{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1100,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":1100,"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":"6c72437377aa","filters":{"topic":"Data Mining Algorithms and Applications"}},"results":[{"id":"W2064853889","doi":"10.1145/335191.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6360,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Scalability; Set (abstract data type); Tree (set theory); GSP Algorithm; Trie; Apriori algorithm; Association rule learning; Database transaction; Data structure; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02961243143666664,"gpt":0.2688342363591712,"spread":0.2392218049225046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347452,0.0001160786,0.0001125526,0.00004543518,0.0001709769,0.0002053458,0.0009652141,0.00004245195,0.0002379336],"category_scores_gemma":[0.00001965805,0.0001076114,0.00003441189,0.0001763004,0.00001513094,0.0004159127,0.0001366032,0.00007983806,0.0001809084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002978156,"about_ca_system_score_gemma":0.00003698879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005004618,"about_ca_topic_score_gemma":0.0001915441,"domain_scores_codex":[0.9989803,0.00003029193,0.0001990298,0.0004091923,0.0001540332,0.0002271486],"domain_scores_gemma":[0.9987328,0.000033456,0.00005686031,0.001060004,0.00002970633,0.00008713994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.213145e-7,0.00002687723,0.003585535,0.000002062584,0.000008742509,0.000003806644,0.0002893022,0.00002836535,0.0007479956,0.0003752284,0.004856424,0.9900748],"study_design_scores_gemma":[0.0008090095,0.000231119,0.01132679,0.00007052186,0.00002738519,0.0000611908,0.00005418539,0.7520654,0.00656089,0.001676776,0.2262554,0.0008614005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6896045,0.00003295649,0.307116,0.00134116,0.0002875429,0.0001334093,0.00002210895,0.0001835684,0.001278754],"genre_scores_gemma":[0.6193132,0.0001050628,0.3764024,0.0006936823,0.0004421746,0.00009794698,0.0001005486,0.00001781967,0.002827053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9892133,"threshold_uncertainty_score":0.4388266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4252403066","doi":"10.1145/342009.335372","title":"Mining frequent patterns without candidate generation","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02286779170339445,"gpt":0.2596902950618048,"spread":0.2368225033584103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008003981,0.0000644843,0.00005649247,0.00002424951,0.0001094746,0.0001839165,0.0003520371,0.00001891329,0.0003983122],"category_scores_gemma":[0.00000181177,0.00005516396,0.0000161874,0.0001072689,0.000008231948,0.0003149366,0.0000395995,0.00003302642,0.000192667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001414181,"about_ca_system_score_gemma":0.000020604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003118098,"about_ca_topic_score_gemma":0.0001014919,"domain_scores_codex":[0.9993872,0.00001221428,0.0001140367,0.0002423713,0.0001084365,0.0001357075],"domain_scores_gemma":[0.9994954,0.000007307201,0.00002057179,0.0004025737,0.00001700779,0.00005712002],"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":[3.428797e-7,0.0000351097,0.002227376,0.000001622869,0.000007509734,0.000003010313,0.0004344389,0.00009930125,0.0009204756,0.008916104,0.00847875,0.9788759],"study_design_scores_gemma":[0.0002062482,0.00003388497,0.004121784,0.000009430719,0.00000433602,0.00001908432,0.00002165627,0.9351001,0.004355408,0.0001457628,0.05576492,0.0002173383],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2569748,0.00001197407,0.7337631,0.0008616333,0.00007266157,0.00006697218,0.000009699472,0.0001562679,0.008082894],"genre_scores_gemma":[0.6749654,0.00002575227,0.317751,0.0008609932,0.000166988,0.00004065073,0.00005727012,0.0000066607,0.006125328],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9786586,"threshold_uncertainty_score":0.4361239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115482638","doi":"10.1023/b:dami.0000005258.31418.83","title":"Mining Frequent Patterns without Candidate Generation: A Frequent-Pattern Tree Approach","year":2003,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2615,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Data mining; Computer science; Scalability; Tree (set theory); Set (abstract data type); Apriori algorithm; GSP Algorithm; Association rule learning; Trie; Tree structure; Pattern recognition (psychology); Data structure; Artificial intelligence; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06223377143017436,"gpt":0.2906354910060366,"spread":0.2284017195758623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000626223,0.0003235563,0.0003181227,0.0001334253,0.0004049583,0.001082298,0.001475488,0.0000896878,0.000009347651],"category_scores_gemma":[0.00008109482,0.0002958364,0.00004480857,0.0003210364,0.00008453459,0.002180757,0.0008225354,0.0001487667,0.00002164632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004115632,"about_ca_system_score_gemma":0.0002053703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002051842,"about_ca_topic_score_gemma":0.0004532245,"domain_scores_codex":[0.9974858,0.0001400067,0.0004130488,0.001256015,0.0002358509,0.0004692793],"domain_scores_gemma":[0.9973748,0.0000847287,0.0001570188,0.002130726,0.00005780134,0.00019497],"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":[0.000005988209,0.0008369552,0.06569037,0.0001877766,0.0002595705,0.00004495326,0.01125097,0.0000174571,0.001106072,0.01250646,0.04609149,0.862002],"study_design_scores_gemma":[0.002526203,0.000219009,0.006705577,0.0003723191,0.0001866629,0.000386871,0.003755227,0.9131619,0.00168923,0.0001343722,0.06875874,0.002103856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1653436,0.001232436,0.8261517,0.000138587,0.0005319418,0.0002251722,0.0009919428,0.000142353,0.00524229],"genre_scores_gemma":[0.8112686,0.0001615975,0.1819956,0.0002725592,0.0004761686,0.0001282487,0.003911326,0.00004612405,0.001739785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9131445,"threshold_uncertainty_score":0.9999547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167681385","doi":"10.1109/icdm.2001.989541","title":"CMAR: accurate and efficient classification based on multiple class-association rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1209,"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":"Association rule learning; Associative property; Overfitting; Computer science; Data mining; Class (philosophy); Artificial intelligence; Scalability; Flexibility (engineering); Classification rule; Set (abstract data type); Statistical classification; Decision tree; Tree (set theory); One-class classification; Pattern recognition (psychology); Machine learning; Database; Support vector machine; Mathematics; Artificial neural network; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03426440388287782,"gpt":0.2436940187716003,"spread":0.2094296148887225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002049448,0.0000868334,0.00007488606,0.00006919408,0.0001744826,0.0002245601,0.0002764533,0.00005067068,0.00002971441],"category_scores_gemma":[0.0001308382,0.00007567226,0.00002233701,0.0002080274,0.00001509907,0.000157269,0.00005565986,0.00007610675,0.000207673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007474749,"about_ca_system_score_gemma":0.000009226555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001651969,"about_ca_topic_score_gemma":0.000005096859,"domain_scores_codex":[0.9991192,0.00003352003,0.0001501772,0.0003205279,0.0002150689,0.0001615514],"domain_scores_gemma":[0.9989994,0.00036591,0.0000998251,0.0004144646,0.0000560203,0.00006443246],"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":[0.000006772575,0.001207556,0.007528423,0.00002288976,0.00002825955,0.000002629496,0.000735315,0.004739561,0.002215219,0.1683586,0.04701778,0.768137],"study_design_scores_gemma":[0.0002498302,0.00002725965,0.01805217,0.000005948653,0.000002706729,4.515992e-7,0.0000147083,0.9702441,0.0002066416,0.00006400865,0.01103679,0.00009540092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03295823,0.00002922389,0.9373521,0.01099459,0.0001702094,0.0002813645,0.00004201312,0.0003874757,0.01778485],"genre_scores_gemma":[0.944839,0.00001235884,0.05356289,0.0005708711,0.00003203391,0.00004475317,0.00002174203,0.000005653618,0.0009107048],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9655045,"threshold_uncertainty_score":0.3085825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102297485","doi":"10.1145/1132960.1132963","title":"Interestingness measures for data mining","year":2006,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Ranking (information retrieval); Data mining; Process (computing); Data science; Measure (data warehouse); Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.295248331531593,"gpt":0.4196157088055408,"spread":0.1243673772739478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.006375656,0.000499811,0.001269542,0.000204063,0.0003942945,0.0007325637,0.01292307,0.0002017209,9.628759e-7],"category_scores_gemma":[0.002071792,0.0004512803,0.0002172329,0.0007908252,0.00005796782,0.000326387,0.0065853,0.0003067197,0.00003344399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005832926,"about_ca_system_score_gemma":0.0003495356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002104486,"about_ca_topic_score_gemma":0.00004462467,"domain_scores_codex":[0.9959319,0.0006876651,0.0009365287,0.001547529,0.0003089587,0.0005874268],"domain_scores_gemma":[0.9888154,0.004351588,0.00070416,0.005848452,0.0001774746,0.0001029058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[7.038353e-8,0.00003070365,0.000007516372,0.001275645,0.00004684846,0.00000278882,0.00002246008,0.000003164269,2.132701e-8,0.0002795556,0.01462828,0.983703],"study_design_scores_gemma":[0.00009443065,0.00001986294,0.00002387955,0.003655042,0.0001073291,0.00003514311,0.000002661264,0.06218503,1.431066e-7,0.000122055,0.9332471,0.0005072849],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[4.264906e-7,0.4580953,0.5404462,0.00002478091,0.0004838525,0.0003436609,0.00025426,0.0002554727,0.00009607524],"genre_scores_gemma":[0.000005548368,0.2733306,0.7220736,0.00002622875,0.0006745706,0.00005778322,0.003578048,0.00007559685,0.000178092],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9831957,"threshold_uncertainty_score":0.9997939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151953639","doi":"10.1109/tkde.2005.166","title":"Fast algorithms for frequent itemset mining using FP-trees","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","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":"Concordia University","funders":"","keywords":"Computer science; Data mining; Traverse; Association rule learning; Algorithm; Tree (set theory); Data structure; Tree structure; Trie; Prefix; Binary tree; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05517782314487753,"gpt":0.3067297556925058,"spread":0.2515519325476283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001941877,0.0001773885,0.0001578308,0.0001621162,0.0002377558,0.000176843,0.0007163907,0.00005733486,0.000004527164],"category_scores_gemma":[0.000005707857,0.0001836319,0.0000379477,0.0002658083,0.00001941717,0.0009323033,0.00002110892,0.0001193066,0.00001428661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004174819,"about_ca_system_score_gemma":0.00003867082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000153798,"about_ca_topic_score_gemma":0.00003306532,"domain_scores_codex":[0.9988756,0.000007874056,0.0002304932,0.0005226892,0.00009284649,0.000270515],"domain_scores_gemma":[0.9988046,0.0001390864,0.00003547944,0.0008561587,0.0000432712,0.0001214113],"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":[0.00000229816,0.0001532455,0.000002270808,0.00003794017,0.00005037117,0.000001234929,0.0005487343,0.0327771,0.00263042,0.0004759213,0.0008216894,0.9624988],"study_design_scores_gemma":[0.0002649273,0.00003324448,0.00001543196,0.00005872684,0.00002368727,0.00002060261,0.00002952387,0.9620176,0.003079309,0.000006797861,0.03423934,0.0002107866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001680434,0.0003745414,0.9963653,0.0001203766,0.0003658569,0.0001703619,0.0006825803,0.0001945859,0.0000459653],"genre_scores_gemma":[0.1133055,0.00007764086,0.8859453,0.00003875242,0.0002993993,0.00007474193,0.00008503442,0.00002955934,0.0001440631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.962288,"threshold_uncertainty_score":0.7488291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W80315153","doi":"10.1137/1.9781611972740.51","title":"A Foundational Approach to Mining Itemset Utilities from Databases","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","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":"University of Regina","funders":"","keywords":"Database transaction; Association rule learning; Computer science; Data mining; Database; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.0640315864945909,"gpt":0.2867239123360464,"spread":0.2226923258414555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009113332,0.00007928082,0.00007572152,0.00005344099,0.0001298854,0.0002083033,0.0006045589,0.0000130142,0.000030797],"category_scores_gemma":[0.00003185056,0.00007174688,0.00001912494,0.0002549895,0.00002418507,0.0005233056,0.0002979579,0.00003653902,0.0001673199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002395718,"about_ca_system_score_gemma":0.00007843743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009173336,"about_ca_topic_score_gemma":0.00003354144,"domain_scores_codex":[0.9991646,0.000007893031,0.0001320847,0.0003635092,0.0001824894,0.0001493792],"domain_scores_gemma":[0.9992364,0.00007323985,0.00002380934,0.0005438685,0.00003452954,0.00008812689],"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":[0.00000132799,0.0001780269,0.0001543061,0.000003265773,0.0000160401,0.000001123929,0.001734451,0.0003617473,0.0001372838,0.9343991,0.01295978,0.05005359],"study_design_scores_gemma":[0.001465048,0.0001183898,0.01889783,0.00009281305,0.00002129979,0.0000418605,0.003629026,0.2789011,0.002970038,0.03472034,0.6578749,0.001267307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01036647,0.00001522902,0.9757261,0.001013235,0.00007290585,0.00008545649,0.0002615598,0.0001566344,0.01230241],"genre_scores_gemma":[0.05385992,0.000001145215,0.9442768,0.0007699974,0.00008865738,0.0000599156,0.0005191528,0.00000420543,0.0004202574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8996787,"threshold_uncertainty_score":0.2925753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507635762","doi":"10.1007/978-3-319-46131-1_8","title":"The SPMF Open-Source Data Mining Library Version 2","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":551,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Implementation; Authorship attribution; Data mining; Plug-in; Open source; Visualization; Information retrieval; Interface (matter); Software; Software engineering; Artificial intelligence; Programming language; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03201302824163588,"gpt":0.2657663356650473,"spread":0.2337533074234114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001061724,0.0003673833,0.0003013809,0.0002339911,0.0009438265,0.003061086,0.0251153,0.0001691482,0.0000267689],"category_scores_gemma":[0.00009131594,0.0002360022,0.00004769032,0.0005016099,0.0007176307,0.002814252,0.0230522,0.0004461748,0.0001636844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007547386,"about_ca_system_score_gemma":0.0006228227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001074278,"about_ca_topic_score_gemma":0.00001545456,"domain_scores_codex":[0.9964331,0.00003343374,0.0004075693,0.001852083,0.0007004574,0.000573324],"domain_scores_gemma":[0.9932131,0.001171617,0.0002854978,0.005092297,0.00007196533,0.0001655657],"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":[0.000002057354,0.000008764488,0.000008861952,0.000003746672,0.000005447478,0.00001147648,0.0001092958,0.00009073387,0.00001039084,0.01483858,0.002696409,0.9822142],"study_design_scores_gemma":[0.0002095589,0.00006442932,0.00003140561,0.0003950091,0.000005736054,0.00004193587,3.570082e-7,0.4144326,0.0001521895,0.03665651,0.5475284,0.0004817954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005793956,0.00042884,0.9786344,0.006037675,0.001109887,0.000329872,0.00007895607,0.00017322,0.01320142],"genre_scores_gemma":[0.001029099,0.0002651015,0.985873,0.002106094,0.0008548244,0.00001534452,0.00007486575,0.00005852602,0.009723125],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9817324,"threshold_uncertainty_score":0.9979739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569729202","doi":"10.1007/3-540-45571-x_47","title":"Mining Access Patterns Efficiently from Web Logs","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":498,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Web mining; Data mining; Web mapping; Tree (set theory); Web modeling; World Wide Web; Information retrieval; Web service","retraction":null,"screen_n_in":null,"score":{"opus":0.02328515983586727,"gpt":0.2684583184193423,"spread":0.245173158583475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004304225,0.0005542263,0.0005072799,0.0006521121,0.0003464683,0.00177496,0.007815873,0.0002854928,0.0001221278],"category_scores_gemma":[0.00003156486,0.0005229894,0.0001231936,0.0006917982,0.0004269246,0.0009225883,0.002349698,0.0006686245,0.0001512889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001743371,"about_ca_system_score_gemma":0.0005303473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001507985,"about_ca_topic_score_gemma":0.0001479181,"domain_scores_codex":[0.9956039,0.0000249643,0.0005580064,0.002142385,0.0009535808,0.0007172059],"domain_scores_gemma":[0.9966633,0.0005047552,0.0002857361,0.002196446,0.0001236142,0.0002261528],"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":[0.000001610254,0.00003341461,0.0001128113,0.000007795138,0.000009079245,0.00005302524,0.0004110838,0.005895467,0.00003202228,0.002396271,0.00008806815,0.9909593],"study_design_scores_gemma":[0.0002874118,0.00007819184,0.0005349938,0.0004991368,0.00001265445,0.00003167989,2.35305e-7,0.9463339,0.000475535,0.04012298,0.01074307,0.000880179],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001120257,0.0002222628,0.9920714,0.0006925585,0.001181615,0.0002894599,0.0001265147,0.0002507564,0.004045193],"genre_scores_gemma":[0.1263205,0.0001818189,0.8679193,0.003550573,0.001267127,0.00004140652,0.0001387948,0.00008310095,0.0004974282],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9900792,"threshold_uncertainty_score":0.9997222,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1546703457","doi":"10.1137/1.9781611972733.6","title":"Hierarchical Document Clustering Using Frequent Itemsets","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":469,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Information retrieval; Hierarchical clustering; Brown clustering; Intuition; Vocabulary; Artificial intelligence; Library science; Fuzzy clustering; Canopy clustering algorithm; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03053123436791092,"gpt":0.2888526014938362,"spread":0.2583213671259252,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001655708,0.00007049591,0.00006650003,0.00003925569,0.0001280346,0.000194262,0.0003785386,0.00002186805,0.000049464],"category_scores_gemma":[0.00001782131,0.00006135506,0.00002153374,0.0002212609,0.00001783936,0.0002684695,0.0001536759,0.00006676271,0.0000536338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003668044,"about_ca_system_score_gemma":0.00003833855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005386897,"about_ca_topic_score_gemma":0.000003453727,"domain_scores_codex":[0.9992689,0.0000261975,0.0001352514,0.0002503507,0.0001347805,0.0001845063],"domain_scores_gemma":[0.9994065,0.00002825223,0.00002592759,0.0004292092,0.00002249823,0.0000876153],"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":[2.81391e-7,0.00007717373,0.0002419164,0.000006891718,0.00001433423,0.00001149882,0.0002826278,0.0006000337,0.00238543,0.8996252,0.001073237,0.09568136],"study_design_scores_gemma":[0.000487368,0.00005517537,0.0007746704,0.00003476788,0.000008476417,0.0002176527,0.00005808955,0.8474373,0.007602897,0.01820283,0.1245848,0.0005359126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008140318,0.00001888097,0.9842293,0.0003759536,0.0001372207,0.00006850819,0.000001330982,0.0001054858,0.006923061],"genre_scores_gemma":[0.1496608,0.000003740232,0.8496949,0.000309472,0.00002389492,0.000008290268,0.000002192223,0.000005043441,0.0002915945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8814224,"threshold_uncertainty_score":0.2501987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1906561224","doi":"10.1109/pdis.1996.568665","title":"A fast distributed algorithm for mining association rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":439,"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":"Association rule learning; Computer science; Scalability; Database transaction; Data mining; Distributed database; Distributed algorithm; Association (psychology); Algorithm design; Algorithm; Distributed computing; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02193598178644724,"gpt":0.2439799088221452,"spread":0.222043927035698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001525243,0.0000713398,0.00008387313,0.00003230066,0.0001587139,0.0002066986,0.0003984287,0.00004134517,0.00003446989],"category_scores_gemma":[0.00005186651,0.00006649027,0.00004094078,0.0001995884,0.000006965747,0.0003076141,0.00008153892,0.00003549184,0.0001083344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005691497,"about_ca_system_score_gemma":0.000007119377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009921973,"about_ca_topic_score_gemma":0.000002040714,"domain_scores_codex":[0.9992715,0.000009528515,0.000137902,0.0002375011,0.0001361718,0.0002074455],"domain_scores_gemma":[0.9993829,0.0001457765,0.00007601501,0.0002620555,0.00007994281,0.00005328974],"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":[6.019108e-8,0.00004417125,0.00004428969,0.000001211806,0.00001023146,2.9343e-7,0.000127171,0.000003194635,0.00001608999,0.008945186,0.05060082,0.9402073],"study_design_scores_gemma":[0.0001807298,0.00002152988,0.0003387683,0.000003453077,0.000004237382,0.00000177841,0.0000325753,0.9299083,0.0001345406,0.0004414526,0.06883688,0.00009577954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002581808,0.00002412862,0.9952404,0.001785836,0.0001004011,0.0001190734,0.0002812301,0.0002096631,0.001981086],"genre_scores_gemma":[0.001579243,0.000007494567,0.9940358,0.0001843049,0.00009667273,0.0001033327,0.0001267508,0.000005544859,0.003860843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9401115,"threshold_uncertainty_score":0.2711395,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126046032","doi":"","title":"SPMF: a Java open-source pattern mining library","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":417,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Java; Source code; License; Interface (matter); MIT License; Open source; Documentation; Database transaction; Implementation; Data mining; Database; Programming language; Information retrieval; World Wide Web; Operating system; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.05115801282898343,"gpt":0.3570069714406174,"spread":0.305848958611634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005018271,0.000114593,0.0002462483,0.0003919954,0.000451391,0.001378133,0.003738106,0.0000542594,0.0001044629],"category_scores_gemma":[0.0007992554,0.00009259699,0.00007156381,0.0007593492,0.0000678936,0.001361014,0.002111179,0.001394405,0.0001007136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597163,"about_ca_system_score_gemma":0.0001535082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000921299,"about_ca_topic_score_gemma":0.000002911434,"domain_scores_codex":[0.9973193,0.0007322135,0.0004276059,0.0002851557,0.0008231597,0.0004125808],"domain_scores_gemma":[0.9977609,0.0009889345,0.000285602,0.0005058801,0.0002117429,0.000246937],"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":[0.00001061745,0.00009738193,0.01270113,0.00001394591,0.00002147702,0.00003078669,0.0008678123,0.000398739,0.0002445677,0.001093274,0.01479633,0.9697239],"study_design_scores_gemma":[0.0006001992,0.0006044717,0.005083202,0.0001387083,0.000003883837,0.0002117979,0.0001303058,0.4226753,0.0002204645,0.0006229889,0.5695646,0.0001440724],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09662678,0.000472334,0.8714099,0.01865081,0.0002279282,0.000200379,0.000004058285,0.0001200842,0.01228775],"genre_scores_gemma":[0.799513,0.000119474,0.189574,0.0004894206,0.0007891075,0.00001079802,0.000009761105,0.00005479464,0.009439611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9695799,"threshold_uncertainty_score":0.9996585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1498871448","doi":"10.1109/icdm.2001.989550","title":"H-mine: hyper-structure mining of frequent patterns in large databases","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Scalability; Overhead (engineering); Process (computing); Set (abstract data type); Database; GSP Algorithm; Association rule learning; Apriori algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.03236253180025632,"gpt":0.2603427974947213,"spread":0.227980265694465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007379705,0.00007509217,0.0001053094,0.00007214054,0.00003189847,0.00002898583,0.0005221895,0.00002047973,0.0003240994],"category_scores_gemma":[0.00001946181,0.00006391941,0.00001893079,0.0002645121,0.00001319773,0.0002839527,0.0002143102,0.00006298051,0.00001431894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009410926,"about_ca_system_score_gemma":0.000007283594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001760481,"about_ca_topic_score_gemma":0.0002325101,"domain_scores_codex":[0.9992536,0.00001302128,0.0001853658,0.0002449822,0.0001306964,0.0001723411],"domain_scores_gemma":[0.9992853,0.00004696879,0.00004954227,0.0005567822,0.00002120416,0.00004015326],"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":[0.00000158182,0.0009360422,0.3273105,0.00009900915,0.00003257857,0.00004659744,0.004267426,0.00009564373,0.006373751,0.1513895,0.02771597,0.4817314],"study_design_scores_gemma":[0.001367957,0.00009910355,0.1468302,0.0001781941,0.00001263829,0.00006555641,0.0006681827,0.7808631,0.01362993,0.0004160496,0.05515053,0.0007184914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6260024,0.0001401134,0.3701093,0.0008089583,0.0001152746,0.0001152932,0.0005018067,0.0000844774,0.002122337],"genre_scores_gemma":[0.8161629,0.00001754138,0.1833306,0.0002021226,0.00002419099,0.000007016183,0.00003850528,0.000004131549,0.000212993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7807675,"threshold_uncertainty_score":0.3548661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146606092","doi":"10.1145/1824795.1824798","title":"A taxonomy of sequential pattern mining algorithms","year":2010,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":396,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Taxonomy (biology); Tree traversal; Sequential Pattern Mining; Key (lock); Data mining; Web mining; Information retrieval; Artificial intelligence; Machine learning; Algorithm; Web page; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1231731861239806,"gpt":0.3469654630301945,"spread":0.2237922769062139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003191373,0.0005059811,0.001515579,0.0002769301,0.0001974817,0.0002758596,0.005267059,0.0003468246,0.0000123382],"category_scores_gemma":[0.0002886992,0.0004682482,0.0004283673,0.0008707221,0.0001099576,0.0002051736,0.002876463,0.0007144632,0.000082934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000433679,"about_ca_system_score_gemma":0.0004148738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002272038,"about_ca_topic_score_gemma":0.00001566942,"domain_scores_codex":[0.9962771,0.000736769,0.001100014,0.001001511,0.0003713996,0.0005132255],"domain_scores_gemma":[0.9943764,0.00133255,0.001088381,0.002891943,0.0001638532,0.0001469018],"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":[3.112144e-8,0.00004207279,0.00001856594,0.0007663678,0.0000557677,0.00000747183,0.00005502376,0.00000129478,2.936022e-7,0.00009756508,0.0004192403,0.9985363],"study_design_scores_gemma":[0.0001182162,0.00003437724,0.00005077722,0.002763454,0.00009592209,0.00007796565,0.000004966478,0.01364663,0.000003324913,0.00003346361,0.9826189,0.0005519706],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005728662,0.3728141,0.6255513,0.000015589,0.0008115123,0.0003799033,0.0001073084,0.0001587113,0.0001558752],"genre_scores_gemma":[0.00003314732,0.4229795,0.5757232,0.00002685139,0.0006203607,0.00009251416,0.0003684454,0.00006701465,0.00008893301],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9979843,"threshold_uncertainty_score":0.9997769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1599136575","doi":"10.1109/adl.1998.670376","title":"Discovering Web access patterns and trends by applying OLAP and data mining technology on Web logs","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":396,"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; Web mining; World Wide Web; Clickstream; Data Web; The Internet; Web page; Web development; Web intelligence; Online analytical processing; Web API; Database; Data warehouse","retraction":null,"screen_n_in":null,"score":{"opus":0.05271091983902785,"gpt":0.3046453902207973,"spread":0.2519344703817695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000981772,0.000122794,0.0001222536,0.0001686704,0.0001683859,0.0004894452,0.001332355,0.00005264839,0.00002675314],"category_scores_gemma":[0.000009712523,0.0001072655,0.000007166667,0.0003741231,0.00005425822,0.0009339131,0.001944288,0.0001068827,0.000006606624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007812323,"about_ca_system_score_gemma":0.000004579785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003522551,"about_ca_topic_score_gemma":0.00004700056,"domain_scores_codex":[0.9989044,0.000008367072,0.0001253422,0.0006385358,0.0001066189,0.0002167532],"domain_scores_gemma":[0.9988942,0.00005648929,0.00005053912,0.0009261679,0.000007862039,0.00006472572],"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":[3.144815e-7,0.00003433207,0.003318785,0.000006564373,0.000008262596,0.000003280752,0.00008366803,0.000001230762,0.0004425126,0.001655724,0.01534689,0.9790984],"study_design_scores_gemma":[0.0004197436,0.00006345351,0.001418481,0.00004272073,0.000009429963,0.0000369932,0.000211707,0.9252347,0.0003548955,0.00005236552,0.0718363,0.0003192318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5922421,0.0005622102,0.3828672,0.01463133,0.0001496179,0.0002381588,0.0006581232,0.000712147,0.00793907],"genre_scores_gemma":[0.969842,0.0001688526,0.02872034,0.000294368,0.00003186724,0.00004479108,0.00005852221,0.00001065743,0.0008286627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9787792,"threshold_uncertainty_score":0.4719731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028470267","doi":"10.1017/s0269888906000737","title":"A survey of Knowledge Discovery and Data Mining process models","year":2006,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":388,"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; Process (computing); Business process discovery; Interoperability; Knowledge extraction; Process mining; Process modeling; Automation; Knowledge management; Data mining; Work in process; Engineering; Business process; Business process management; World Wide Web; Business process modeling","retraction":null,"screen_n_in":null,"score":{"opus":0.06022485778747027,"gpt":0.3127235079404043,"spread":0.252498650152934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001207374,0.0001380946,0.0002739446,0.00003887047,0.00005948018,0.00007155499,0.00167519,0.00002238678,8.151715e-7],"category_scores_gemma":[0.0001160935,0.00009742666,0.00002187266,0.000660972,0.00003584538,0.0006403925,0.0007245654,0.0000871629,0.000007602755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009341035,"about_ca_system_score_gemma":0.00006915636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005455256,"about_ca_topic_score_gemma":0.00003670966,"domain_scores_codex":[0.9990568,0.0000477771,0.0003039674,0.0003359775,0.00008733875,0.0001680981],"domain_scores_gemma":[0.9982213,0.0002800973,0.00008235662,0.001284381,0.00009691175,0.00003492817],"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":[0.000001947954,0.0004680764,0.0004860471,0.01265294,0.0001006057,0.000001893417,0.001349314,0.001637953,0.0001364389,0.05433729,0.02044757,0.9083799],"study_design_scores_gemma":[0.00007448395,0.000009716853,0.003792393,0.002019385,0.00002839564,0.000009555325,0.000002724558,0.9863476,0.00002782707,0.0001191453,0.007400224,0.0001685139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001994503,0.4023069,0.5937769,0.0001362463,0.0001161694,0.0003138922,0.0001059957,0.0001077885,0.001141591],"genre_scores_gemma":[0.9027498,0.02816456,0.06690317,0.00005909103,0.0002994513,0.0002174325,0.0004055205,0.00007908728,0.001121843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9847097,"threshold_uncertainty_score":0.3972944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140617045","doi":"","title":"Application of data mining techniques for medical image classification","year":2001,"lang":"en","type":"article","venue":"ACM Multimedia","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":311,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Computer science; Categorization; Mammography; Data mining; Breast cancer; Artificial intelligence; Artificial neural network; Anomaly detection; Contextual image classification; Pattern recognition (psychology); Image (mathematics); Machine learning; Cancer; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.06693477581833332,"gpt":0.3635870522762567,"spread":0.2966522764579234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006179645,0.00008350919,0.000121296,0.00006739781,0.00006879555,0.00004053652,0.00333143,0.00008165892,0.000008535179],"category_scores_gemma":[0.00079431,0.0000793236,0.0000234551,0.0002926296,0.00007925052,0.0006247504,0.0006750295,0.00006375937,0.00001895454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001320406,"about_ca_system_score_gemma":0.00007116309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003693852,"about_ca_topic_score_gemma":0.000009066342,"domain_scores_codex":[0.9988263,0.00001650041,0.0002947932,0.0004370976,0.0002702237,0.0001551433],"domain_scores_gemma":[0.9968868,0.0004255992,0.0001542982,0.002324166,0.0001219695,0.00008709892],"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":[0.000001847086,0.00006590452,0.0003411846,0.000007619992,0.000005093859,3.9297e-7,0.00009950347,4.600481e-8,0.004165481,0.001350829,0.005244042,0.988718],"study_design_scores_gemma":[0.0001918033,0.00002666337,0.002629811,0.00001678466,0.000008000493,0.000007924844,0.00003684969,0.9328204,0.002833852,0.0007062429,0.06061644,0.0001052277],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008099199,0.00002983053,0.9950787,0.003120731,0.00004726895,0.0003329187,0.00008207857,0.0001829926,0.0003155162],"genre_scores_gemma":[0.02578627,0.00005233803,0.9730119,0.0001070056,0.0001434002,0.0002486176,0.0006057742,0.000009326191,0.00003539332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9886128,"threshold_uncertainty_score":0.6190681,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105564121","doi":"","title":"Privacy preserving frequent itemset mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":286,"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 mining; Database transaction; Set (abstract data type); Process (computing); Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04667822289339513,"gpt":0.2506300199518214,"spread":0.2039517970584263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009811573,0.00006925323,0.00006451794,0.00004121082,0.0001141308,0.0002123151,0.001072715,0.00002164611,0.000294456],"category_scores_gemma":[0.00003064992,0.00006088663,0.00002343122,0.0002499339,0.00001246691,0.0004986564,0.0004209587,0.00004995039,0.0003058654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001269361,"about_ca_system_score_gemma":0.000005786358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004391952,"about_ca_topic_score_gemma":0.000002768033,"domain_scores_codex":[0.9992642,0.00001196031,0.0001324612,0.0002657345,0.000141367,0.0001842661],"domain_scores_gemma":[0.9990822,0.00005267522,0.00003522858,0.0007309187,0.00002584631,0.00007312871],"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":[1.76182e-7,0.0001467298,0.0008835992,0.00001038237,0.00001678035,0.00001030336,0.002673975,0.00003124523,0.000612312,0.08155864,0.4135037,0.5005521],"study_design_scores_gemma":[0.0001013361,0.00001772687,0.0006877076,0.00001104102,0.000001679294,0.00001119857,0.0000300807,0.7158704,0.0003616792,0.0006138028,0.2821619,0.0001315179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01000311,0.0001701558,0.8851843,0.004850516,0.0001473678,0.0001224312,0.000006903409,0.0004517697,0.09906343],"genre_scores_gemma":[0.111248,0.00002130891,0.8775625,0.0006107306,0.00009276615,0.00004034056,0.000006070582,0.000008015424,0.01041017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7158391,"threshold_uncertainty_score":0.3931383,"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":"W2112971308","doi":"10.1007/978-3-319-06608-0_4","title":"Fast Vertical Mining of Sequential Patterns Using Co-occurrence Information","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":242,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pruning; Bottleneck; Data mining; Representation (politics); Sequential Pattern Mining; Information bottleneck method; State (computer science); Pattern recognition (psychology); Artificial intelligence; Algorithm; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.02807506608825088,"gpt":0.2794808825966699,"spread":0.251405816508419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005696915,0.0003062715,0.0003736692,0.0005214154,0.0001756896,0.0004728784,0.002315752,0.0001833614,0.00001255751],"category_scores_gemma":[0.00006558043,0.0002963277,0.00008080331,0.0003548167,0.0004473406,0.001111835,0.0008541852,0.0003733721,0.00002138592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269937,"about_ca_system_score_gemma":0.0003958787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003102114,"about_ca_topic_score_gemma":0.000007002699,"domain_scores_codex":[0.9975193,0.00002159338,0.0006125033,0.0006620088,0.0007749876,0.0004096382],"domain_scores_gemma":[0.9981282,0.0002272734,0.0002798763,0.001016759,0.0002190236,0.0001288325],"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":[0.000002099095,0.00001609808,0.000158486,0.00006601148,0.000008099109,0.000004984587,0.0009054125,0.01372683,0.0001519729,0.0149059,0.00002146738,0.9700326],"study_design_scores_gemma":[0.000156829,0.00008082535,0.00009530047,0.0003658427,0.000008715081,0.00003944223,4.140587e-7,0.9940398,0.001504296,0.002162305,0.001181265,0.0003649968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001153248,0.00001676848,0.9972318,0.00009589725,0.0006756347,0.0001786398,0.0001088787,0.0000640784,0.0004749926],"genre_scores_gemma":[0.2434722,0.00001270267,0.75555,0.0005257642,0.0002831317,0.00000753749,0.0001205148,0.00001498906,0.00001313807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9803129,"threshold_uncertainty_score":0.9999489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2513061279","doi":"10.1007/s10115-016-0986-0","title":"EFIM: a fast and memory efficient algorithm for high-utility itemset mining","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Key (lock); Data mining; Projection (relational algebra); Database transaction; Task (project management); Tree (set theory); Algorithm; High memory; Database; Mathematics; Parallel computing","retraction":null,"screen_n_in":null,"score":{"opus":0.01286533636610831,"gpt":0.2381222319819108,"spread":0.2252568956158025,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000548853,0.0001143918,0.0001602475,0.0001092999,0.0002194931,0.0002770021,0.000214128,0.00005614005,0.000001484387],"category_scores_gemma":[0.00003823084,0.00007865322,0.00002025423,0.000163047,0.00004770574,0.001459292,0.0001527072,0.00002957216,0.00004823738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002252444,"about_ca_system_score_gemma":0.00003956776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001762827,"about_ca_topic_score_gemma":0.000001267471,"domain_scores_codex":[0.9991227,0.00002595643,0.0003644195,0.0001936656,0.0001101053,0.0001831537],"domain_scores_gemma":[0.999092,0.00017271,0.0001378472,0.0003033266,0.0001906559,0.0001034221],"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":[0.000001081535,0.00001394249,0.00002219216,0.00005725368,0.000006597157,6.281721e-8,0.00161845,0.000001581604,0.00001966127,0.00993299,0.003538189,0.984788],"study_design_scores_gemma":[0.0009723359,0.00007488783,0.001319578,0.0001437574,0.000008045311,0.00002787545,0.000555233,0.7896622,0.000267569,0.00005650237,0.2066921,0.0002198322],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006712245,0.0003578088,0.9895452,0.0001816323,0.00042066,0.0004128819,0.0002185038,0.0001046645,0.002046431],"genre_scores_gemma":[0.9233494,0.00008428992,0.07429645,0.0001218442,0.0003272239,0.0005772162,0.0001028264,0.00001280115,0.001127884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9845682,"threshold_uncertainty_score":0.3207385,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052496634","doi":"10.1007/s10844-006-0006-z","title":"Constraint-based sequential pattern mining: the pattern-growth methods","year":2007,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":233,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Simon Fraser University; National Science Foundation","keywords":"Sequential Pattern Mining; Computer science; Constraint (computer-aided design); Data mining; Point (geometry); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04073344562841342,"gpt":0.3292330749489349,"spread":0.2884996293205215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004318491,0.0001316182,0.0001998215,0.0002687593,0.0001439289,0.0005916406,0.001078062,0.00006285728,0.00001246021],"category_scores_gemma":[0.0001234675,0.00008535542,0.0001300322,0.0003424875,0.0000555724,0.001248469,0.00007966897,0.0002188755,0.00006971855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008995743,"about_ca_system_score_gemma":0.000146038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005293284,"about_ca_topic_score_gemma":0.000001349095,"domain_scores_codex":[0.9977692,0.000122596,0.001341397,0.00008386061,0.0004592095,0.000223674],"domain_scores_gemma":[0.9972278,0.0004177561,0.001212415,0.000355001,0.0006811451,0.0001059192],"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":[0.000004726419,0.0000378924,0.0003767145,0.00004310804,0.00006198786,0.000005556102,0.002792024,0.0006833519,0.0001170564,0.003587671,0.003910419,0.9883795],"study_design_scores_gemma":[0.001106938,0.0004384691,0.001182233,0.0005155763,0.00006754164,0.00164055,0.01158783,0.5591515,0.03624678,0.0001237932,0.3873363,0.0006024632],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001451291,0.00008646582,0.9951153,0.0006617937,0.001602698,0.0001734453,0.00001352862,0.00003141509,0.0008640054],"genre_scores_gemma":[0.9149901,0.00001500734,0.08360515,0.001036247,0.0002865878,0.00001016296,0.00001749433,0.000007565749,0.00003169339],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9877771,"threshold_uncertainty_score":0.5705204,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2744510879","doi":"10.1016/j.ins.2017.08.031","title":"Information sciences 1968–2016: A retrospective analysis with text mining and bibliometric","year":2017,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Citation; Data science; Computer science; Construct (python library); Salient; Citation analysis; Bibliometrics; Web of science; Information retrieval; Key (lock); Library science; Political science; MEDLINE","retraction":null,"screen_n_in":null,"score":{"opus":0.02740014933177197,"gpt":0.3024425598335855,"spread":0.2750424105018136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001508145,0.000117839,0.0001591973,0.01105352,0.002742051,0.006917721,0.001662905,0.00003574304,0.00001009672],"category_scores_gemma":[0.0003142521,0.00008343613,0.00003252946,0.0303039,0.000803264,0.02812971,0.0003623434,0.0000583326,0.00004968816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002674716,"about_ca_system_score_gemma":0.000176439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003653794,"about_ca_topic_score_gemma":0.0000404214,"domain_scores_codex":[0.998404,0.0000149694,0.0003301253,0.0001979366,0.0007944857,0.0002585399],"domain_scores_gemma":[0.998437,0.00009063361,0.0006229872,0.0005035987,0.0002522144,0.00009357893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000002319438,0.00001604131,0.1005004,0.00001139647,0.00005393934,3.230084e-7,0.004900936,0.0004550386,0.000005480124,0.03401365,0.001163207,0.8588773],"study_design_scores_gemma":[0.0002155493,0.0001818038,0.5771274,0.00002105506,0.00002721376,0.00001317596,0.001293276,0.4145515,0.00006873642,0.0005370448,0.005747304,0.0002159117],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1681019,0.00003794305,0.7873097,0.001824308,0.0001371831,0.0002230268,0.00003863452,0.0001386611,0.04218865],"genre_scores_gemma":[0.9028447,0.0000394759,0.09681308,0.0002291975,0.00001609022,0.00002403187,0.000007335458,9.543642e-7,0.00002519772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8586614,"threshold_uncertainty_score":0.9985563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1794915560","doi":"10.1007/978-3-540-68125-0_61","title":"A Tree-Based Approach for Frequent Pattern Mining from Uncertain Data","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Database transaction; Data mining; Tree (set theory); Transaction data; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06928100922740438,"gpt":0.280066816554506,"spread":0.2107858073271017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006514601,0.0005329186,0.0005363923,0.000434703,0.0003887699,0.000577975,0.009000313,0.0002625465,0.000008164827],"category_scores_gemma":[0.00008298396,0.0004935115,0.0001093521,0.0004534086,0.0005080337,0.0006069536,0.002032161,0.0004553158,0.00001152687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001618514,"about_ca_system_score_gemma":0.0008023416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002270839,"about_ca_topic_score_gemma":0.0001041534,"domain_scores_codex":[0.9952518,0.00002542368,0.000548336,0.002725473,0.0008062361,0.0006427708],"domain_scores_gemma":[0.9944163,0.0008182245,0.0003305102,0.004081486,0.0001631235,0.0001903649],"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":[0.0000021192,0.0000498138,0.00003018959,0.00001823332,0.00001250541,0.00001941725,0.0003283068,0.008714082,0.00001909067,0.0003100834,0.0005446937,0.9899515],"study_design_scores_gemma":[0.0003779863,0.00008340554,0.00003831941,0.0001655398,0.00001235126,0.00001350193,3.440508e-7,0.9888149,0.0001500043,0.003800922,0.005961888,0.0005808215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001417945,0.0003771312,0.9963573,0.0006852229,0.0005360792,0.0006133635,0.0006066543,0.0001703167,0.0006398078],"genre_scores_gemma":[0.004743263,0.00002299755,0.991785,0.001613145,0.0005849696,0.00006754476,0.001056319,0.00004098338,0.00008578104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9893706,"threshold_uncertainty_score":0.9997516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117423052","doi":"10.1109/icdm.2002.1183881","title":"Text document categorization by term association","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":224,"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; Classifier (UML); Categorization; Artificial intelligence; Text categorization; Association rule learning; Machine learning; Natural language processing; Data mining; Information retrieval; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.005463032048834978,"gpt":0.2254333012677956,"spread":0.2199702692189607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001915998,0.00005133496,0.00004523106,0.00002156379,0.00008781657,0.0001910437,0.0002321062,0.0000293387,0.0000604623],"category_scores_gemma":[0.00003164484,0.00004650152,0.00001383349,0.0002169256,0.000003615588,0.0003815386,0.0000312744,0.00003466696,0.000202703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008327157,"about_ca_system_score_gemma":0.00002314516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002378188,"about_ca_topic_score_gemma":0.00000201044,"domain_scores_codex":[0.9994141,0.00002268918,0.0001050389,0.0001837376,0.0001502354,0.0001242326],"domain_scores_gemma":[0.999586,0.00002928058,0.00005825962,0.0002478363,0.00003867842,0.00003987605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[1.1904e-7,0.00007681376,0.001755596,0.00000194379,0.00001159404,2.812368e-7,0.0001798778,0.00000691664,0.001901452,0.7541828,0.1497347,0.09214789],"study_design_scores_gemma":[0.0005734193,0.00006589701,0.003700466,0.000005795639,0.00001193819,0.000005494903,0.00005637317,0.02319917,0.03620964,0.01985304,0.9158555,0.0004632351],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009139549,0.000019547,0.9739731,0.001031761,0.0001217167,0.00007570568,0.00000369152,0.0001184295,0.02374212],"genre_scores_gemma":[0.5951189,0.00006771811,0.3447198,0.001356419,0.00007062284,0.000129567,0.0001525599,0.00001602137,0.05836838],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7661209,"threshold_uncertainty_score":0.2605405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169474320","doi":"10.1109/ideas.2003.1214917","title":"Incremental mining of frequent patterns without candidate generation or support constraint","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":216,"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; Constraint (computer-aided design); Data mining; Tree (set theory); Tree structure; Binary tree; Algorithm; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0403410905032692,"gpt":0.284965270308043,"spread":0.2446241798047738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184131,0.00007683773,0.00009743316,0.00004074194,0.00006412523,0.00006526377,0.0002471858,0.00002191404,0.0002933582],"category_scores_gemma":[0.00001486152,0.00005976217,0.00002036615,0.0001117966,0.00003033142,0.0002077112,0.00005673254,0.00003374216,0.00001210624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002264699,"about_ca_system_score_gemma":0.0001206557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832108,"about_ca_topic_score_gemma":0.0001728693,"domain_scores_codex":[0.9992406,0.00002519566,0.0002243041,0.0002224665,0.0001500113,0.0001374349],"domain_scores_gemma":[0.9994816,0.00001584793,0.00008015084,0.0003219804,0.00004031074,0.00006015196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000790893,0.0006512692,0.08537741,0.00005876334,0.0001634639,0.00004830127,0.00413391,0.00008860336,0.09885857,0.4277788,0.01674204,0.3660909],"study_design_scores_gemma":[0.002752633,0.0008325762,0.01031378,0.00009013685,0.00005790886,0.0004433412,0.002185033,0.2765062,0.678694,0.0004263099,0.02647762,0.001220535],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2385033,0.000003341389,0.7574009,0.0001142158,0.0001001524,0.0001105055,0.00004418679,0.00004317986,0.003680219],"genre_scores_gemma":[0.7430863,0.000004087848,0.2564383,0.0001771561,0.00001718554,0.00001678863,0.00002953583,0.000003397795,0.0002272302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5798354,"threshold_uncertainty_score":0.3212067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1581468894","doi":"10.1007/978-3-540-30116-5_6","title":"Mining Positive and Negative Association Rules: An Approach for Confined Rules","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Association rule learning; Association (psychology); Associative property; Computer science; Process (computing); Data mining; Correlation; Complement (music); Affinity analysis; Space (punctuation); Artificial intelligence; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01876755616653307,"gpt":0.2550179653593767,"spread":0.2362504091928436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007903567,0.0003698906,0.0004081206,0.0003522264,0.0004132441,0.0008193811,0.001489745,0.0002654531,0.000002832237],"category_scores_gemma":[0.0001403544,0.0003544887,0.00006461191,0.0002402882,0.0003423365,0.0007689181,0.0005118598,0.0003340911,0.000004326063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003825538,"about_ca_system_score_gemma":0.0004242446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005526694,"about_ca_topic_score_gemma":0.00001729236,"domain_scores_codex":[0.9972646,0.00002544025,0.0003498726,0.001389368,0.0005090142,0.0004616785],"domain_scores_gemma":[0.9977608,0.0007323358,0.0003663338,0.000666713,0.000323253,0.0001505492],"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":[0.000004657249,0.00005183742,0.00002099988,0.00002894832,0.00002359865,0.000004141839,0.003325276,0.002321635,0.00005371109,0.1075034,0.00001575448,0.886646],"study_design_scores_gemma":[0.0005174748,0.0002510114,0.0005109875,0.0002034888,0.00001890305,0.00001930383,0.000002692846,0.8203733,0.0005277579,0.1767332,0.0002427892,0.0005990657],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002256317,0.00009378438,0.9961382,0.0004923455,0.000244204,0.0005829725,0.0001401301,0.0001073886,0.001975308],"genre_scores_gemma":[0.01056834,0.00001565853,0.9881974,0.0005805162,0.0002793372,0.00004963605,0.000124498,0.00002323221,0.0001613364],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.886047,"threshold_uncertainty_score":0.9998907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972870286","doi":"10.1145/347090.347166","title":"Can we push more constraints into frequent pattern mining?","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Computer science; Data science; Library science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01379721733865673,"gpt":0.2539804103553299,"spread":0.2401831930166732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008174239,0.0001053458,0.00009556079,0.00003664664,0.0001132182,0.0001557126,0.000779163,0.00003480473,0.001037698],"category_scores_gemma":[0.000004388162,0.00009208285,0.00003175744,0.0001923979,0.0001018634,0.0001759773,0.00009808085,0.00006684255,0.00028522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002406737,"about_ca_system_score_gemma":0.00005364106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006289402,"about_ca_topic_score_gemma":0.000111594,"domain_scores_codex":[0.9990929,0.0000127538,0.0001656559,0.0003514088,0.0001618212,0.0002154033],"domain_scores_gemma":[0.9991937,0.00002989346,0.00002910062,0.0005963206,0.00002651076,0.0001244936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[1.203783e-7,0.00002937711,0.0002925125,0.000002152164,0.000005708405,0.00000733417,0.001162442,0.000003754566,0.00003358398,0.002415641,0.007652686,0.9883947],"study_design_scores_gemma":[0.001649769,0.0002626943,0.01296929,0.0001879252,0.0000321016,0.0002925795,0.00199956,0.4167355,0.00367287,0.01495118,0.5453707,0.001875846],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1155347,0.0001072275,0.7677879,0.05892119,0.0003015219,0.0003660975,0.0001055997,0.0008277765,0.05604807],"genre_scores_gemma":[0.663508,0.00004753177,0.3271768,0.003645012,0.0001103446,0.0000672177,0.00003802954,0.00001380389,0.005393254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9865189,"threshold_uncertainty_score":0.9998755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128723273","doi":"10.1145/775047.775081","title":"Mining frequent item sets by opportunistic projection","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Set (abstract data type); Tree (set theory); Data mining; Database transaction; Projection (relational algebra); Algorithm; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05014063780212529,"gpt":0.2591399793286207,"spread":0.2089993415264954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008162038,0.00007026163,0.00005993569,0.00003759991,0.0001212965,0.0001498685,0.0003610117,0.00002582681,0.0001189594],"category_scores_gemma":[0.00001794379,0.00006278575,0.00001834486,0.0002198614,0.00001551856,0.0002899553,0.00008189142,0.00004565846,0.0001609335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002218694,"about_ca_system_score_gemma":0.00001008929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004240788,"about_ca_topic_score_gemma":0.000002533151,"domain_scores_codex":[0.999314,0.00001146327,0.000128485,0.0002648373,0.0001295002,0.0001517446],"domain_scores_gemma":[0.9994599,0.00003956295,0.00004216734,0.0003583379,0.00002593212,0.00007405951],"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":[1.388654e-7,0.0001010542,0.00008753959,0.000004197835,0.000006949006,0.000004572882,0.0003232119,0.000001007353,0.0007671422,0.02153234,0.4009188,0.5762531],"study_design_scores_gemma":[0.0001020615,0.00003564468,0.0001224872,0.000007523898,0.000003227634,0.0000272774,0.00005239628,0.8564972,0.0003565506,0.0001900652,0.1424623,0.0001432797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003660491,0.00005733387,0.9525583,0.002355238,0.0001769478,0.0001454426,0.00002136609,0.0004038716,0.04062096],"genre_scores_gemma":[0.2366847,0.00006419679,0.7307353,0.001412904,0.0001032426,0.0001583909,0.00009458763,0.00002019015,0.03072648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8564962,"threshold_uncertainty_score":0.2560329,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2617643752","doi":"10.1038/nmeth.4299","title":"Clustering","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Cluster analysis; Computational biology; Computer science; Biology; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03710119200032522,"gpt":0.4468142170302719,"spread":0.4097130250299466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006268613,0.00005599111,0.0000714593,0.00002445938,0.0003963376,0.000420021,0.001713516,0.00009446748,0.000005188352],"category_scores_gemma":[0.0002434572,0.00004754769,0.000027744,0.00005184796,0.00002555353,0.0003547299,0.0005638845,0.0002693643,0.00001985321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008116109,"about_ca_system_score_gemma":0.00001417587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009365505,"about_ca_topic_score_gemma":0.000002192124,"domain_scores_codex":[0.9994751,0.00003945513,0.00006579873,0.0002218094,0.00008068336,0.0001171892],"domain_scores_gemma":[0.9983858,0.00006956655,0.00006686339,0.00140295,0.00002988605,0.00004487427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[1.771333e-7,0.000005046872,0.00002683432,0.000001655994,0.000002815057,0.000001473588,0.00003858699,0.000001099493,0.0006249459,0.02701952,0.001194868,0.971083],"study_design_scores_gemma":[0.0001865111,0.00001761998,0.01761688,0.00001778405,0.000005561582,0.00002499361,0.000006765312,0.3689397,0.008812699,0.01400609,0.5901399,0.0002254699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006870621,0.0001420653,0.9800836,0.002024991,0.0006279043,0.00003696408,0.000002128022,0.0000865346,0.01692704],"genre_scores_gemma":[0.007387209,0.000006285865,0.9914904,0.000298101,0.0001246605,0.000009161463,0.000001030952,0.000003887933,0.0006793285],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9708575,"threshold_uncertainty_score":0.4050272,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157169143","doi":"10.1109/icdm.2012.20","title":"Direct Discovery of High Utility Itemsets without Candidate Generation","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Data mining; Pruning; Bounding overwatch; Property (philosophy); Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02712208151631306,"gpt":0.2701453798814657,"spread":0.2430232983651526,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002225165,0.00005991521,0.00009287846,0.00002572109,0.00005675435,0.00006845807,0.0002722999,0.00002045782,0.00001296814],"category_scores_gemma":[0.00001265356,0.0000468604,0.00002047958,0.0001504772,0.0000235671,0.001077033,0.000118464,0.00002823676,0.00001819308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009568947,"about_ca_system_score_gemma":0.00002322608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006963382,"about_ca_topic_score_gemma":0.00004213599,"domain_scores_codex":[0.9994182,0.00002305404,0.0001374225,0.0001605999,0.0001192453,0.0001414806],"domain_scores_gemma":[0.999355,0.00002221284,0.00005611821,0.000488514,0.00002871248,0.00004941153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007291641,0.0008860023,0.07445814,0.00003970313,0.00007601248,8.286646e-7,0.001620925,0.00004264743,0.04370318,0.4524613,0.0388049,0.3878991],"study_design_scores_gemma":[0.0005814257,0.00008388377,0.2181252,0.00002306688,0.00003296832,0.00001315661,0.0000440762,0.3321343,0.4119141,0.0008504199,0.03558371,0.0006136509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2405016,0.00004634453,0.7553432,0.0001752586,0.0002135303,0.00007398323,0.00004541799,0.00005911051,0.003541578],"genre_scores_gemma":[0.9264166,0.000006570171,0.07272169,0.00005985998,0.0000961614,0.00001308221,0.00003883131,0.000002742902,0.0006444645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.685915,"threshold_uncertainty_score":0.1910912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103986443","doi":"10.1145/564376.564412","title":"Document clustering with committees","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01839922667157008,"gpt":0.2197457956381992,"spread":0.2013465689666291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003517041,0.00004241969,0.00003783708,0.00001747923,0.00006973233,0.0001386337,0.0003805086,0.000007522528,0.0001033359],"category_scores_gemma":[9.858884e-7,0.00002974705,0.000007516062,0.0001230795,0.00001242879,0.0002465005,0.000127591,0.00002904317,0.0001882323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006875153,"about_ca_system_score_gemma":0.000001913609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002511119,"about_ca_topic_score_gemma":0.00001349368,"domain_scores_codex":[0.9996269,0.000004223818,0.000053823,0.0001356882,0.00008409831,0.00009529838],"domain_scores_gemma":[0.9995708,0.00001427551,0.00001423889,0.0003529147,0.00001142779,0.0000362935],"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":[3.963536e-7,0.00007857569,0.0002510344,0.000004703493,0.00001370037,0.000007714984,0.0006664769,0.0001201183,0.00005295154,0.119035,0.03357806,0.8461913],"study_design_scores_gemma":[0.0002384458,0.00008200607,0.0007999474,0.00001194717,0.000002459991,0.00003540661,0.00004692666,0.8317521,0.0003950968,0.0005360868,0.1659216,0.0001779288],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007027647,0.00001998423,0.9627187,0.002543746,0.00002376396,0.00004199128,5.814743e-7,0.0001446093,0.03380391],"genre_scores_gemma":[0.202933,0.00001000977,0.7916515,0.0005582559,0.00002541155,0.00002362711,0.000001063166,0.000003663221,0.004793514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8460134,"threshold_uncertainty_score":0.2419408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005499394","doi":"10.14778/2168651.2168658","title":"Dense subgraph maintenance under streaming edge weight updates for real-time story identification","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":172,"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; Enhanced Data Rates for GSM Evolution; Identification (biology); Social media; Globe; Scale (ratio); Point (geometry); Data science; Edge device; Range (aeronautics); Social network (sociolinguistics); World Wide Web; Artificial intelligence; Geography; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0132090247020189,"gpt":0.2384151435654986,"spread":0.2252061188634797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006221068,0.0001234175,0.0001312776,0.00007071628,0.0002387768,0.00009514148,0.000970941,0.0000363739,0.000003709798],"category_scores_gemma":[0.00004234499,0.00009408485,0.00008700402,0.0002870941,0.00006796048,0.0006674593,0.0002703213,0.00007253347,0.000019318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007704707,"about_ca_system_score_gemma":0.00002182009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834517,"about_ca_topic_score_gemma":6.298242e-7,"domain_scores_codex":[0.9989182,0.000006334805,0.0002469689,0.0002812808,0.0002249435,0.000322222],"domain_scores_gemma":[0.9990567,0.00007127695,0.0002969279,0.0003005978,0.0001982198,0.00007630842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001292214,0.0004172147,0.002134425,0.0001158259,0.00009172467,5.46532e-8,0.001879664,0.000008658285,0.347117,0.5531856,0.04869983,0.046337],"study_design_scores_gemma":[0.001516584,0.0001499862,0.07202521,0.0003276091,0.0002020034,0.00003702205,0.001259285,0.03445954,0.7972062,0.04403552,0.04781608,0.0009650009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7876935,0.0008398109,0.1883656,0.01246155,0.001818225,0.003366261,0.000218545,0.0006089368,0.004627535],"genre_scores_gemma":[0.9329337,0.00009321036,0.06498047,0.00009990918,0.0001632036,0.0003291957,0.00001156774,0.00001868499,0.001370076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5091501,"threshold_uncertainty_score":0.3836669,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105347536","doi":"10.1109/icdm.2006.62","title":"DSTree: A Tree Structure for the Mining of Frequent Sets from Data Streams","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":165,"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":"Data stream mining; Computer science; STREAMS; Data mining; Tree (set theory); Flood myth; Data stream; Tree structure; Data structure; Computer network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03155954862587509,"gpt":0.269129729241148,"spread":0.2375701806152729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001195992,0.00009825675,0.0001100055,0.00002650511,0.000124142,0.0001628495,0.001970128,0.00003742129,0.000005192855],"category_scores_gemma":[0.00004136396,0.00006861955,0.00002521344,0.0002094951,0.00004308062,0.0004269842,0.0004195703,0.00005949001,0.000001283864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001070911,"about_ca_system_score_gemma":0.00003062923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004533856,"about_ca_topic_score_gemma":0.00006692428,"domain_scores_codex":[0.9990915,0.000001548484,0.0001899941,0.0003833624,0.0001703289,0.000163245],"domain_scores_gemma":[0.999095,0.0001166786,0.0001443305,0.0005229378,0.0000927427,0.0000283205],"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":[0.00000505573,0.00007250151,0.002841814,0.0000306135,0.00004839216,4.299276e-7,0.000946856,0.000009957803,0.009650298,0.03655718,0.0752696,0.8745673],"study_design_scores_gemma":[0.0007921148,0.0000878819,0.0196215,0.00008814884,0.00009546349,0.000009952766,0.0006619014,0.8553546,0.01951103,0.03311687,0.07027428,0.0003862806],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4838086,0.001035301,0.496957,0.007087819,0.0004393926,0.001206832,0.006506623,0.0003570286,0.002601437],"genre_scores_gemma":[0.5953814,0.00000553923,0.4039893,0.00006690396,0.0001908134,0.00003614688,0.0002620738,0.000009360727,0.00005839984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.874181,"threshold_uncertainty_score":0.3661021,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1888464276","doi":"10.1109/icde.2000.839450","title":"Efficient mining of constrained correlated sets","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Set (abstract data type); Computer science; Meaning (existential); Data mining; Mathematics; Algorithm; Theoretical computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02343558730825698,"gpt":0.2382634183594904,"spread":0.2148278310512334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000769618,0.00004952822,0.00007243486,0.00004041793,0.00004344401,0.00002531925,0.0003350469,0.00002199434,0.0001416473],"category_scores_gemma":[0.00001693222,0.00004280731,0.0000211207,0.0002887263,0.0000425488,0.0000365711,0.00008391819,0.00003315933,0.00008148496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005082612,"about_ca_system_score_gemma":0.00000786254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008636453,"about_ca_topic_score_gemma":4.300445e-7,"domain_scores_codex":[0.9994792,0.00000832774,0.0001443283,0.0001572987,0.0001025857,0.0001083003],"domain_scores_gemma":[0.9995033,0.0000584744,0.0000493072,0.0003085596,0.00003715346,0.00004324965],"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":[0.00000111401,0.0005627247,0.000336418,0.00001482171,0.00004227452,0.00001393447,0.003646259,0.003016324,0.003450692,0.193167,0.0360729,0.7596755],"study_design_scores_gemma":[0.0001356919,0.00002074247,0.000209169,0.000007725932,0.000001930232,0.00001073569,0.00004271097,0.9980379,0.0004849439,0.00002832381,0.0009647234,0.00005537225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1387585,0.00005346678,0.8130062,0.001072061,0.0001556327,0.0001165079,0.00001596695,0.0002295888,0.04659211],"genre_scores_gemma":[0.7411985,0.000001402677,0.2581986,0.00006306231,0.00000423429,0.000003676652,0.000002032374,0.000002051325,0.0005264835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9950216,"threshold_uncertainty_score":0.1745631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027440536","doi":"10.1007/s10707-006-9827-8","title":"Mining Co-Location Patterns with Rare Events from Spatial Data Sets","year":2006,"lang":"en","type":"article","venue":"GeoInformatica","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Property (philosophy); Data mining; Geography; Scale (ratio); Spatial ecology; Feature (linguistics); Scalability; Computer science; Measure (data warehouse); Common spatial pattern; Spatial analysis; Cartography; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Remote sensing; Ecology; Database; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01955937255258091,"gpt":0.2537781371904637,"spread":0.2342187646378827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001378737,0.000122484,0.0001176729,0.00005022495,0.0001635086,0.0002136621,0.00136594,0.00003586995,0.00003420477],"category_scores_gemma":[0.00001050361,0.0001022779,0.00001227001,0.0001865964,0.00001925985,0.001551971,0.0003768973,0.00007305027,0.0002548497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001861886,"about_ca_system_score_gemma":0.00007402697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001511649,"about_ca_topic_score_gemma":0.0002178646,"domain_scores_codex":[0.9989009,0.00001352849,0.000293708,0.0002563928,0.0003091694,0.0002262856],"domain_scores_gemma":[0.9982384,0.00006159151,0.000149172,0.001435876,0.00005339473,0.00006158763],"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":[0.00001345264,0.0002512631,0.01774702,0.00009587676,0.0000768551,0.00001461409,0.003690538,0.0005677676,0.00002190392,0.00367872,0.04621836,0.9276236],"study_design_scores_gemma":[0.0005043377,0.00004282749,0.06796412,0.0000993516,0.00001604717,0.00001737934,0.0002127779,0.9153977,0.0001323248,0.0003838617,0.01496435,0.0002649307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04278797,0.00001050227,0.9537348,0.0004012289,0.00006853234,0.000168409,0.0005781022,0.0001479312,0.002102492],"genre_scores_gemma":[0.6569363,0.000002933298,0.3356886,0.0002512461,0.0001224405,0.0000378134,0.006846951,0.00001053006,0.0001031865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9273587,"threshold_uncertainty_score":0.4170771,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102589938","doi":"10.1109/icdm.2001.989600","title":"Fast parallel association rule mining without candidacy generation","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":154,"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":"Association rule learning; Computer science; Candidacy; Data mining; Process (computing); Parallel algorithm; Tree (set theory); Parallel computing; Mathematics; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03154291050930846,"gpt":0.246651509559753,"spread":0.2151085990504445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470892,0.00007183685,0.00007466791,0.00003786063,0.0001784697,0.000260493,0.0002450903,0.00003952159,0.0001058215],"category_scores_gemma":[0.0000272014,0.00006649844,0.00002274912,0.0001986156,0.000006022083,0.0004722478,0.00006993323,0.00004914106,0.0002722074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000683414,"about_ca_system_score_gemma":0.00001067582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008111332,"about_ca_topic_score_gemma":0.0000420004,"domain_scores_codex":[0.9992342,0.00001972799,0.0001406953,0.0002421321,0.0001905904,0.000172633],"domain_scores_gemma":[0.9994894,0.00002635289,0.00008132775,0.0002967469,0.00005043519,0.0000557356],"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":[5.741786e-7,0.0002197002,0.01619602,0.000004564059,0.00004707471,0.000004022623,0.003023932,0.0005878744,0.002148468,0.03842347,0.2884693,0.650875],"study_design_scores_gemma":[0.0001785856,0.00001431253,0.002128225,0.000002582241,0.00000373677,0.000003916146,0.00002330506,0.9806181,0.0002749832,0.0001008199,0.01653222,0.000119234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02302212,0.00004013018,0.95505,0.00263631,0.0001641001,0.00009332949,0.000006463567,0.0002179703,0.01876957],"genre_scores_gemma":[0.2587389,0.00003014286,0.7169735,0.0006794615,0.0003018285,0.00006158106,0.00003707056,0.000009031603,0.02316847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9800302,"threshold_uncertainty_score":0.3498766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063529879","doi":"10.1145/358108.358114","title":"Beyond intratransaction association analysis","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":153,"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":"Badan Riset dan Inovasi Nasional; Helsingin Yliopisto","keywords":"Association rule learning; Apriori algorithm; Database transaction; Computer science; Association (psychology); Transaction data; Affinity analysis; Data mining; Data science; Psychology; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.007761500766622136,"gpt":0.2255636195039939,"spread":0.2178021187373717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004454585,0.0001424168,0.000191683,0.0004509859,0.0003719051,0.0006408253,0.0006646636,0.0001217015,0.0002273978],"category_scores_gemma":[0.00001182621,0.0001424372,0.0001429549,0.001970882,0.00001136349,0.003628066,0.000003173706,0.0001860332,0.001462349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099493,"about_ca_system_score_gemma":0.00004036261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002036879,"about_ca_topic_score_gemma":0.00001378686,"domain_scores_codex":[0.9984878,0.00006256729,0.0005343498,0.0002028211,0.0004873721,0.0002250946],"domain_scores_gemma":[0.9985387,0.0001216601,0.0001849961,0.0009071411,0.0001525059,0.00009493841],"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":[0.000008188953,0.00008881724,0.00005967701,0.00001586168,0.0004304019,3.111282e-7,0.001348074,0.0784836,0.00001234927,0.003929523,0.001232119,0.9143911],"study_design_scores_gemma":[0.0008304841,0.0001387094,0.002892619,0.00002539555,0.0003900283,0.00001842097,0.0004611143,0.7025983,0.0005550621,0.00060145,0.2908849,0.0006035568],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001500734,0.0000105609,0.9880449,0.0008291939,0.0003739925,0.0002386372,0.0001551006,0.0003635152,0.008483386],"genre_scores_gemma":[0.9681417,0.00009958945,0.02851045,0.0005184757,0.00007197644,0.0003180427,0.0002330866,0.000009193347,0.002097438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966641,"threshold_uncertainty_score":0.9993151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2500377098","doi":"10.1137/1.9781611972740","title":"Proceedings of the 2004 SIAM International Conference on Data Mining","year":2004,"lang":"en","type":"paratext","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Library science; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.07677233096175941,"gpt":0.3190282780559112,"spread":0.2422559470941518,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001604106,0.0001742267,0.0001777196,0.00007513912,0.00008619999,0.0002898019,0.008103539,0.0001047842,0.0004175332],"category_scores_gemma":[0.00003222846,0.0001186838,0.00004098489,0.0002804839,0.00008174367,0.000391744,0.002131963,0.0002323,0.0006004465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004762177,"about_ca_system_score_gemma":0.0003426857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007335306,"about_ca_topic_score_gemma":0.000005113706,"domain_scores_codex":[0.9984959,0.00000420788,0.0002772921,0.0006345861,0.0004277703,0.000160181],"domain_scores_gemma":[0.9983116,0.00002927318,0.0002935675,0.001116487,0.000206,0.0000430346],"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":[9.268548e-7,0.00006804158,0.000003007262,0.00002133856,0.00002795205,1.89376e-7,0.0001438441,0.00001584047,0.00007717126,0.1031885,0.8791119,0.01734125],"study_design_scores_gemma":[0.0004287301,0.00007749716,0.0001157603,0.001039728,0.00002027512,0.00002153347,0.000191233,0.09116381,0.001417003,0.001339554,0.9036609,0.0005240029],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00007328841,0.00005769555,0.05904832,0.005206782,0.001995253,0.0002806371,0.0009850545,0.00005442376,0.9322985],"genre_scores_gemma":[0.009056454,0.0002848044,0.4128012,0.00129552,0.0009178858,0.00009682361,0.001338152,0.00004719369,0.574162],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3581366,"threshold_uncertainty_score":0.9972631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032469362","doi":"10.1007/s10115-006-0032-8","title":"CanTree: a canonical-order tree for incremental frequent-pattern mining","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Tree (set theory); GSP Algorithm; Database transaction; Tree structure; A priori and a posteriori; Association rule learning; Apriori algorithm; Database; Mathematics; Algorithm; Binary tree","retraction":null,"screen_n_in":null,"score":{"opus":0.01329467542214002,"gpt":0.2450617536862699,"spread":0.2317670782641299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002289257,0.0001017177,0.0001268355,0.00009636548,0.0001920595,0.0003639731,0.0002646018,0.00004684648,0.000002124256],"category_scores_gemma":[0.00001319359,0.0000911038,0.00002537921,0.0002130593,0.00002064592,0.001855865,0.00009218301,0.00003752891,0.00005495962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004409355,"about_ca_system_score_gemma":0.00008177441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008626219,"about_ca_topic_score_gemma":0.0002328012,"domain_scores_codex":[0.9991714,0.00001540575,0.0003846003,0.0001368479,0.000108579,0.0001831038],"domain_scores_gemma":[0.9993578,0.00005801074,0.0001303031,0.0002377715,0.0001589832,0.00005708275],"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":[0.000004244461,0.0001015958,0.002701929,0.0002825884,0.00003966493,6.97018e-7,0.003894152,0.0000601961,0.0002606819,0.1270139,0.09229397,0.7733464],"study_design_scores_gemma":[0.0007268995,0.00005013138,0.001974117,0.00005602384,0.000007778801,0.00002173418,0.0003484063,0.4438933,0.0001436961,0.00004010799,0.5525398,0.0001980751],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01007841,0.0005016748,0.9589057,0.0002564671,0.0004609165,0.0005374212,0.0001284529,0.0001396263,0.02899131],"genre_scores_gemma":[0.9777804,0.00001669211,0.0198578,0.0001914855,0.0003567098,0.0004578465,0.0003961672,0.000009487901,0.0009334019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.967702,"threshold_uncertainty_score":0.3715105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1482810056","doi":"10.1007/3-540-47887-6_34","title":"Top Down FP-Growth for Association Rule Mining","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Association rule learning; Pruning; Computer science; Tree (set theory); Data mining; Space (punctuation); Depth-first search; Order (exchange); Algorithm; Search algorithm; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01755477054816567,"gpt":0.2447510518977258,"spread":0.2271962813495601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007667316,0.000366164,0.0003913358,0.0004562043,0.0003714992,0.0007809184,0.002292543,0.0002994626,0.00002003079],"category_scores_gemma":[0.0002271915,0.0003581361,0.0001252762,0.000525913,0.0001525912,0.0006000318,0.0007365308,0.0003923169,0.00005687326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004449739,"about_ca_system_score_gemma":0.0002240967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001803681,"about_ca_topic_score_gemma":0.00001418685,"domain_scores_codex":[0.9968591,0.00001479692,0.0004410359,0.001326167,0.0007355821,0.0006232938],"domain_scores_gemma":[0.9973328,0.0007885052,0.000382621,0.00101023,0.0003512011,0.0001346228],"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":[0.000001155119,0.00003443412,0.0001063215,0.00002746942,0.00001520555,0.000009161165,0.000622351,0.00095005,0.00004299758,0.02843718,0.001127231,0.9686264],"study_design_scores_gemma":[0.000338809,0.0001325071,0.0001242127,0.0002083406,0.00001566141,0.00002453545,3.080924e-7,0.8761788,0.0007835604,0.101745,0.01971359,0.0007346921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003822437,0.0001429482,0.9924091,0.001919097,0.001085182,0.0003908481,0.0000455803,0.0001709195,0.003798153],"genre_scores_gemma":[0.003774178,0.00004328152,0.9916406,0.001258369,0.0007530901,0.00005640538,0.00002938679,0.0000315725,0.002413131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9678918,"threshold_uncertainty_score":0.999887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078064242","doi":"10.1023/b:dami.0000023674.74932.4c","title":"Pushing Convertible Constraints in Frequent Itemset Mining","year":2004,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Constraint (computer-aided design); Computer science; Data mining; Context (archaeology); Association rule learning; Convertible; A priori and a posteriori; Class (philosophy); Apriori algorithm; Monotonic function; Sequential Pattern Mining; Artificial intelligence; Mathematics; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04812423122534112,"gpt":0.2999252304469889,"spread":0.2518009992216478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001483,0.0001914476,0.0002338912,0.0001679469,0.0001771475,0.0006596675,0.001370053,0.00006857543,0.000004163047],"category_scores_gemma":[0.0001429205,0.0001880572,0.00002301893,0.0004436754,0.0001719618,0.00269697,0.001249589,0.0001384632,0.00002968026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005041645,"about_ca_system_score_gemma":0.000260768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002048042,"about_ca_topic_score_gemma":0.0003767018,"domain_scores_codex":[0.9982846,0.00003998034,0.0003458346,0.0008089613,0.0001416738,0.0003789382],"domain_scores_gemma":[0.9983996,0.0001751121,0.00008984292,0.001186813,0.00002910577,0.0001195762],"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":[0.00001281319,0.0007398567,0.01328415,0.0001588532,0.00008887381,0.0001694409,0.02157012,0.00005724798,0.001587273,0.06512616,0.01079294,0.8864123],"study_design_scores_gemma":[0.02278739,0.001062106,0.0779665,0.009119489,0.0002618,0.001482431,0.04504868,0.6490068,0.006962256,0.01190998,0.1658763,0.00851623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6607854,0.002747791,0.3247079,0.00125736,0.0009149932,0.0003636606,0.001520706,0.0002810382,0.007421197],"genre_scores_gemma":[0.8722166,0.0001121527,0.1262277,0.0001939572,0.0001175479,0.00002989845,0.0008815663,0.00001869716,0.0002018365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.877896,"threshold_uncertainty_score":0.7668749,"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":"W2066881707","doi":"10.1016/j.fss.2004.09.014","title":"Genetic algorithm based framework for mining fuzzy association rules","year":2004,"lang":"en","type":"article","venue":"Fuzzy Sets and Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Association rule learning; Data mining; Cluster analysis; Apriori algorithm; Fuzzy logic; Fuzzy clustering; Centroid; Computer science; Fuzzy set; Membership function; Mathematics; Fuzzy classification; Defuzzification; Fuzzy set operations; Midpoint; Algorithm; Artificial intelligence; Fuzzy number","retraction":null,"screen_n_in":null,"score":{"opus":0.02101407464046413,"gpt":0.2648853785248908,"spread":0.2438713038844267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003758098,0.0001287138,0.0001859507,0.00006319172,0.0002648887,0.0004690793,0.0003291845,0.0001190457,6.835118e-7],"category_scores_gemma":[0.00007252519,0.0001182959,0.00004545382,0.0001670708,0.0000147148,0.0001772745,0.00005762926,0.00007551692,0.00001912815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000804346,"about_ca_system_score_gemma":0.00006570588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009456553,"about_ca_topic_score_gemma":0.00000265331,"domain_scores_codex":[0.9988362,0.00003086764,0.0002558862,0.0003712024,0.000227743,0.000278085],"domain_scores_gemma":[0.9990239,0.0002412317,0.0001694877,0.0003674885,0.00009461342,0.0001032474],"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":[0.000004652256,0.0002289969,0.002212474,0.0002237397,0.0001239444,0.00001379487,0.002351976,0.002607107,0.0001027541,0.2652799,0.008249524,0.7186011],"study_design_scores_gemma":[0.00168097,0.0002918801,0.01470288,0.0004470787,0.00005236532,0.00003367157,0.0004245103,0.8733344,0.00008106945,0.05908158,0.04909187,0.0007776875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008877703,0.0005025041,0.988221,0.0008271486,0.0005941869,0.0003605222,0.000210673,0.0001232661,0.0002829192],"genre_scores_gemma":[0.04897517,0.00001699114,0.9501262,0.0001913578,0.0003068063,0.0002071614,0.00005185769,0.0000146098,0.000109886],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8707273,"threshold_uncertainty_score":0.4823968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1514516794","doi":"","title":"Mining Frequent Itemsets Using Support Constraints","year":2000,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03351622836162168,"gpt":0.2488833181669882,"spread":0.2153670898053665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001358748,0.00005439329,0.00007342546,0.00007368733,0.0001852774,0.00002429051,0.0003927055,0.00003618549,0.0005411279],"category_scores_gemma":[0.00001210376,0.00006917723,0.00003060255,0.0002528623,0.0001318912,0.0003434077,0.00005526046,0.00004905674,0.00002968914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006148295,"about_ca_system_score_gemma":0.0002044304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004961444,"about_ca_topic_score_gemma":0.000002509682,"domain_scores_codex":[0.9993523,0.00001188267,0.00008830265,0.0001793945,0.0002708338,0.00009726802],"domain_scores_gemma":[0.9995382,0.00003786437,0.00006641151,0.0001281715,0.0001788515,0.0000504788],"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":[0.00001096116,0.0004680767,0.00319554,0.00003172115,0.000126675,0.0001150148,0.005515613,0.003214306,0.003964598,0.1275136,0.02423972,0.8316042],"study_design_scores_gemma":[0.003285398,0.0002160086,0.0362776,0.0002765236,0.00008312835,0.0005657903,0.002945247,0.5886593,0.002837295,0.004927267,0.3585543,0.001372156],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7214713,0.00001707022,0.233877,0.001247463,0.00009478763,0.0001409641,0.0002285482,0.000142639,0.04278023],"genre_scores_gemma":[0.7072337,0.000005364237,0.2918874,0.00009266677,0.00002299399,5.684837e-8,0.00006994671,0.00000325213,0.0006846187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8302321,"threshold_uncertainty_score":0.5924972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116064560","doi":"10.1007/s10618-005-0248-3","title":"Mining Web Log Sequential Patterns with Position Coded Pre-Order Linked WAP-Tree","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Web log analysis software; Tree (set theory); Trie; Suffix tree; Prefix; Data mining; Subsequence; Web mining; Node (physics); Web server; Fractal tree index; Tree structure; Interval tree; Web page; Data structure; Algorithm; The Internet; World Wide Web; Mathematics; Binary tree; Static web page","retraction":null,"screen_n_in":null,"score":{"opus":0.03043223887843423,"gpt":0.2874098398765441,"spread":0.2569776009981099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003406552,0.0002604002,0.0002431552,0.0001230886,0.0003168859,0.0008432153,0.001295133,0.0000883836,0.000009813011],"category_scores_gemma":[0.00003725662,0.0002239381,0.00002724366,0.000357004,0.0000983629,0.003001302,0.001188678,0.0001490298,0.00002972633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003402542,"about_ca_system_score_gemma":0.0002203737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004975872,"about_ca_topic_score_gemma":0.0007672216,"domain_scores_codex":[0.9980757,0.00006218169,0.0003167343,0.000944461,0.0002104576,0.0003905236],"domain_scores_gemma":[0.9980248,0.0001350154,0.0001385972,0.001477529,0.00008695341,0.0001370948],"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":[0.00005507024,0.0005616664,0.004878875,0.00009738216,0.0001613494,0.00003221812,0.006641196,0.00004137515,0.001596616,0.002412306,0.02143318,0.9620888],"study_design_scores_gemma":[0.002190587,0.0003287783,0.009117535,0.0005781777,0.0001488616,0.0002016608,0.001128793,0.9432654,0.0007557073,0.00004555566,0.0411676,0.001071324],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4851626,0.0005469155,0.508792,0.001024375,0.0002717532,0.0002528855,0.001577493,0.0002613068,0.00211061],"genre_scores_gemma":[0.7526994,0.0001209411,0.2399664,0.0002451001,0.0006603774,0.00006011726,0.004183121,0.00003889328,0.002025724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9610174,"threshold_uncertainty_score":0.913193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131225292","doi":"10.1109/ride.1997.583715","title":"Generalization and decision tree induction: efficient classification in data mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Decision tree; Data mining; Abstraction; Generalization; Relevance (law); Machine learning; Artificial intelligence; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1137594219951989,"gpt":0.2990887928556513,"spread":0.1853293708604524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002062974,0.00005713488,0.00005608875,0.0001039413,0.00008246272,0.0001422995,0.0005089474,0.00003246203,0.00001746894],"category_scores_gemma":[0.00003193632,0.00005192681,0.000004817027,0.0004909181,0.00001807927,0.0004300975,0.0002790472,0.00003911784,0.0000218207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707767,"about_ca_system_score_gemma":0.000006356934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002096365,"about_ca_topic_score_gemma":0.00004440214,"domain_scores_codex":[0.9991951,0.0000140791,0.0001669093,0.0003975318,0.0001309325,0.0000954487],"domain_scores_gemma":[0.9990836,0.00004475989,0.00004206031,0.0007682816,0.00002331762,0.00003797616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.672208e-7,0.00004641241,0.0002665451,9.92869e-7,8.461159e-7,4.519611e-7,0.000203926,0.0001678621,0.000170128,0.00936118,0.004710427,0.9850709],"study_design_scores_gemma":[0.0001425187,0.000006978693,0.0111857,0.000008274734,0.000001244963,0.000007580329,0.00004875894,0.9835901,0.00002811622,0.0001634211,0.004751231,0.00006610891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08001295,0.00009872755,0.9170102,0.00108182,0.000091642,0.00007956991,0.00000420187,0.00006328395,0.001557638],"genre_scores_gemma":[0.2965929,0.00008148015,0.7028828,0.0001010703,0.00005173019,0.00001421522,0.00005465528,0.000004525821,0.0002167025],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9850048,"threshold_uncertainty_score":0.2117514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970828623","doi":"10.14778/3342263.3342645","title":"Efficient algorithms for densest subgraph discovery","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Induced subgraph isomorphism problem; Intuition; Computer science; Subgraph isomorphism problem; Graph; Algorithm; Color-coding; Efficient algorithm; Theoretical computer science; Artificial intelligence; Line graph","retraction":null,"screen_n_in":null,"score":{"opus":0.01307049411882908,"gpt":0.2375503892464292,"spread":0.2244798951276001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002558508,0.0001201804,0.0001464833,0.00005796587,0.0001106982,0.0001638606,0.001266123,0.00002853155,0.000002470348],"category_scores_gemma":[0.00002714729,0.00008098593,0.0001265006,0.0003459824,0.00004304125,0.0001957762,0.0004372188,0.00006559136,0.00001470716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003672066,"about_ca_system_score_gemma":0.00002880273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002165705,"about_ca_topic_score_gemma":4.30241e-7,"domain_scores_codex":[0.9988986,0.00000206414,0.0002182576,0.0003518796,0.0002872511,0.0002418988],"domain_scores_gemma":[0.9992806,0.00005470656,0.0001805778,0.0003013,0.0001376661,0.00004518603],"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":[0.00002552519,0.0007830472,0.004875159,0.0002989809,0.0001269396,2.279367e-7,0.00154999,0.000533874,0.0851652,0.8348223,0.01042683,0.06139191],"study_design_scores_gemma":[0.002906623,0.0006408296,0.01424708,0.0003904539,0.0001027835,0.00004434141,0.0007752433,0.5267554,0.3926595,0.01994577,0.04054733,0.0009846651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8442253,0.0002037985,0.1422397,0.004165852,0.001301415,0.002864289,0.0001296975,0.000196548,0.004673449],"genre_scores_gemma":[0.8976334,0.00001020788,0.1006229,0.0001706586,0.00006740246,0.0002434801,0.000002723724,0.00001392484,0.001235227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8148766,"threshold_uncertainty_score":0.3302511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115866740","doi":"10.1145/1008694.1008705","title":"An associative classifier based on positive and negative rules","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":106,"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":"Associative property; Association rule learning; Classifier (UML); Computer science; Negation; Artificial intelligence; Correlation; Data mining; Machine learning; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01325472196489189,"gpt":0.2646293309659183,"spread":0.2513746090010264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009816969,0.00007774783,0.00007359567,0.00003935162,0.000143837,0.0001529262,0.0002427005,0.00003156762,0.00000820429],"category_scores_gemma":[0.0000229324,0.00006359431,0.00001532264,0.0001266337,0.00004488799,0.0002845209,0.00004398357,0.00007182732,0.00004272775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004807692,"about_ca_system_score_gemma":0.00004957837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001196587,"about_ca_topic_score_gemma":0.00002275131,"domain_scores_codex":[0.9993702,0.00002926612,0.00007096758,0.0002847168,0.0001239465,0.0001209425],"domain_scores_gemma":[0.9994546,0.0001289809,0.00003929135,0.0002459851,0.00005347028,0.00007765576],"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":[0.000005988781,0.0004230147,0.0002654825,0.000001697679,0.00002328729,0.000007724149,0.002568359,0.0001858468,0.0003169915,0.8369077,0.0005900741,0.1587038],"study_design_scores_gemma":[0.001492156,0.0008664716,0.1756024,0.0000497144,0.00001182628,0.00000349347,0.0005278521,0.7327108,0.01043088,0.07701024,0.0008135018,0.0004805633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02052654,0.000003809784,0.9447018,0.004075971,0.00003588845,0.0001355593,0.00008334589,0.0001384155,0.03029868],"genre_scores_gemma":[0.5665728,0.000001711889,0.4313653,0.001818856,0.00002339129,0.00001963532,0.0000190379,0.000004829787,0.0001744753],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7598975,"threshold_uncertainty_score":0.2593301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W170258093","doi":"","title":"A Unified Framework for Utility Based Measures for Mining Itemsets","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Data mining; Computer science; Process (computing); Function (biology)","retraction":null,"screen_n_in":null,"score":{"opus":0.05371318287178579,"gpt":0.3005510801555023,"spread":0.2468378972837165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003591888,0.00009070395,0.0001073663,0.00004055599,0.0001928669,0.0001640496,0.0005267109,0.00005897382,0.000006183509],"category_scores_gemma":[0.0001290892,0.00008078426,0.00006676403,0.0002009225,0.0000226024,0.0001460478,0.00004459799,0.00003810575,0.000003406983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001158957,"about_ca_system_score_gemma":0.00006288359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000617903,"about_ca_topic_score_gemma":0.00002682324,"domain_scores_codex":[0.9991215,0.00001149811,0.0001780507,0.0003476033,0.0001174342,0.0002239395],"domain_scores_gemma":[0.998648,0.000606704,0.0000557164,0.0005302659,0.000113203,0.00004604327],"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":[0.00001031526,0.000149585,0.0003060207,0.00002568406,0.000009172567,2.734982e-7,0.00006523746,0.00005706623,0.0001728416,0.742557,0.03871321,0.2179336],"study_design_scores_gemma":[0.000314471,0.00004501854,0.001130188,0.00001468332,0.000006324519,5.216676e-7,0.00001972726,0.8161157,0.002015408,0.0659022,0.1142875,0.0001483104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006756244,0.00002289346,0.9957952,0.001688526,0.0001072651,0.0003999648,0.00008554673,0.000199716,0.001025219],"genre_scores_gemma":[0.1360815,1.786689e-7,0.8628694,0.0003288686,0.00009137891,0.0003020392,0.00004718814,0.000006549925,0.0002728363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8160586,"threshold_uncertainty_score":0.3294286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}