining; Pattern recognition (psychology); Binary classification; k-nearest neighbors algorithm; Machine learning; Euclidean distance; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.2537296575736704,"gpt":0.3552435413062274,"spread":0.101513883732557,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008900145,0.0001711771,0.000141149,0.0002180294,0.0003085076,0.000321496,0.00071226,0.00008347724,0.00000312238],"category_scores_gemma":[0.0003088171,0.0001678824,0.00006503037,0.0004702241,0.00009806947,0.0008881051,0.0003516371,0.000151054,0.00000916197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006195376,"about_ca_system_score_gemma":0.00007696875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000173322,"about_ca_topic_score_gemma":0.00004095743,"domain_scores_codex":[0.998477,0.00008784428,0.000316855,0.0005402273,0.0002463705,0.0003317224],"domain_scores_gemma":[0.997981,0.0009589305,0.0000810989,0.0007158204,0.0001556052,0.0001075994],"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":[0.0001000659,0.000304454,0.002921921,0.0001122459,0.0001358802,0.000008733562,0.007497697,0.01863693,0.1510108,0.5863374,0.003993504,0.2289404],"study_design_scores_gemma":[0.000956649,0.0001040282,0.05886061,0.00001153726,0.00002136612,0.00003302996,0.0003411157,0.8737705,0.01839096,0.04412705,0.002860351,0.0005228289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1266618,0.00002722453,0.8549194,0.01756341,0.0001716863,0.0004284697,0.00001328012,0.00009278283,0.0001219469],"genre_scores_gemma":[0.4397019,0.000001097605,0.5586464,0.001348676,0.0001452196,0.0000538855,0.00005758329,0.00001242885,0.00003277773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8551335,"threshold_uncertainty_score":0.6846046,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2627710665","doi":"10.1145/772862.772887","title":"Multi-relational data mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"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; Knowledge extraction; Data science; Relational database; Data mining; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.2564192870307092,"gpt":0.3081369896490975,"spread":0.05171770261838832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001722161,0.0001482985,0.0001137435,0.0001214954,0.0003725353,0.0003057445,0.002887266,0.00005766753,0.0002233332],"category_scores_gemma":[0.0002409387,0.0001474823,0.00003282268,0.0005423793,0.00005240646,0.002858319,0.00125536,0.0001457224,0.001905879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002184952,"about_ca_system_score_gemma":0.00002091833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001140528,"about_ca_topic_score_gemma":0.00001322634,"domain_scores_codex":[0.998515,0.00004265557,0.0002995264,0.0006240063,0.0002613833,0.0002574974],"domain_scores_gemma":[0.9960802,0.0002142125,0.00009046302,0.003452697,0.00006902614,0.00009346687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.674853e-7,0.0002307877,0.0005026239,0.000003247133,0.00003415688,0.00001025383,0.001797058,0.0001560752,0.001179554,0.007773654,0.8761573,0.1121548],"study_design_scores_gemma":[0.0003025107,0.00001431868,0.0009458337,0.000009769948,0.000009961243,0.00001348431,0.00005632203,0.7351367,0.0000852517,0.0002755928,0.2629049,0.0002452325],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00108281,0.00009402289,0.9488583,0.0485773,0.0002352485,0.0001477286,0.00008144328,0.000267655,0.0006554553],"genre_scores_gemma":[0.01424389,0.00001899912,0.9790378,0.004486531,0.000295591,0.0001015849,0.0004477508,0.00001642544,0.001351485],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7349807,"threshold_uncertainty_score":0.9988713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028572284","doi":"10.1145/846183.846208","title":"Discovering geographic knowledge in data rich environments","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"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":"City, University of London; University of Utah; University of Florida; Florida State University","keywords":"Data science; Identification (biology); Computer science; Geographic information system; Knowledge extraction; Data mining; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.05390222068445348,"gpt":0.2862366298714703,"spread":0.2323344091870168,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001926393,0.0001529525,0.0001271246,0.0001594215,0.0001826169,0.0002633248,0.002982357,0.0000475888,0.0001334322],"category_scores_gemma":[0.00002576478,0.0001526403,0.00002585013,0.0007174892,0.00005264568,0.002675874,0.0009630269,0.0001699633,0.001370706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002734981,"about_ca_system_score_gemma":0.00002570122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005165968,"about_ca_topic_score_gemma":0.0001097002,"domain_scores_codex":[0.998542,0.00005262221,0.0002898689,0.0006521598,0.0001683209,0.0002950864],"domain_scores_gemma":[0.9964285,0.00009535511,0.0000417671,0.003357871,0.000007148381,0.00006935592],"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":[0.000007642443,0.001494272,0.008502877,0.00001922191,0.00008321429,0.00004932864,0.006178829,0.001899876,0.003834649,0.007511124,0.1675511,0.8028679],"study_design_scores_gemma":[0.0006696104,0.00003363949,0.01772199,0.00004171078,0.00001633389,0.00001148345,0.0001155964,0.08759618,0.0004559663,0.002310041,0.8904195,0.0006078877],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.308407,0.0004678744,0.6444324,0.04009342,0.0004003402,0.0007871108,0.0002199152,0.0003796261,0.004812312],"genre_scores_gemma":[0.6144987,0.0006758735,0.3705802,0.005529786,0.0006758542,0.000808151,0.001878731,0.00007802594,0.005274657],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.80226,"threshold_uncertainty_score":0.9994068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082225138","doi":"10.1145/1046456.1046458","title":"Extracting relational data from HTML repositories","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"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; Set (abstract data type); Information retrieval; Data mining; Information extraction; Quality (philosophy)","retraction":null,"screen_n_in":null,"score":{"opus":0.1297204511692792,"gpt":0.3005306323875561,"spread":0.170810181218277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002229565,0.0001487216,0.0001464707,0.0001155634,0.0004240787,0.0005240083,0.002295598,0.00006853427,0.00004777138],"category_scores_gemma":[0.000686105,0.0001441787,0.0000496479,0.0005100747,0.00005531375,0.004812952,0.001088023,0.0002147519,0.0006338899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004635008,"about_ca_system_score_gemma":0.000111467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002460489,"about_ca_topic_score_gemma":0.00006659404,"domain_scores_codex":[0.9983298,0.00006130678,0.0003608278,0.0006717383,0.0003609486,0.0002154163],"domain_scores_gemma":[0.9957921,0.0003500376,0.000152166,0.003549522,0.00008079632,0.00007536652],"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":[0.00003049247,0.0008515397,0.02478451,0.00001994753,0.0009527984,0.0005288162,0.01814923,0.01837353,0.08105386,0.1475038,0.6748206,0.03293088],"study_design_scores_gemma":[0.004262245,0.0002209451,0.02529628,0.0004093976,0.000585851,0.000166203,0.002451843,0.08547164,0.03518156,0.1757706,0.6662915,0.003891956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02391498,0.00008156543,0.9240887,0.05048844,0.0005528514,0.0000621739,0.00007072955,0.0002523164,0.0004882945],"genre_scores_gemma":[0.4474546,0.000009312016,0.5466772,0.002741223,0.001169853,0.0000231542,0.00162537,0.00001670907,0.0002826246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4235396,"threshold_uncertainty_score":0.8147584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406939872","doi":"10.1145/3715073.3715081","title":"Graph Fairness via Authentic Counterfactuals: Tackling Structural and Causal Challenges","year":2025,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Counterfactual conditional; Computer science; Psychology; Counterfactual thinking; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.05891837359566172,"gpt":0.3637102994061234,"spread":0.3047919258104617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005661293,0.0001650664,0.0002040303,0.000167117,0.001343851,0.0004557107,0.0003634445,0.0002088813,0.00008545507],"category_scores_gemma":[0.0009666916,0.0001606861,0.00006195723,0.0002886177,0.0004783691,0.001098095,0.0001274279,0.0003060031,0.00002738161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006630329,"about_ca_system_score_gemma":0.0001454857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009489833,"about_ca_topic_score_gemma":0.004117316,"domain_scores_codex":[0.9985232,0.0002306296,0.0002533837,0.0002990088,0.0003203373,0.0003734938],"domain_scores_gemma":[0.998674,0.0005469187,0.0000794982,0.0003425516,0.0002436427,0.0001134083],"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":[0.00004526832,0.0001016494,0.003138388,0.0001287312,0.0003449676,0.00002167959,0.3719122,0.00006696635,0.003588104,0.5650857,0.02476979,0.0307966],"study_design_scores_gemma":[0.0008532723,0.0001003995,0.005976699,0.000168613,0.0001623329,0.000001936369,0.05764781,0.0002112255,0.0007615753,0.8496167,0.08369065,0.0008087755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.593012,0.001524925,0.005044545,0.3892469,0.001477202,0.0005145366,0.00001371593,0.0002291006,0.008937026],"genre_scores_gemma":[0.9928964,0.0007557444,0.0004239122,0.004769999,0.0003521192,0.00003239907,0.000009697217,0.00001395645,0.0007457126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3998845,"threshold_uncertainty_score":0.9999563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3112675244","doi":"10.1145/3447556.3447563","title":"A Report on the First Workshop on Document Intelligence (DI) at NeurIPS 2019","year":2021,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"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; Library science; Intelligence analysis; Data science; World Wide Web; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.05144086556164734,"gpt":0.2786518561287233,"spread":0.2272109905670759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003521332,0.0002149659,0.0001820753,0.0001194887,0.0005679362,0.0005532511,0.001479832,0.00006105982,0.0002156788],"category_scores_gemma":[0.0007854542,0.0001551568,0.000147689,0.0009199952,0.00005629242,0.0005802693,0.0008933123,0.000283877,0.002270188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009031579,"about_ca_system_score_gemma":0.00006513412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001999517,"about_ca_topic_score_gemma":0.0001121905,"domain_scores_codex":[0.9978971,0.0001365584,0.0004103722,0.000755664,0.0004892443,0.0003110041],"domain_scores_gemma":[0.995096,0.0008347482,0.0001497948,0.003725427,0.0001110391,0.00008295264],"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":[0.000009326516,0.0001683243,0.0005204177,0.000004561564,0.00009317496,0.0008501337,0.001510712,0.005126696,0.0004008307,0.0153205,0.9650748,0.01092056],"study_design_scores_gemma":[0.0002423397,0.0001472376,0.001361453,0.0002273638,0.00007900671,0.0002335352,0.0004476396,0.01059564,0.02898917,0.006063642,0.9507241,0.0008889033],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03661755,0.0001072281,0.2221587,0.7373458,0.0009890738,0.0002455512,0.000009301049,0.000242565,0.002284195],"genre_scores_gemma":[0.8178104,0.000302881,0.0185985,0.1335661,0.001193269,0.000433617,0.0003754671,0.00006916877,0.02765067],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.7811928,"threshold_uncertainty_score":0.9985067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039760999","doi":"10.1145/380995.381054","title":"Report on MDM/KDD2000","year":2000,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Citation; Library science; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03370207834165126,"gpt":0.2762263369441018,"spread":0.2425242586024506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000199709,0.0001738509,0.0001415909,0.0001349301,0.000235321,0.0002639393,0.001112825,0.00008220874,0.0008505521],"category_scores_gemma":[0.000112831,0.0001543538,0.00008924718,0.0005990344,0.00005717962,0.001068281,0.00009190646,0.0001881226,0.00338217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005016373,"about_ca_system_score_gemma":0.00005492335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001030718,"about_ca_topic_score_gemma":0.000001456465,"domain_scores_codex":[0.9984393,0.0000707976,0.0003692929,0.0004994161,0.0003553239,0.0002659048],"domain_scores_gemma":[0.9975889,0.00009677128,0.00008567079,0.002046163,0.00009390722,0.00008857747],"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":[0.00002574444,0.0004158422,0.0003626627,0.000009484625,0.00003984651,0.0004050507,0.0009378252,0.00007535395,0.007870147,0.03754111,0.5245359,0.4277811],"study_design_scores_gemma":[0.0002601593,0.0001451925,0.001344695,0.00002258208,0.000009120191,0.0001330983,0.00001449302,0.001634662,0.08777832,0.01431747,0.8938747,0.0004655115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01068808,0.0000703258,0.7768957,0.1678337,0.0004015473,0.0005687888,0.000005901985,0.001971987,0.04156394],"genre_scores_gemma":[0.672691,0.0002207806,0.1870963,0.07430854,0.001270782,0.0007680494,0.0001559583,0.00009355212,0.06339508],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6620029,"threshold_uncertainty_score":0.9973938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110788923","doi":"10.1145/1117454.1117475","title":"WebKDD 2005","year":2005,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Theme (computing); Conjunction (astronomy); Web mining; World Wide Web; Data science; Knowledge extraction; Data mining; Web service","retraction":null,"screen_n_in":null,"score":{"opus":0.03629811663647502,"gpt":0.2671368829012802,"spread":0.2308387662648052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002289697,0.0001689987,0.0001573733,0.0001661235,0.0001918139,0.0003233259,0.001354799,0.0000779335,0.0001418132],"category_scores_gemma":[0.00004021412,0.0001522928,0.00008367845,0.0002730613,0.00002531989,0.002008612,0.0003540635,0.000158722,0.001421195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006364653,"about_ca_system_score_gemma":0.00003877861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002152188,"about_ca_topic_score_gemma":0.00007364607,"domain_scores_codex":[0.9986441,0.00007471738,0.0003336603,0.0003757262,0.0002256555,0.0003461002],"domain_scores_gemma":[0.9981062,0.00008207552,0.00008646292,0.001563275,0.00005927264,0.0001027492],"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":[7.911828e-7,0.00005921818,0.0001698563,0.000003151736,0.00001521512,0.000005510655,0.0006635567,0.00003309548,0.001970605,0.02806164,0.9299879,0.03902943],"study_design_scores_gemma":[0.0001689266,0.00002670835,0.0001489323,0.00001084995,0.000003614103,0.00001858698,0.00002160439,0.002277733,0.009263871,0.004240742,0.9835811,0.0002373099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001420844,0.0001213949,0.7911146,0.1986726,0.000363463,0.0002431326,0.000001932192,0.0007552133,0.007306866],"genre_scores_gemma":[0.4589306,0.00005260508,0.5038363,0.03129769,0.001485739,0.0003615977,0.00001624361,0.00003522424,0.003984067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4575097,"threshold_uncertainty_score":0.9993563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311079975","doi":"10.1145/3575637.3575654","title":"Experiences with Contrastive Predictive Coding in Industrial Time-Series Classification","year":2022,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Machine learning; Coding (social sciences); Data mining; Multivariate statistics; Pattern recognition (psychology); Artificial neural network; Time series; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04476407521292988,"gpt":0.2294792200046118,"spread":0.1847151447916819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002717065,0.0001539115,0.000199964,0.0002262897,0.0005843135,0.0002265562,0.0007669563,0.00003879572,0.0002633648],"category_scores_gemma":[0.0001272431,0.0001380308,0.0000448309,0.001158344,0.000102639,0.00186368,0.0003847385,0.0002856266,0.00002638477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252775,"about_ca_system_score_gemma":0.0001007341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003060944,"about_ca_topic_score_gemma":0.00002770495,"domain_scores_codex":[0.9983976,0.000184816,0.0003285201,0.0004444927,0.0003752523,0.0002692942],"domain_scores_gemma":[0.9990015,0.0001638367,0.0001853185,0.0005248213,0.0000722921,0.00005225381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00158174,0.001386264,0.03612605,0.00002171063,0.000654422,0.0003748299,0.6410747,0.0637811,0.02810923,0.06280996,0.1045534,0.05952664],"study_design_scores_gemma":[0.005537843,0.004024673,0.008957387,0.0001270415,0.0001384303,0.0001465655,0.3462788,0.5733794,0.00867636,0.00308427,0.04715133,0.002497921],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4936736,0.00006550954,0.4679309,0.03387409,0.0005854084,0.001018935,0.00003272284,0.0003755392,0.002443294],"genre_scores_gemma":[0.9919627,0.000001875978,0.006127668,0.0005739051,0.0001459378,0.0008502738,0.00004241373,0.00001161834,0.0002835809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5095983,"threshold_uncertainty_score":0.5628734,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048976003","doi":"10.1145/1540276.1540299","title":"WebKDD 2008","year":2008,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Knowledge extraction; Las vegas; Conjunction (astronomy); Data science; Library science; World Wide Web; Data mining; History; Archaeology; Tourism","retraction":null,"screen_n_in":null,"score":{"opus":0.05751956576975635,"gpt":0.2554444167508769,"spread":0.1979248509811206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009131375,0.0001501659,0.0001286377,0.0001241607,0.0005236179,0.0001422535,0.001569447,0.00005384882,0.00007913826],"category_scores_gemma":[0.00009057507,0.0001437435,0.00006161067,0.0006272701,0.0000870205,0.001479757,0.0004152682,0.0001525293,0.002477017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002548089,"about_ca_system_score_gemma":0.00007354696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002659547,"about_ca_topic_score_gemma":0.000007039539,"domain_scores_codex":[0.9987483,0.00003536891,0.0002553899,0.0004309676,0.0002444575,0.0002855019],"domain_scores_gemma":[0.9977534,0.0001079128,0.00006823026,0.001874763,0.0000861102,0.0001095665],"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":[8.723085e-7,0.0001084462,0.0003528106,0.000002026532,0.00001622414,0.00003449605,0.001372207,0.00005475562,0.001994216,0.01501762,0.9631273,0.01791909],"study_design_scores_gemma":[0.0004854385,0.00006804307,0.003265043,0.00001187033,0.00001053056,0.0001784044,0.00006679335,0.01571389,0.004100855,0.005662871,0.969869,0.0005672364],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01026585,0.00007493906,0.9276432,0.05852316,0.0003185649,0.0002038637,0.00001810305,0.0004839181,0.0024684],"genre_scores_gemma":[0.1191333,0.0001193648,0.8588606,0.01674403,0.0007241712,0.0004799683,0.0001474591,0.0000364556,0.003754649],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1088675,"threshold_uncertainty_score":0.9982997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2246590112","doi":"10.1145/2783702.2783708","title":"New Research Directions in Knowledge Discovery and Allied Spheres","year":2015,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Systems, Applications & Products in Data Processing (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Knowledge extraction; Data science; Schema (genetic algorithms); Viewpoints; Domain knowledge; Realm; Point (geometry); Information retrieval; World Wide Web; Knowledge management; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1693548473193507,"gpt":0.3730839166959473,"spread":0.2037290693765966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003906862,0.0001309475,0.0001571435,0.0002398302,0.0001832504,0.0002591854,0.0004471295,0.00005277616,0.00001240553],"category_scores_gemma":[0.0004550656,0.000117388,0.0000239632,0.0008948788,0.00008135365,0.003655183,0.0006691057,0.0002369572,0.0002063403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007695411,"about_ca_system_score_gemma":0.0002292938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006589983,"about_ca_topic_score_gemma":0.004691871,"domain_scores_codex":[0.9985349,0.0002125391,0.0002572474,0.0004233657,0.0002521883,0.0003198038],"domain_scores_gemma":[0.9983687,0.0003092494,0.00003828654,0.0009859193,0.0001239218,0.0001739323],"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":[0.00002311439,0.0001544585,0.003925543,0.00002168656,0.0000236023,0.00004300908,0.01302959,0.0002060467,0.003310579,0.2964619,0.6444122,0.03838832],"study_design_scores_gemma":[0.0007100333,0.00009023337,0.001207227,0.00006548728,0.000003163968,0.00001596862,0.001914467,0.0007447511,0.001511948,0.01795678,0.9754686,0.0003113423],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01820931,0.001724918,0.9564835,0.01848884,0.0006466082,0.0004074835,0.000009844724,0.0001729432,0.003856578],"genre_scores_gemma":[0.2979665,0.0003822098,0.6752157,0.002045327,0.001855074,0.0006377274,0.00008948611,0.0000788677,0.02172917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3310564,"threshold_uncertainty_score":0.4786943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311079932","doi":"10.1145/3575637.3575645","title":"Finding Multidimensional Simpson's Paradox","year":2022,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Burnaby Hospital","funders":"","keywords":"Computer science; Curse of dimensionality; Multidimensional data; Data science; Phenomenon; Data mining; Machine learning; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.04358511030504669,"gpt":0.2740753601844798,"spread":0.2304902498794331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002451126,0.0001459361,0.0001236277,0.0001584906,0.001134624,0.000165658,0.001454964,0.00002642977,0.0002655323],"category_scores_gemma":[0.00008149783,0.0001539123,0.00006724196,0.0007123972,0.00003467733,0.0008944956,0.001503199,0.0002694154,0.0004231538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007192809,"about_ca_system_score_gemma":0.00006901292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002086589,"about_ca_topic_score_gemma":0.000002998885,"domain_scores_codex":[0.9984572,0.00009051751,0.0002539345,0.0004958439,0.0004041186,0.0002984201],"domain_scores_gemma":[0.9981133,0.0002343104,0.00009561512,0.001423085,0.00004518298,0.00008851895],"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":[0.000005429383,0.0003780032,0.0004702376,0.000004736803,0.00004936385,0.00005560288,0.003268565,0.007184472,0.008874969,0.1003354,0.8149069,0.06446631],"study_design_scores_gemma":[0.000477965,0.00008666827,0.0007056877,0.000005104156,0.00001206926,0.00005239129,0.0003280089,0.1389393,0.001199481,0.005295003,0.8524459,0.0004524876],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02590994,0.00006041203,0.8863432,0.0856034,0.0006901848,0.0003528875,0.00009484245,0.0004514596,0.0004936737],"genre_scores_gemma":[0.3049092,0.000007496514,0.6744365,0.01708874,0.0003455339,0.001398853,0.0003911996,0.00003600204,0.001386443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2789993,"threshold_uncertainty_score":0.8726722,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978091735","doi":"10.1145/1809400.1809419","title":"Summary of the first ACM SIGKDD workshop on knowledge discovery from uncertain data (U'09)","year":2010,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data science; Knowledge extraction; Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.07323755533522192,"gpt":0.3036676604865192,"spread":0.2304301051512972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002917747,0.0002641945,0.0002366237,0.0001096153,0.0004920158,0.0004811743,0.01011466,0.0001345664,0.00004331941],"category_scores_gemma":[0.0008311992,0.0001964103,0.00009644545,0.0008880813,0.0002049227,0.002409876,0.004830461,0.0005709555,0.0003129413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002923917,"about_ca_system_score_gemma":0.0001567928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001841,"about_ca_topic_score_gemma":0.001121762,"domain_scores_codex":[0.9979243,0.0000793913,0.0004542072,0.0008632517,0.0003530755,0.0003258155],"domain_scores_gemma":[0.986958,0.001356448,0.0002108164,0.01128821,0.00009734762,0.00008913274],"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":[0.000009514864,0.0005399824,0.001190795,0.0000122233,0.00007791811,0.000004628731,0.002245619,0.0001608944,0.00787264,0.01387518,0.9097424,0.06426821],"study_design_scores_gemma":[0.0008184646,0.0000607579,0.008407855,0.0002419474,0.00008254375,0.000005464098,0.0003335654,0.0351544,0.006696067,0.01620496,0.9311208,0.0008731411],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1209132,0.0003216433,0.4339176,0.430402,0.005636776,0.001729826,0.002945855,0.0005901469,0.003542939],"genre_scores_gemma":[0.5047298,0.0001644639,0.4583522,0.02230249,0.004049383,0.000923659,0.003899383,0.0001677874,0.005410825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4080995,"threshold_uncertainty_score":0.9952411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967519701","doi":"10.1145/772862.772885","title":"KDD-2002 workshop report fractals and self-similarity in data mining","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Carnegie Mellon University; University of Southern California; National Science Foundation","keywords":"Computer science; Similarity (geometry); Data mining; Conjunction (astronomy); Fractal; Data science; Self-similarity; Information retrieval; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1189229411204401,"gpt":0.2997637057302101,"spread":0.1808407646097699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002907701,0.0001814793,0.0001905285,0.0001288799,0.0002427409,0.0003667844,0.001544038,0.00009393012,0.00009342065],"category_scores_gemma":[0.0002011406,0.0001787684,0.00002866751,0.0007667208,0.00004748447,0.002184817,0.001173344,0.0002657523,0.0001132363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002324326,"about_ca_system_score_gemma":0.00001583842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000131314,"about_ca_topic_score_gemma":0.0001359806,"domain_scores_codex":[0.9981542,0.00007134223,0.0004480942,0.0007729739,0.0002240074,0.0003293306],"domain_scores_gemma":[0.996377,0.0003592534,0.0001366329,0.002973594,0.00004588698,0.0001076451],"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":[0.000001921811,0.0004766422,0.006092973,0.00001219129,0.00003547596,0.0004094534,0.00281198,0.000389156,0.0006929467,0.002137,0.9504197,0.03652057],"study_design_scores_gemma":[0.0007548552,0.00003775051,0.00690747,0.00007140483,0.00003568544,0.0003375091,0.000198958,0.4166423,0.0002328633,0.003316192,0.5705238,0.0009411885],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1849016,0.001072459,0.3305137,0.4766368,0.0006803012,0.001261488,0.00002974501,0.0009804813,0.003923443],"genre_scores_gemma":[0.6947733,0.0003806308,0.2873253,0.01496035,0.0006357913,0.0002586543,0.0001105464,0.00003842528,0.001517002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5098717,"threshold_uncertainty_score":0.7289965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}