{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":68,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":68,"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":"a9f6a182b581","filters":{"venue":"Information Processing & Management"}},"results":[{"id":"W2170505850","doi":"10.1016/j.ipm.2009.03.002","title":"A systematic analysis of performance measures for classification tasks","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6477,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Children's Hospital of Eastern Ontario","funders":"McGill University","keywords":"Confusion matrix; Confusion; Computer science; Artificial intelligence; Classifier (UML); Measure (data warehouse); Binary classification; Machine learning; Binary number; Natural language processing; Set (abstract data type); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics; Support vector machine; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.02272805573408605,"gpt":0.2683619694755179,"spread":0.2456339137414319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005199111,0.0001059729,0.0002267584,0.00090179,0.0001382695,0.000278447,0.0006544032,0.0000446479,0.000001574917],"category_scores_gemma":[0.00005272912,0.00009086225,0.00008432471,0.001556263,0.00002355796,0.002518761,0.00004344318,0.00003703653,0.000009626126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006142181,"about_ca_system_score_gemma":0.00002069184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.345231e-7,"about_ca_topic_score_gemma":2.244121e-7,"domain_scores_codex":[0.9986649,0.00001372859,0.0006673835,0.0001404787,0.0003664799,0.0001470203],"domain_scores_gemma":[0.9986134,0.00002567492,0.0006158617,0.0004597011,0.0002630583,0.00002225739],"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":[0.000007650897,0.00004420116,0.00005411914,0.003947658,0.0001726364,4.809408e-8,0.0008975135,0.000870404,0.00006555935,0.2056251,0.0001892062,0.7881259],"study_design_scores_gemma":[0.0004045221,0.00009616658,0.02155467,0.0007110161,0.0005237047,6.181966e-7,0.0008964241,0.966887,0.001240324,0.003864699,0.003575963,0.0002449008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001074945,0.00007709054,0.9930567,0.0007474971,0.0000471955,0.0006256838,0.000001587601,0.0003392645,0.004030053],"genre_scores_gemma":[0.9708304,0.00003119811,0.02864741,0.0001895291,0.000003095157,0.0001674918,0.00002337171,0.000001756143,0.0001057534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9697555,"threshold_uncertainty_score":0.3705255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2925285378","doi":"10.1016/j.ipm.2019.03.004","title":"An overview of online fake news: Characterization, detection, and discussion","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":1000,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"Mainstream; Social media; Internet privacy; Computer science; Point (geometry); Fake news; Public relations; World Wide Web; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.02587419064493992,"gpt":0.3263129100200856,"spread":0.3004387193751457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000355471,0.00007802058,0.00009944623,0.0001882304,0.0002213515,0.000235582,0.0001165112,0.00004584948,0.0001603259],"category_scores_gemma":[0.0000273238,0.00005871551,0.00001714963,0.0003501746,0.000041083,0.005384791,0.00003019164,0.00004403983,0.00004169567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003991949,"about_ca_system_score_gemma":0.00004862167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004366818,"about_ca_topic_score_gemma":0.00004247993,"domain_scores_codex":[0.9990169,0.00003503561,0.0003836933,0.00006862415,0.0003618984,0.0001338212],"domain_scores_gemma":[0.999307,0.000004740487,0.0003254873,0.000124637,0.0001589627,0.00007912167],"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":[0.00001075168,0.00002998805,0.0003851811,0.0003993174,0.000005390924,3.454852e-8,0.0278649,0.00003638699,0.0001575532,0.003967707,0.00003539571,0.9671074],"study_design_scores_gemma":[0.001265377,0.000122232,0.2619046,0.0005692989,0.00004098511,0.000001595737,0.09523179,0.01274609,0.0004180969,0.0009514499,0.626322,0.0004264548],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9218004,0.0000917679,0.02767009,0.002612092,0.0004491979,0.001319222,0.00002939266,0.0002803439,0.04574746],"genre_scores_gemma":[0.9971997,0.0004607894,0.000494336,0.0008755908,0.00002870993,0.000003122032,0.0001169841,0.000004172119,0.0008166179],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9666809,"threshold_uncertainty_score":0.3903843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120308175","doi":"10.1016/s0306-4573(00)00010-8","title":"Variations in relevance judgments and the measurement of retrieval effectiveness","year":2000,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":507,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Standards and Technology; University of Waterloo","keywords":"Relevance (law); Information retrieval; Computer science; NIST; Set (abstract data type); Test (biology); Reliability (semiconductor); Ranking (information retrieval); Document retrieval; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01358723951661481,"gpt":0.2439882889508641,"spread":0.2304010494342493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00199057,0.00008392227,0.0001160483,0.0001653482,0.0001457898,0.000206068,0.0003235911,0.00002546214,0.0000133807],"category_scores_gemma":[0.00004456936,0.00006034298,0.0000235819,0.0006434642,0.00006261068,0.002566693,0.00008957271,0.0000846864,0.00002511167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008561881,"about_ca_system_score_gemma":0.00003984557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001280902,"about_ca_topic_score_gemma":8.647815e-7,"domain_scores_codex":[0.9985726,0.00006599332,0.0004479587,0.00008881446,0.0006757324,0.0001488787],"domain_scores_gemma":[0.9993935,0.00004314186,0.0001507864,0.000197595,0.0001879249,0.00002701394],"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":[0.0002497541,0.00004325721,0.0001271454,0.0004117633,0.00001400212,6.594875e-7,0.003933338,0.001294436,0.000008894204,0.05458475,0.00002766542,0.9393044],"study_design_scores_gemma":[0.01657975,0.0001760072,0.3156985,0.001269776,0.00007263148,0.00001279841,0.0007474276,0.60887,0.002999929,0.02566536,0.02719804,0.00070978],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599037,0.0002850297,0.7581871,0.002069337,0.0003038634,0.003407024,0.0000061407,0.0002297762,0.07560806],"genre_scores_gemma":[0.9965052,0.00007435706,0.00309956,0.000213182,0.00000375737,0.00004319032,0.000002786375,0.000001877711,0.00005607223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9385946,"threshold_uncertainty_score":0.2460715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2919877138","doi":"10.1016/j.ipm.2019.02.016","title":"Detecting breaking news rumors of emerging topics in social media","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":255,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Concordia University","funders":"Natural Science Foundation of Zhejiang Province; Natural Sciences and Engineering Research Council of Canada; Saudi Arabian Cultural Mission; Canada Excellence Research Chairs, Government of Canada; King Saud University; National Natural Science Foundation of China; Canada Research Chairs; National Science Foundation","keywords":"Rumor; Computer science; Social media; Fake news; Focus (optics); Task (project management); Statement (logic); Recall; Computer security; Artificial intelligence; Internet privacy; Psychology; Cognitive psychology; World Wide Web; Political science; Public relations; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02033234344826333,"gpt":0.3055574141943943,"spread":0.285225070746131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000832519,0.00007693651,0.0001202709,0.0003520616,0.0002428345,0.0001703514,0.0001708037,0.00005360961,0.0001796351],"category_scores_gemma":[0.0001416537,0.00008025179,0.00003159788,0.0005816293,0.00003651352,0.002700845,0.00005306512,0.00008891088,0.000061084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001255385,"about_ca_system_score_gemma":0.00006515541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001243123,"about_ca_topic_score_gemma":0.0001434244,"domain_scores_codex":[0.9986628,0.00003278548,0.0005123092,0.00006099111,0.0004837843,0.0002473559],"domain_scores_gemma":[0.9994014,0.00002559666,0.0003735798,0.00007379613,0.00008669636,0.00003891894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000006529227,0.00000725255,0.0006037856,0.0002289283,0.000003846828,1.914696e-7,0.2042244,0.0002358761,0.000002009049,0.01103103,0.0001737829,0.7834823],"study_design_scores_gemma":[0.001739099,0.00001956866,0.04004211,0.00058094,0.00002287002,0.000001036279,0.6319551,0.006659307,0.0001888948,0.002991166,0.3153014,0.0004984672],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4514833,0.00001930899,0.002053241,0.0009022397,0.0003795683,0.0003964611,0.000001295044,0.00009991093,0.5446646],"genre_scores_gemma":[0.998473,0.00001822267,0.0007990707,0.0003562316,0.00006736934,0.000002805494,0.00000744995,0.000003658691,0.0002721355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7829838,"threshold_uncertainty_score":0.3272573,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1966791154","doi":"10.1016/s0306-4573(01)00034-6","title":"Gender differences in collaborative Web searching behavior: an elementary school study","year":2002,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":205,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Hypertext; Class (philosophy); Psychology; Mathematics education; Web page; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07561169604868281,"gpt":0.3645816513261622,"spread":0.2889699552774794,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003464553,0.0001402459,0.00012787,0.0002865915,0.0002227629,0.0003475525,0.0002452151,0.00003694579,0.001759724],"category_scores_gemma":[0.000008049346,0.0001273267,0.00001609698,0.0004138466,0.00003903274,0.00168731,0.00006660046,0.0001535262,0.0003137476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001161052,"about_ca_system_score_gemma":0.00003130877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001158056,"about_ca_topic_score_gemma":0.00006583846,"domain_scores_codex":[0.9986861,0.000107343,0.0004488736,0.0001796508,0.0003122283,0.0002658508],"domain_scores_gemma":[0.9994866,0.00001778487,0.0001605893,0.0001894305,0.00008387418,0.00006178447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005950032,0.00212332,0.6627829,0.000200283,0.0001095203,0.00003143426,0.09418092,0.0001591983,0.000003121415,0.004564424,0.005843195,0.2299422],"study_design_scores_gemma":[0.0006292021,0.0001224577,0.7675004,0.00001909657,0.00002092246,0.000002035105,0.2283457,0.0004847514,6.674948e-7,0.0002613104,0.002463121,0.0001503829],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.911158,0.0001358522,0.00008538924,0.0001885376,0.0002159587,0.0008024375,0.000006755025,0.00008145328,0.08732565],"genre_scores_gemma":[0.9977338,0.00002390256,0.0006613095,0.0003233786,0.0000366832,0.0005653721,0.0000367565,0.00000631613,0.0006125208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2297918,"threshold_uncertainty_score":0.9991528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2953722276","doi":"10.1016/j.ipm.2019.102063","title":"A multi-centrality index for graph-based keyword extraction","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Centrality; Betweenness centrality; PageRank; Computer science; Clustering coefficient; Cluster analysis; Graph; Artificial intelligence; Data mining; Natural language processing; Information retrieval; Theoretical computer science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01397295543473869,"gpt":0.2989504196007305,"spread":0.2849774641659918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003660819,0.0001375734,0.0001294557,0.0003616163,0.0001403117,0.0003951232,0.0004776535,0.00004876306,0.000008091645],"category_scores_gemma":[0.00001367955,0.0001347611,0.0000826362,0.0005614907,0.0000172716,0.004635443,0.00008658486,0.00007922481,0.00005093828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144923,"about_ca_system_score_gemma":0.00003104425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005427016,"about_ca_topic_score_gemma":0.000002081643,"domain_scores_codex":[0.9988089,0.00001515004,0.0004047324,0.0002085057,0.0003219728,0.0002407078],"domain_scores_gemma":[0.9989888,0.00001918225,0.0003598099,0.0003994864,0.0001891275,0.00004356863],"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":[0.00002568861,0.0001182913,0.001095972,0.0006030032,0.00002926549,5.37352e-7,0.0003496749,0.009555063,0.0000794947,0.009800004,0.0004027241,0.9779403],"study_design_scores_gemma":[0.001078959,0.00003381771,0.007995318,0.00008780326,0.00001919952,7.755364e-7,0.0000922242,0.9403892,0.001364928,0.005125605,0.04354413,0.0002680633],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001378752,0.00001598634,0.9954499,0.0002982869,0.0001115375,0.0007560275,0.00000124272,0.0005685277,0.001419768],"genre_scores_gemma":[0.5957311,0.000003641267,0.4033107,0.0006041412,0.000006837212,0.0001370085,0.00002099374,0.000004647972,0.0001810093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776722,"threshold_uncertainty_score":0.5495397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991377870","doi":"10.1016/j.ipm.2015.03.003","title":"An empirical evaluation of the User Engagement Scale (UES) in online news environments","year":2015,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Knowledge Management and Sharing","field":"Social Sciences","cited_by":84,"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":"Computer science; Reliability (semiconductor); Scale (ratio); Psychology; Robustness (evolution); Measure (data warehouse); Validity; Face validity; Information retrieval; Applied psychology; Psychometrics; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1066429178151116,"gpt":0.3917724897839717,"spread":0.2851295719688601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003622398,0.00009638321,0.0001007232,0.0001965841,0.000230958,0.0001629077,0.0004227232,0.0000450353,0.00005637299],"category_scores_gemma":[0.00008137007,0.00008000089,0.00003093216,0.0004886325,0.00008137267,0.001985963,0.0001824887,0.00009817927,0.00003882236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003863157,"about_ca_system_score_gemma":0.0001096142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000139167,"about_ca_topic_score_gemma":0.0008389498,"domain_scores_codex":[0.9976196,0.0003076727,0.0004375695,0.0001261925,0.001300952,0.0002080709],"domain_scores_gemma":[0.9993436,0.000008819969,0.0002337023,0.0002343848,0.0001128085,0.00006662793],"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":[0.00002561363,0.0004428982,0.09988396,0.0001191525,0.0000272378,3.617545e-7,0.08583353,0.01088999,0.000005112166,0.001603418,0.00208331,0.7990854],"study_design_scores_gemma":[0.002805474,0.00004865192,0.3754066,0.0002324381,0.0001959736,1.35115e-7,0.1365459,0.06667534,0.00008313584,0.003768289,0.413862,0.0003760908],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.796141,0.00008049823,0.004255496,0.001545812,0.0004623434,0.001692616,0.00000289116,0.00007032772,0.195749],"genre_scores_gemma":[0.9977477,0.00001846004,0.001015355,0.000351747,0.00005041356,0.00005575299,0.00002655931,0.000005312629,0.0007286617],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7987093,"threshold_uncertainty_score":0.3262341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015603385","doi":"10.1016/j.ipm.2003.10.001","title":"A modeling approach to uncover hyperlink patterns: the case of Canadian universities","year":2003,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Web visibility and informetrics","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Hyperlink; Quality (philosophy); Link analysis; World Wide Web; Regression analysis; Geography; Computer science; Web page; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02199722242827473,"gpt":0.2202162180540746,"spread":0.1982189956257999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005385641,0.00008491486,0.00007533182,0.0008973971,0.0002582616,0.0003091389,0.0004309598,0.00002917393,0.000004144367],"category_scores_gemma":[0.00001882271,0.00006744701,0.00002850776,0.001566742,0.00001458828,0.002689769,0.00009809659,0.000068414,0.00001622503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001529487,"about_ca_system_score_gemma":0.0001857271,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008021923,"about_ca_topic_score_gemma":0.0007738003,"domain_scores_codex":[0.9992157,0.00001924077,0.0002794263,0.00009679929,0.0001939811,0.0001948129],"domain_scores_gemma":[0.9993584,0.00001016342,0.00007602056,0.0003131066,0.0001612043,0.00008112945],"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":[0.000003330135,0.00002837421,0.00003665049,0.0005141904,0.00002551681,0.00001343801,0.01629123,0.3288714,1.73482e-7,0.414327,0.0004793011,0.2394094],"study_design_scores_gemma":[0.0002008433,0.00001974285,0.0000661703,0.00004008928,0.00001123674,0.00005080846,0.01839322,0.9588609,0.00003078334,0.0008242413,0.0213526,0.0001493221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02162821,0.00001810648,0.8442825,0.0001676484,0.00006930732,0.0002332936,0.000003053841,0.00003379008,0.1335641],"genre_scores_gemma":[0.9673971,0.000006475561,0.03111771,0.00134314,0.000004316089,0.000009128006,0.00000351555,0.000002152539,0.0001164906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9457688,"threshold_uncertainty_score":0.9985837,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2973078541","doi":"10.1016/j.ipm.2019.102111","title":"Immigrating after 60: Information experiences of older Chinese migrants to Australia and Canada","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Technology Use by Older Adults","field":"Social Sciences","cited_by":67,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"University of South Australia","keywords":"Immigration; Family reunification; Population; Qualitative research; Coping (psychology); Sociology; Settlement (finance); Gender studies; Geography; Psychology; Demography; Social science; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.00468570842820317,"gpt":0.2541924854414541,"spread":0.2495067770132509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002633551,0.0001080954,0.0001203378,0.0002146041,0.0001661473,0.0001581133,0.0001981224,0.00005608132,0.00007625456],"category_scores_gemma":[0.00005174178,0.00009771432,0.00001497732,0.0003817711,0.00006454499,0.003262795,0.00008111115,0.00006164524,0.0000366111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008848459,"about_ca_system_score_gemma":0.00009941585,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1222679,"about_ca_topic_score_gemma":0.1384538,"domain_scores_codex":[0.9987923,0.0000160216,0.0004106552,0.00008646647,0.0004685524,0.0002260181],"domain_scores_gemma":[0.9994321,0.00001186033,0.0002309061,0.0001237611,0.0001379138,0.00006343835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00004416633,0.000019844,0.06043161,0.001039991,0.00002908909,0.00000187264,0.7579378,0.0001708522,0.000008148864,0.001170301,0.002246702,0.1768997],"study_design_scores_gemma":[0.000879488,0.00004482526,0.4853913,0.0005639324,0.00001959981,0.000001747829,0.4603041,0.0006100247,0.0002127178,0.0001875448,0.05131071,0.0004740231],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944835,0.00001281463,0.0005325046,0.0005256948,0.0002012183,0.0005624639,0.000003818609,0.00006538666,0.00361263],"genre_scores_gemma":[0.9979182,0.000004158176,0.001196299,0.0005103294,0.000009629138,0.0001091407,0.000007537803,0.000002527536,0.0002422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4249597,"threshold_uncertainty_score":0.8835769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018764947","doi":"10.1016/j.ipm.2011.11.001","title":"A three-phase method for patent classification","year":2012,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Phase (matter); Computer science; Information retrieval; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.07881797612441159,"gpt":0.3411085603720877,"spread":0.2622905842476761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006607394,0.000125291,0.0000981699,0.000283908,0.0002375818,0.0004575102,0.0005704798,0.00005651815,0.000007982271],"category_scores_gemma":[0.00002949054,0.0001115491,0.00004664606,0.0004198579,0.00002121835,0.005439035,0.0001525608,0.00005836493,0.0001109711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009195747,"about_ca_system_score_gemma":0.00001985712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001833911,"about_ca_topic_score_gemma":3.245976e-7,"domain_scores_codex":[0.9988663,0.00001109594,0.0004052084,0.0001449719,0.0002738065,0.0002986437],"domain_scores_gemma":[0.9990601,0.00002497742,0.0003226257,0.0004011143,0.0001328752,0.00005832159],"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":[0.000004738677,0.00005595036,0.00003859719,0.00008757296,0.000007898981,3.106219e-8,0.000384733,0.000008977382,0.00002460234,0.290449,0.002106506,0.7068314],"study_design_scores_gemma":[0.001484247,0.00006670636,0.00509353,0.0000439508,0.00003367876,0.000003388899,0.000947761,0.5157804,0.001637315,0.03178029,0.4427781,0.0003505454],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001550226,0.00008875235,0.991313,0.002328967,0.000228209,0.0006231918,0.000002218361,0.0007531848,0.004507479],"genre_scores_gemma":[0.3796265,0.00001218211,0.6189886,0.0005502132,0.00003052516,0.0006151486,0.0000390169,0.000005489467,0.0001322767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7064809,"threshold_uncertainty_score":0.4548838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399785296","doi":"10.1016/j.ipm.2024.103809","title":"Are LLMs good at structured outputs? A benchmark for evaluating structured output capabilities in LLMs","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02699792293706213,"gpt":0.3020599101299465,"spread":0.2750619871928844,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008874912,0.0002643468,0.0002285317,0.0006159737,0.000251345,0.00132457,0.0008684581,0.0001026092,0.00001621562],"category_scores_gemma":[0.000128681,0.0002470134,0.00006971702,0.0007406953,0.00005473807,0.004447567,0.0004117508,0.0001638491,0.00002630985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005676851,"about_ca_system_score_gemma":0.00008577896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008096347,"about_ca_topic_score_gemma":0.00001868702,"domain_scores_codex":[0.997656,0.00004570781,0.0008284398,0.0004399373,0.0006283591,0.0004015173],"domain_scores_gemma":[0.9985792,0.00006692833,0.0004648839,0.0006155752,0.0002149628,0.00005845878],"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":[0.00002415075,0.0000210811,0.0003846017,0.003164658,0.00003826324,0.000003794759,0.007656362,0.001220104,0.0001194305,0.08471923,0.004162819,0.8984855],"study_design_scores_gemma":[0.001224229,0.0001100832,0.03583704,0.001215452,0.0000514811,0.00001859442,0.002337473,0.784241,0.003976021,0.06989072,0.1001521,0.0009458198],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01026838,0.0003653287,0.9797121,0.001276237,0.0007277673,0.001936305,0.00008951528,0.001303712,0.004320611],"genre_scores_gemma":[0.8460637,0.00001103997,0.1516653,0.0006331027,0.00004166251,0.0006831901,0.0002238756,0.0000179055,0.0006602959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8975397,"threshold_uncertainty_score":0.9999982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950257936","doi":"10.1016/j.ipm.2019.102056","title":"User community detection via embedding of social network structure and temporal content","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Embedding; User-generated content; Social network (sociolinguistics); Similarity (geometry); Social media; Information retrieval; Feature (linguistics); Social network analysis; Graph; World Wide Web; Machine learning; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01095797323119896,"gpt":0.2537127352941816,"spread":0.2427547620629827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002159936,0.00009844624,0.0001498677,0.00008163361,0.0002483341,0.0001003581,0.0001033303,0.00002488935,0.00007121781],"category_scores_gemma":[6.356813e-7,0.00009491154,0.00004046763,0.0001917669,0.00002529591,0.000673614,0.0001268311,0.0001427624,0.000003570313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002563768,"about_ca_system_score_gemma":0.000005622866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001058248,"about_ca_topic_score_gemma":0.00000705908,"domain_scores_codex":[0.9993213,0.00003886584,0.0003136096,0.00005825807,0.0001438875,0.0001241081],"domain_scores_gemma":[0.9994326,0.00000949657,0.0003348289,0.0001170076,0.00008848403,0.0000175402],"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":[0.00004872287,0.00004798985,0.06888395,0.0005669442,0.0002271056,7.438869e-8,0.002922735,0.003013547,0.0002446792,0.01137766,0.0004582811,0.9122083],"study_design_scores_gemma":[0.004058203,0.000275958,0.5016392,0.0007820856,0.0006861385,0.000002597161,0.02160905,0.3083526,0.006033843,0.09713995,0.05769948,0.001720938],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.781749,0.00001021663,0.2132207,0.00002341796,0.00005042929,0.0002989341,0.000004238229,0.00006216333,0.004580952],"genre_scores_gemma":[0.9973503,5.67349e-7,0.002405482,0.00005144158,0.0000489288,0.00001070173,0.00006817342,0.000005239939,0.00005912182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9104874,"threshold_uncertainty_score":0.387038,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226334043","doi":"10.1016/j.ipm.2022.102933","title":"ARL: An adaptive reinforcement learning framework for complex question answering over knowledge base","year":2022,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Interpretability; Computer science; Reinforcement learning; Artificial intelligence; Knowledge base; Benchmark (surveying); Metric (unit); Machine learning; Relation (database); Question answering; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03806807387468865,"gpt":0.3012217434974285,"spread":0.2631536696227399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009190507,0.0001547554,0.0001241668,0.0002800814,0.000907207,0.000458562,0.0005756888,0.00003121045,0.00004186417],"category_scores_gemma":[0.00002899566,0.0001761389,0.00004474498,0.0003731724,0.00001440005,0.003387862,0.0005592997,0.000221471,0.00001313455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003348338,"about_ca_system_score_gemma":0.00005622267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001246448,"about_ca_topic_score_gemma":0.000001259972,"domain_scores_codex":[0.9984772,0.00006116046,0.0004601935,0.0002503321,0.0004287003,0.0003224025],"domain_scores_gemma":[0.9991332,0.00003259264,0.0003095098,0.0003248264,0.0001256853,0.00007418491],"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":[0.00002005152,0.00002522591,0.00001527644,0.0001455656,0.00001075212,6.871949e-7,0.004806161,0.38656,0.000004502102,0.1889741,0.0001026657,0.419335],"study_design_scores_gemma":[0.0003818372,0.0001461113,0.0002689206,0.00007028747,0.00001043754,0.000002115188,0.00148889,0.955884,0.00002057547,0.007674823,0.03384358,0.0002084728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001432929,0.00002929035,0.9924501,0.0001947117,0.0002852821,0.000568944,0.000001275126,0.0003831841,0.004654308],"genre_scores_gemma":[0.7114611,0.000002642577,0.2873932,0.0005438424,0.00004228914,0.0003169022,0.0000471997,0.00000838374,0.0001844889],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7100282,"threshold_uncertainty_score":0.7182735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3171889065","doi":"10.1016/j.ipm.2021.102642","title":"Machine learning fairness notions: Bridging the gap with real-world applications","year":2021,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":54,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"H2020 European Research Council; Horizon 2020; European Research Council; Horizon 2020 Framework Programme; European Commission","keywords":"Bridging (networking); Computer science; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.02918010393541636,"gpt":0.3327276565242364,"spread":0.30354755258882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009547394,0.00008702774,0.00008428779,0.0000969197,0.002700777,0.001194266,0.0002070513,0.00003755271,0.00005299059],"category_scores_gemma":[0.00008361491,0.00006834372,0.00003049108,0.0009092235,0.0001602121,0.00183183,0.00007117999,0.0002439332,0.00004576951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001207914,"about_ca_system_score_gemma":0.0002049688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008381764,"about_ca_topic_score_gemma":0.00200162,"domain_scores_codex":[0.9988172,0.00008389443,0.0002379022,0.0001024189,0.000525692,0.0002328726],"domain_scores_gemma":[0.9990475,0.00005784849,0.0002026852,0.0001412619,0.000490586,0.00006012038],"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":[0.000005855323,0.00003563507,0.0008352097,0.0001800197,0.00003886587,0.000002492346,0.02983552,0.002092998,0.000001091498,0.5374271,0.000473168,0.429072],"study_design_scores_gemma":[0.0002971089,0.000009766323,0.003629831,0.0001659338,0.000062797,0.000001154762,0.03724359,0.002692685,0.00001902719,0.01322531,0.9424191,0.0002336579],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0007275573,0.0001473575,0.09214878,0.03010312,0.00008523669,0.0005577821,0.000003327697,0.0002761082,0.8759508],"genre_scores_gemma":[0.9854469,0.0005751263,0.001885446,0.002046363,0.0001490208,0.0001520298,0.00006281622,0.000009761994,0.009672575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9847193,"threshold_uncertainty_score":0.9998426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999247825","doi":"10.1016/j.ipm.2009.06.005","title":"Facet-based opinion retrieval from blogs","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Facet (psychology); Query expansion; Lexicon; Structuring; Divergence (linguistics); Natural language processing; Artificial intelligence; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01596783699014856,"gpt":0.2525663967330099,"spread":0.2365985597428613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002257256,0.0001100049,0.00008869886,0.0001640723,0.0001421933,0.0005519463,0.0005505629,0.0000423991,0.00001031625],"category_scores_gemma":[0.00001305623,0.0001077488,0.00002963864,0.000308268,0.000009488719,0.0025844,0.00008658188,0.00008144523,0.0001075442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006942105,"about_ca_system_score_gemma":0.00003756217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005312315,"about_ca_topic_score_gemma":1.385213e-7,"domain_scores_codex":[0.9988763,0.0000139472,0.0003444242,0.0001676406,0.0004079741,0.0001897123],"domain_scores_gemma":[0.9993401,0.000007209716,0.0001718708,0.0003572645,0.00007531748,0.0000482438],"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":[0.000007002719,0.00002259167,0.00001621905,0.00005225754,0.000005281896,0.000001195609,0.0007892608,0.007372029,0.00002424638,0.01262913,0.0006324112,0.9784484],"study_design_scores_gemma":[0.0006889086,0.00003416386,0.003229827,0.00012713,0.00000617664,7.566381e-7,0.0001005562,0.9566913,0.0007211014,0.009700712,0.0284753,0.0002241126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003487233,0.00005675211,0.9816833,0.002438658,0.0002763593,0.0001790232,0.000001036486,0.0003570582,0.01152057],"genre_scores_gemma":[0.8463968,0.000006646708,0.1496321,0.003815664,0.00004447805,0.00000515705,0.00002994625,0.000002643285,0.00006655801],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9782243,"threshold_uncertainty_score":0.5322431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2744881172","doi":"10.1016/j.ipm.2017.07.004","title":"Modeling Arabic subjectivity and sentiment in lexical space","year":2017,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":43,"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":"Subjectivity; Arabic; Natural language processing; Computer science; Space (punctuation); Artificial intelligence; Linguistics; Philosophy; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.01928436550720981,"gpt":0.2747371884251029,"spread":0.2554528229178931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004991682,0.0001005509,0.0001163205,0.0002260054,0.0004020656,0.001551336,0.0003954844,0.00002762728,0.000003380356],"category_scores_gemma":[0.00001323716,0.0000953678,0.00002776586,0.000123274,0.00002387202,0.00439594,0.0004107413,0.00007381094,0.00002811627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004537178,"about_ca_system_score_gemma":0.00001402095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000030927,"about_ca_topic_score_gemma":0.000007285754,"domain_scores_codex":[0.9990722,0.0000148163,0.0002741563,0.0001766778,0.0002789685,0.0001831894],"domain_scores_gemma":[0.999392,0.000005374856,0.0001691763,0.0003486217,0.0000415303,0.00004328368],"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":[0.000009748659,0.00006264753,0.005658339,0.0001691741,0.00003238412,0.000006598675,0.002684968,0.01927084,0.00001055394,0.04048951,0.0001061293,0.9314991],"study_design_scores_gemma":[0.0003617427,0.000006618334,0.01364212,0.00008057497,0.000007018548,0.000001321349,0.0001798931,0.9830756,0.00005839996,0.00154428,0.0009213954,0.000121008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1161851,0.00006959387,0.865043,0.001496936,0.0001299394,0.0001712475,1.965751e-7,0.00007014896,0.01683379],"genre_scores_gemma":[0.9832612,0.00003924665,0.01638336,0.0001430369,0.00001325378,0.00001330008,0.000002451868,0.000002353942,0.0001417413],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9638048,"threshold_uncertainty_score":0.9994851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951813287","doi":"10.1016/j.ipm.2019.102054","title":"Compact group discovery in attributed graphs and social networks","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":42,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ontario Institute of Technology; Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Node (physics); Set (abstract data type); Theoretical computer science; Group (periodic table); Time complexity; Combinatorics; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.006334680114128278,"gpt":0.2343614577232908,"spread":0.2280267776091625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002082543,0.000114766,0.0001624131,0.0001880405,0.00009897684,0.0003365809,0.000105916,0.00002194201,0.00004309722],"category_scores_gemma":[2.860545e-7,0.0001118932,0.0000441419,0.0003485032,0.00002175695,0.001621861,0.00008210625,0.0001017449,0.00001112582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003215301,"about_ca_system_score_gemma":0.000005212124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005465416,"about_ca_topic_score_gemma":0.000004053134,"domain_scores_codex":[0.9992471,0.00001843237,0.0003021536,0.0001047263,0.0001405519,0.000187082],"domain_scores_gemma":[0.9996836,0.000009672707,0.0001679637,0.00009537143,0.00002596459,0.00001741574],"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":[0.00004404172,0.0001095272,0.1816524,0.0002475108,0.0001383555,5.974378e-7,0.001034443,0.006607389,0.000004885414,0.1589056,0.003391856,0.6478634],"study_design_scores_gemma":[0.002463958,0.00004981245,0.5546449,0.0003056269,0.000126014,6.257854e-7,0.002964316,0.3601961,0.00002250611,0.03771114,0.04069258,0.0008224116],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6324314,0.00007683792,0.3221322,0.0003317568,0.0001004642,0.0009428257,0.00001079326,0.0002467575,0.04372698],"genre_scores_gemma":[0.9991485,0.000003686604,0.0003528534,0.0001369174,0.00001923448,0.00001737988,0.0002176669,0.000005362975,0.00009835606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.647041,"threshold_uncertainty_score":0.4562874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2800110000","doi":"10.1016/j.ipm.2018.04.007","title":"Neural word and entity embeddings for ad hoc retrieval","year":2018,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Task (project management); Word (group theory); Information retrieval; Artificial intelligence; Natural language processing; Question answering; Artificial neural network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01615621521834194,"gpt":0.2657383048232765,"spread":0.2495820896049346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003201784,0.00008555896,0.00007269978,0.0001280951,0.0002461325,0.0006801234,0.0003143895,0.00002769075,0.000003991341],"category_scores_gemma":[0.00002371507,0.00008297911,0.00001965142,0.0002061684,0.00003360262,0.003379006,0.000246608,0.00004436836,0.00001806423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003528607,"about_ca_system_score_gemma":0.00001477396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001029244,"about_ca_topic_score_gemma":7.984322e-7,"domain_scores_codex":[0.9991875,0.000006210361,0.0002547337,0.0001509077,0.0002149382,0.0001856575],"domain_scores_gemma":[0.9994702,0.000009438228,0.0001387504,0.0001955849,0.0001437226,0.00004231894],"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":[0.00001357538,0.000005388209,0.00001986019,0.0001971296,0.000005613909,2.489418e-7,0.002026541,0.00004779845,0.000005286146,0.006783387,0.0004493369,0.9904459],"study_design_scores_gemma":[0.0005445753,0.0000517111,0.001105433,0.00006296842,0.00001118695,0.000003941454,0.0002125176,0.912915,0.0001996111,0.00556732,0.07915477,0.0001709489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03670384,0.00007048903,0.958986,0.0007356973,0.0002903156,0.0002860307,7.181374e-7,0.0001729305,0.002754025],"genre_scores_gemma":[0.8248838,0.00001315595,0.1735819,0.001097947,0.00005909137,0.00001870579,0.000004148289,0.000003944263,0.0003372813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9902749,"threshold_uncertainty_score":0.6558446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297829713","doi":"10.1016/j.ipm.2022.103076","title":"An efficiency relation-specific graph transformation network for knowledge graph representation learning","year":2022,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Graph; Relation (database); Transformation (genetics); Theoretical computer science; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0176962029112127,"gpt":0.2723371055770977,"spread":0.254640902665885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008413134,0.0001943393,0.0001498359,0.0005314261,0.002022362,0.0004977529,0.0007251483,0.00004154975,0.00001068119],"category_scores_gemma":[0.000009261333,0.000216456,0.00009795312,0.002399244,0.00003416228,0.007397871,0.0001401813,0.0002721983,0.00001218596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186459,"about_ca_system_score_gemma":0.00002575157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001462549,"about_ca_topic_score_gemma":8.052297e-7,"domain_scores_codex":[0.997927,0.00012377,0.0006956554,0.0003256703,0.0005187088,0.0004091598],"domain_scores_gemma":[0.9988256,0.00007067776,0.0004733995,0.0003715234,0.0001846176,0.00007416309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002302797,0.00003719803,0.00004635773,0.0000636953,0.00000731796,3.88001e-7,0.004281697,0.5758125,0.000006631949,0.06397348,0.0005804541,0.3551673],"study_design_scores_gemma":[0.0009753356,0.0002077478,0.001970882,0.00004163541,0.00001749935,0.000008196949,0.001771073,0.8930649,0.00005092973,0.03786382,0.06364369,0.00038429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002599913,0.0002509516,0.9903237,0.0002391425,0.0005612613,0.001047961,0.000002593026,0.0006026449,0.004371854],"genre_scores_gemma":[0.9323314,0.00006742801,0.06598852,0.0003077209,0.00007627005,0.0007691185,0.0003491641,0.00001728689,0.00009308119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9297315,"threshold_uncertainty_score":0.9992769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320480083","doi":"10.1016/j.ipm.2023.103266","title":"Spatial spillovers of sport industry clusters and community resilience: Bridging a spatial lens to building a smart tourism city","year":2023,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Sport and Mega-Event Impacts","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"National Research Foundation of Korea; Ministry of Education","keywords":"Tourism; Community resilience; Spillover effect; Resilience (materials science); Business; Context (archaeology); Psychological resilience; Spatial analysis; Geography; Environmental resource management; Economic geography; Economics; Computer science; Psychology; Resource (disambiguation)","retraction":null,"screen_n_in":null,"score":{"opus":0.02869647267145917,"gpt":0.3123498810157363,"spread":0.2836534083442771,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001933124,0.00011887,0.0001629953,0.0003904138,0.0008626233,0.0001860868,0.0002400759,0.0001065759,0.00002179971],"category_scores_gemma":[0.0001133589,0.0001276183,0.0000337216,0.0007514712,0.0001245474,0.001543976,0.0002268945,0.0003121794,0.00001156135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338878,"about_ca_system_score_gemma":0.0001173987,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106653,"about_ca_topic_score_gemma":0.0006764273,"domain_scores_codex":[0.9985036,0.00003219771,0.0003960656,0.0001035347,0.0006118147,0.0003527391],"domain_scores_gemma":[0.9993036,0.00001902835,0.0002769997,0.0001578002,0.0001019311,0.0001406071],"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":[0.000159726,0.00009717814,0.07752417,0.0008061153,0.00005674015,0.00001667908,0.1096961,0.002320369,0.00003553608,0.002636262,0.006910547,0.7997406],"study_design_scores_gemma":[0.001461244,0.0001378805,0.7113197,0.001083671,0.00009563403,0.000003208451,0.05876903,0.005880753,0.0005032924,0.0005250033,0.2195914,0.0006291369],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9646106,0.000004179022,0.003834209,0.0008725415,0.0002027374,0.000451809,0.00000357913,0.0001414282,0.02987886],"genre_scores_gemma":[0.9985755,0.00001927781,0.0004202552,0.0004339065,0.00006515634,0.00001511479,0.00001800095,0.000005926111,0.0004468416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7991115,"threshold_uncertainty_score":0.9959227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4316813420","doi":"10.1016/j.ipm.2022.103262","title":"SmartRolling: A human–machine interface for wheelchair control using EEG and smart sensing techniques","year":2023,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":36,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Wheelchair; Brain–computer interface; Computer science; Interface (matter); Fist; Motion (physics); Human–computer interaction; Electroencephalography; Artificial intelligence; Head (geology); Motion control; Inertial measurement unit; Computer vision; Simulation; Robot; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03067517900050492,"gpt":0.3078482972513358,"spread":0.2771731182508309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005132545,0.0001968625,0.0001935296,0.0004156401,0.0005220756,0.0006049433,0.0001820216,0.00005128372,0.000002822517],"category_scores_gemma":[0.00005719089,0.0001819412,0.00004726225,0.0003495221,0.0000725116,0.001374926,0.0001643206,0.0001102624,0.00001378515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005272215,"about_ca_system_score_gemma":0.00001385541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007581055,"about_ca_topic_score_gemma":0.000001910623,"domain_scores_codex":[0.9986628,0.00003596252,0.0004746472,0.0002517113,0.0002469277,0.0003279451],"domain_scores_gemma":[0.9993787,0.00006649664,0.0002624756,0.0001590318,0.00007970908,0.00005352823],"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":[0.0001248389,0.00005209114,0.0001182248,0.002276524,0.0000509184,0.00001184132,0.004968847,0.004887251,0.08427157,0.002475429,0.001870009,0.8988925],"study_design_scores_gemma":[0.001396592,0.0001195203,0.0002306418,0.0005328153,0.00005257653,0.00002782054,0.0006093136,0.8712912,0.08332546,0.002011154,0.03999367,0.0004092722],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.231695,0.00005825776,0.7613865,0.0009069352,0.0002692425,0.001355988,0.000023127,0.001210126,0.003094809],"genre_scores_gemma":[0.9903755,0.0000139058,0.008018932,0.001240924,0.00003531573,0.00003541938,0.00001001074,0.00001846898,0.0002515477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8984832,"threshold_uncertainty_score":0.7419347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045426578","doi":"10.1016/j.ipm.2009.12.005","title":"A3CRank: An adaptive ranking method based on connectivity, content and click-through data","year":2010,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Glasgow; Badan Riset dan Inovasi Nasional","keywords":"Ranking SVM; Computer science; Ranking (information retrieval); PageRank; Learning to rank; Aggregate (composite); Information retrieval; Data mining; Rank (graph theory); Machine learning; Web page; Artificial intelligence; Mathematics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0762809013681563,"gpt":0.3101881089765652,"spread":0.2339072076084089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001177013,0.0001649211,0.0001498907,0.0001740063,0.0003389975,0.0009053102,0.0008722262,0.00004974032,0.00000474056],"category_scores_gemma":[0.00004805613,0.0001493783,0.00002501315,0.0002194896,0.00003894761,0.00690166,0.0004873674,0.0002359642,0.00001647411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000277797,"about_ca_system_score_gemma":0.00003793219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009699359,"about_ca_topic_score_gemma":0.00002175339,"domain_scores_codex":[0.9986329,0.00006982502,0.0003133379,0.0003460419,0.0004190932,0.0002187824],"domain_scores_gemma":[0.9986728,0.00008023567,0.0002167264,0.0008408484,0.0001231307,0.00006624631],"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":[0.00005359496,0.00007257055,0.00007246694,0.0000907738,0.00002052167,0.000004321607,0.001123406,0.00116659,0.00006793936,0.04244055,0.0002022636,0.954685],"study_design_scores_gemma":[0.0008893213,0.00009094775,0.001428013,0.00008738074,0.00002154877,0.000007115584,0.0003904232,0.9886628,0.0001033875,0.001595661,0.006507216,0.0002162061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01071866,0.00001554656,0.9797121,0.0008291251,0.0003139981,0.0003004,0.000007856206,0.0002526567,0.007849623],"genre_scores_gemma":[0.8587036,0.000004107798,0.1380292,0.003124921,0.00003170978,0.0000230867,0.00004059785,0.000005886309,0.0000368272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9874962,"threshold_uncertainty_score":0.8729927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102838806","doi":"10.1016/j.ipm.2008.01.003","title":"Lexical cohesion and term proximity in document ranking","year":2008,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Query expansion; Ranking (information retrieval); Computer science; Cohesion (chemistry); Information retrieval; Collocation (remote sensing); Relevance (law); Term (time); Query optimization; Natural language processing; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0155754297426092,"gpt":0.2417716080082823,"spread":0.2261961782656731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002651107,0.00008452153,0.00009311524,0.0001730779,0.0001619949,0.0002187684,0.000243714,0.00002935479,0.000002173932],"category_scores_gemma":[0.00001240193,0.00007197628,0.00001328986,0.0002083195,0.00003938876,0.003244698,0.0002287384,0.00006273761,0.00001470481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004427266,"about_ca_system_score_gemma":0.00001949528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009078203,"about_ca_topic_score_gemma":0.00000200714,"domain_scores_codex":[0.9991701,0.00001536286,0.0002760715,0.0001249209,0.0002476645,0.000165942],"domain_scores_gemma":[0.9996899,0.0000119808,0.00009522391,0.0001471213,0.00002800339,0.00002777721],"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":[0.00001060417,0.00003030939,0.007901972,0.0002830094,0.000005189123,0.0000220608,0.004815666,0.00009502771,0.000004868118,0.01822505,0.0001620469,0.9684442],"study_design_scores_gemma":[0.00245201,0.00008240648,0.8861958,0.0004736048,0.00001264237,0.0001053273,0.0008662398,0.07999527,0.000714547,0.0186357,0.009923565,0.0005429224],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3922166,0.0002039706,0.5881701,0.001575562,0.0001748682,0.0005273113,1.603097e-7,0.0003180383,0.01681342],"genre_scores_gemma":[0.9739259,0.00006474334,0.02544292,0.0004747853,0.000007247316,0.00002519408,0.000001663241,0.000001541723,0.00005597857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9679013,"threshold_uncertainty_score":0.2935107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594363579","doi":"10.1016/j.ipm.2017.02.009","title":"Self-training on refined clause patterns for relation extraction","year":2017,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relationship extraction; Computer science; Parsing; Information extraction; Natural language processing; Dependency (UML); Context (archaeology); Relation (database); Dependency grammar; Benchmark (surveying); Variety (cybernetics); Artificial intelligence; Rule-based machine translation; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.04563325351583229,"gpt":0.3055209064605257,"spread":0.2598876529446934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004404062,0.0001037882,0.00008098396,0.0001572462,0.0007284568,0.001195623,0.0005186204,0.00006564937,0.000002846988],"category_scores_gemma":[0.00004453123,0.0001038663,0.00003274182,0.00005011767,0.000006773416,0.00565047,0.0001157881,0.000105458,0.00004220119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009951924,"about_ca_system_score_gemma":0.00002393499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004042574,"about_ca_topic_score_gemma":0.000001904771,"domain_scores_codex":[0.9990392,0.000009026984,0.0003230209,0.0001714451,0.0002738102,0.0001835346],"domain_scores_gemma":[0.9988373,0.0000183635,0.0004730758,0.0005386146,0.00009765133,0.00003502403],"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":[0.000008728995,0.00001654822,0.00007182766,0.000262317,0.00001202763,7.431606e-7,0.002285732,0.001256968,0.000003678544,0.05159429,0.0001927895,0.9442943],"study_design_scores_gemma":[0.000859659,0.00004154648,0.01867223,0.0002231833,0.00001795231,0.000002901382,0.0002646491,0.8981126,0.0001093185,0.005264182,0.07620309,0.0002286749],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003961409,0.000003564817,0.9716977,0.002022933,0.0003999504,0.0003665854,9.772191e-7,0.000305533,0.02124138],"genre_scores_gemma":[0.8144553,0.000008084481,0.1844223,0.0006515058,0.00006324818,0.00009856357,0.00001321077,0.000005691776,0.0002821158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9440657,"threshold_uncertainty_score":0.9998412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3106364367","doi":"10.1016/j.ipm.2020.102434","title":"User and item-aware estimation of review helpfulness","year":2020,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Independent Electricity System Operator; Università degli Studi di Torino","keywords":"Helpfulness; Computer science; Quality (philosophy); Recommender system; Data mining; Machine learning; Artificial intelligence; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01043133937284873,"gpt":0.261754455847965,"spread":0.2513231164751162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001136976,0.00008082054,0.0001449626,0.00005068802,0.00005675787,0.00006174469,0.0000896033,0.000009240309,0.00009999514],"category_scores_gemma":[0.000004097142,0.00007622642,0.00003141446,0.0002752909,0.00001625496,0.0007796958,0.00008168699,0.00004107971,0.00001120413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007760053,"about_ca_system_score_gemma":0.000008341128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005856221,"about_ca_topic_score_gemma":9.532982e-8,"domain_scores_codex":[0.9993457,0.00001122144,0.0003462022,0.00007265301,0.0001498779,0.00007434702],"domain_scores_gemma":[0.9995368,0.000007580017,0.0002566848,0.00008963364,0.00007734011,0.0000319734],"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":[0.000003028009,0.000009759702,0.0005045317,0.002898269,0.00002920859,7.800278e-8,0.0002593672,0.0005212373,8.422411e-7,0.005661686,0.003751971,0.98636],"study_design_scores_gemma":[0.001071362,0.00008142264,0.007949864,0.007093225,0.0007305527,0.000001016913,0.001637748,0.7758739,0.001426736,0.009458067,0.1938481,0.0008279742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003931717,0.0005870968,0.9808778,0.001417791,0.00001372704,0.000499125,0.000006023718,0.0001169918,0.01254974],"genre_scores_gemma":[0.9941638,0.00006696822,0.004819257,0.0007594618,0.00001943792,0.0000471347,0.000085977,0.000004292419,0.0000336448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9902321,"threshold_uncertainty_score":0.3108423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962840445","doi":"10.1016/j.ipm.2019.102081","title":"“Nothing's available”: Young fathers’ experiences with unmet information needs and barriers to resolving them","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Psychology; Population; Service provider; Young adult; Ethnography; Information needs; Developmental psychology; Social psychology; Service (business); Sociology; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.03280137134763937,"gpt":0.3260608287122516,"spread":0.2932594573646122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009062907,0.0001934096,0.0001937523,0.0003608167,0.001153363,0.0001566605,0.0001782528,0.0000829751,0.0004886291],"category_scores_gemma":[0.00007417038,0.0001415647,0.00001504443,0.0006047504,0.00005293409,0.004594116,0.0001789765,0.0002962428,0.001443369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001716294,"about_ca_system_score_gemma":0.0001728802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004941124,"about_ca_topic_score_gemma":0.000002710769,"domain_scores_codex":[0.9982106,0.00007099053,0.0006255841,0.0001556678,0.0004862389,0.0004509366],"domain_scores_gemma":[0.9988073,0.00002721596,0.0004352089,0.0002693074,0.0002341924,0.0002267714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002057545,0.00001570908,0.02269039,0.002668008,0.00002542247,5.253819e-7,0.9306449,0.0001451034,0.000006422684,0.001447645,0.004084215,0.03806586],"study_design_scores_gemma":[0.0007367878,0.00008492239,0.004838752,0.0006947979,0.00001375762,0.00000412502,0.7995068,0.0008087908,0.00002184802,0.00004288006,0.1929892,0.0002572922],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8509048,0.0000506361,0.01322522,0.002051678,0.0007124796,0.002820609,0.000005022868,0.0003118574,0.1299177],"genre_scores_gemma":[0.9864293,0.00002005336,0.002279095,0.007060477,0.00005939613,0.0002731394,0.00002596015,0.00001312778,0.003839497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.188905,"threshold_uncertainty_score":0.9993341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403483116","doi":"10.1016/j.ipm.2024.103923","title":"Unsupervised feature selection using sparse manifold learning: Auto-encoder approach","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Seneca Polytechnic; Sunnybrook Health Science Centre","funders":"Graduate University of Advanced Technology","keywords":"Autoencoder; Artificial intelligence; Feature selection; Computer science; Nonlinear dimensionality reduction; Selection (genetic algorithm); Pattern recognition (psychology); Feature learning; Unsupervised learning; Feature (linguistics); Machine learning; Manifold (fluid mechanics); Encoder; Dimensionality reduction; Deep learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01827452959897996,"gpt":0.2442923255483582,"spread":0.2260177959493782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003278504,0.0001718932,0.0001076194,0.0004290373,0.0003559915,0.001779092,0.0003030315,0.00009026805,0.00002350743],"category_scores_gemma":[0.00000777325,0.0001540046,0.00005405876,0.0009151578,0.00001197436,0.005894995,0.0001578998,0.0002602489,0.0002076692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001121349,"about_ca_system_score_gemma":0.00005663251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006539266,"about_ca_topic_score_gemma":2.405175e-7,"domain_scores_codex":[0.9987264,0.00003679868,0.0002799851,0.0002603763,0.0004364831,0.0002599112],"domain_scores_gemma":[0.9995672,0.000009139498,0.0001010882,0.0001541025,0.0001095605,0.00005887707],"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":[0.00001252597,0.00006164327,0.00005631558,0.002041257,0.00005973913,0.0000095285,0.004808761,0.03714929,0.0003627983,0.01176123,0.009326844,0.9343501],"study_design_scores_gemma":[0.0001750812,0.00001596386,0.0001662785,0.0002787514,0.00002306629,0.00002508015,0.000483324,0.9238235,0.0003139144,0.0006427681,0.07385714,0.000195169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002507901,0.0001653359,0.9700318,0.0004367503,0.0003116754,0.0002868031,7.253427e-7,0.0009894952,0.02526951],"genre_scores_gemma":[0.7873525,0.00005467813,0.2084775,0.0007949164,0.0001029877,0.00008455238,0.00008531371,0.00002042072,0.003027109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9341549,"threshold_uncertainty_score":0.9992571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983610980","doi":"10.1016/j.ipm.2013.07.006","title":"The relationship between perceived value and information source use during KM strategic decision-making: A study of 17 Chinese business managers","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Knowledge Management and Sharing","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Rogers Communications (Canada)","funders":"","keywords":"Information source (mathematics); Likert scale; Attribution; Business; Value (mathematics); Marketing; Newspaper; Intranet; Knowledge management; Psychology; Computer science; The Internet; Advertising","retraction":null,"screen_n_in":null,"score":{"opus":0.03032183527242007,"gpt":0.3008649844833933,"spread":0.2705431492109733,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000914512,0.0001726594,0.0001640445,0.0004449562,0.001948564,0.002244043,0.0003799725,0.00005991092,0.00001857308],"category_scores_gemma":[0.000452369,0.0001348664,0.00003241352,0.001054183,0.0001191564,0.01165895,0.0002622791,0.0001326454,0.0000512495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009145,"about_ca_system_score_gemma":0.00003046548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003116293,"about_ca_topic_score_gemma":0.00009477645,"domain_scores_codex":[0.9980814,0.00008838795,0.0007319131,0.0001295374,0.0006777723,0.0002909989],"domain_scores_gemma":[0.9984748,0.0003633797,0.0005078274,0.0002392886,0.0003516559,0.00006308319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006765145,0.0001042715,0.476137,0.001023304,0.0001596116,0.000001143638,0.1465024,0.005746752,6.42351e-7,0.01642912,0.0002970609,0.3535311],"study_design_scores_gemma":[0.0005224469,0.00001370473,0.924239,0.0001826956,0.00005299516,1.973334e-7,0.06726562,0.002461739,6.235221e-8,0.00334941,0.001756434,0.0001556317],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.967517,0.00001887292,0.00307028,0.0001947881,0.00009251492,0.001320517,0.000001037837,0.0001197036,0.0276653],"genre_scores_gemma":[0.9987602,0.00002761673,0.0004581234,0.00004644602,0.00003995025,0.00009366939,0.00001272776,0.000007553783,0.0005537259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.448102,"threshold_uncertainty_score":0.9993508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042042646","doi":"10.1016/j.ipm.2010.03.010","title":"Mining and modeling linkage information from citation context for improving biomedical literature retrieval","year":2010,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Linkage (software); Information retrieval; Citation; Weighting; Graph; PageRank; Context (archaeology); Data mining; Probabilistic logic; Data science; Theoretical computer science; World Wide Web; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01099387631666131,"gpt":0.2568205869718952,"spread":0.2458267106552339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003377434,0.0001319451,0.0001026973,0.0001417132,0.000194501,0.0003398334,0.0001209139,0.0002334495,0.000002842627],"category_scores_gemma":[0.0003158079,0.0001153846,0.00003410919,0.0001299043,0.0000662082,0.0001535235,0.00008918576,0.0001150302,0.000002131904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000953048,"about_ca_system_score_gemma":0.00003364729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000639889,"about_ca_topic_score_gemma":0.00000378447,"domain_scores_codex":[0.9991127,0.000009675534,0.0003754073,0.0001364092,0.0001898329,0.0001759973],"domain_scores_gemma":[0.9994242,0.00001857848,0.0001830751,0.0001282818,0.0001761332,0.00006968584],"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":[0.0001033796,0.00001189216,0.00005413997,0.0003809213,0.00002333183,2.520877e-7,0.002708229,0.00002467708,0.003625669,0.0001364962,0.0004640002,0.992467],"study_design_scores_gemma":[0.00569728,0.0005277217,0.002049748,0.0005651527,0.0001733337,0.00001501345,0.02046978,0.6707613,0.009669185,0.002066819,0.2869602,0.001044531],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5820983,0.0002103987,0.4164002,0.0003130746,0.0003148642,0.0002675545,0.0000419798,0.00005912242,0.000294454],"genre_scores_gemma":[0.9410155,0.00002050878,0.05596042,0.0005748483,0.0001276933,0.00002714729,0.002237629,0.000006331819,0.00002996065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9914225,"threshold_uncertainty_score":0.4705249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406281472","doi":"10.1016/j.ipm.2025.104059","title":"A diversity-enhanced knowledge distillation model for practical math word problem solving","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Diversity (politics); Distillation; Mathematics; Mathematics education; Computer science; Chemistry; Sociology; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.02701293583463594,"gpt":0.2946960030078121,"spread":0.2676830671731762,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005020757,0.0001196244,0.0001125944,0.000231432,0.001107064,0.0004886257,0.0002948102,0.00004169912,7.709432e-7],"category_scores_gemma":[0.00004239631,0.0001151417,0.00004597273,0.0003250489,0.00001253468,0.002928651,0.0007379947,0.00009763741,0.00002410482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603233,"about_ca_system_score_gemma":0.00009110807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003190175,"about_ca_topic_score_gemma":0.000001448857,"domain_scores_codex":[0.9990271,0.00001802315,0.000346076,0.0001811721,0.0002049594,0.0002226394],"domain_scores_gemma":[0.9992654,0.00004100592,0.0002254007,0.0001675319,0.0002705267,0.00003018908],"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":[0.00001117463,0.00002547723,0.00002099142,0.0007867052,0.00002228757,2.605977e-7,0.009311216,0.02350109,0.000005932106,0.6929045,0.0003886391,0.2730217],"study_design_scores_gemma":[0.0002440618,0.00001067111,0.0002125927,0.0003692855,0.00001621529,5.064842e-7,0.0004731296,0.9639478,0.000060985,0.008157142,0.02637889,0.0001286652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005829202,0.0000246517,0.9706287,0.0004275831,0.0002085844,0.0005239722,5.684419e-7,0.0002323748,0.02737068],"genre_scores_gemma":[0.782035,0.000004036577,0.2078262,0.0001532625,0.00002213911,0.00007336381,0.000005859262,0.00000376281,0.009876366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9404467,"threshold_uncertainty_score":0.8514753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062134786","doi":"10.1016/j.ipm.2009.04.007","title":"Empirical observations on the session timeout threshold","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":23,"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":"Timeout; Session (web analytics); Computer science; Computer network; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04708374987156168,"gpt":0.2914557649864874,"spread":0.2443720151149257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003659003,0.0001358082,0.00008706122,0.0002258302,0.000383693,0.0006924968,0.001207148,0.00005045613,0.000005166815],"category_scores_gemma":[0.00004411888,0.00009252426,0.00003108091,0.00104041,0.0000221759,0.001900158,0.0003035297,0.0001553513,0.0003071036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008462065,"about_ca_system_score_gemma":0.00002500849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.741688e-7,"about_ca_topic_score_gemma":3.229331e-7,"domain_scores_codex":[0.998736,0.00001383052,0.0003111541,0.0001688675,0.000515206,0.0002549845],"domain_scores_gemma":[0.9991029,0.00002843516,0.0001337198,0.0005911335,0.0001002436,0.00004355026],"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":[0.000004363228,0.00003690294,0.00008533392,0.000015725,0.000005882296,0.00000182595,0.0008681007,0.004895676,0.000006099028,0.1002453,0.07611334,0.8177214],"study_design_scores_gemma":[0.0004884462,0.0002360908,0.08344646,0.00043881,0.00001940167,0.000007125735,0.0004807163,0.3568058,0.0006897704,0.1073443,0.4494084,0.0006346848],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01200611,0.00003543215,0.7801461,0.1354652,0.0002197704,0.0006881586,0.000001070673,0.001650401,0.06978782],"genre_scores_gemma":[0.919045,0.000006398731,0.05054024,0.02970883,0.00002804712,0.00006865836,0.000008219872,0.000004007315,0.0005905606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9070389,"threshold_uncertainty_score":0.6677763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407171721","doi":"10.1016/j.ipm.2025.104079","title":"Exploring hate speech dynamics: The emotional, linguistic, and thematic impact on social media users","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dynamics (music); Linguistics; Social media; Thematic map; Psychology; Sociology; Computer science; Geography; World Wide Web; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03384694922045842,"gpt":0.2694452666570548,"spread":0.2355983174365963,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004240112,0.0001306859,0.00009859719,0.0002653556,0.0005360732,0.0008197398,0.0003325341,0.0000267864,0.00000385876],"category_scores_gemma":[0.00006851617,0.00009161008,0.00004002238,0.0004703458,0.00003693344,0.001394342,0.0001483659,0.0001209164,0.00004013186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462064,"about_ca_system_score_gemma":0.00003004533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008018322,"about_ca_topic_score_gemma":0.000003378562,"domain_scores_codex":[0.9990581,0.00002512648,0.0002736927,0.0001325479,0.0003213081,0.000189256],"domain_scores_gemma":[0.9994888,0.00006100411,0.0001408761,0.0001846549,0.00009481692,0.0000298463],"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":[0.000008475043,0.00001320168,0.00001318849,0.0001904355,0.00002930022,0.000001662189,0.00359652,0.0003719387,8.958704e-7,0.04748457,0.0002079593,0.9480819],"study_design_scores_gemma":[0.001642225,0.00009235926,0.04848588,0.00160554,0.000121974,0.0000231439,0.007931176,0.8639711,0.0006870439,0.06540496,0.009253268,0.0007813594],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1773617,0.00008874295,0.7586215,0.004329349,0.001499525,0.0008428656,0.000005409101,0.0006875979,0.05656336],"genre_scores_gemma":[0.9945062,0.00004590793,0.004766242,0.000450547,0.00004882632,0.0000506431,0.000009573483,0.000004284002,0.0001178022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9473005,"threshold_uncertainty_score":0.790477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406820161","doi":"10.1016/j.ipm.2025.104074","title":"Exploring long- and short-term knowledge state graph representations with adaptive fusion for knowledge tracing","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","keywords":"Term (time); Tracing; Computer science; Graph; Fusion; Artificial intelligence; Theoretical computer science; Programming language; Linguistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.07738686477959825,"gpt":0.3053585535230985,"spread":0.2279716887435003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004005688,0.0001738544,0.0001728105,0.0006609165,0.0004675768,0.000725591,0.0002690324,0.00002618977,0.000001077044],"category_scores_gemma":[0.00001728905,0.0001631287,0.00004006744,0.000828243,0.00004046384,0.006978504,0.0002463134,0.00008743153,0.00001080361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009581587,"about_ca_system_score_gemma":0.00007497545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007220843,"about_ca_topic_score_gemma":0.0000540161,"domain_scores_codex":[0.9988241,0.00003816246,0.000436093,0.0002880719,0.0001810923,0.0002325289],"domain_scores_gemma":[0.9990036,0.0001121911,0.0001665287,0.0002647853,0.000394294,0.00005857033],"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":[0.0000307487,0.0000501058,0.0003311543,0.0007946293,0.00005286181,0.00000120289,0.01096125,0.0001574521,0.000008187736,0.002415096,0.000113952,0.9850833],"study_design_scores_gemma":[0.01082894,0.0007833523,0.2095532,0.01383321,0.0005452423,0.00008995872,0.03421158,0.6736318,0.007769955,0.01246736,0.03304548,0.003239921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02621906,0.0001731194,0.957375,0.000148894,0.0002330283,0.001003557,0.000003979505,0.0002590443,0.01458425],"genre_scores_gemma":[0.9898548,0.00004095025,0.008683961,0.00005866409,0.00001672738,0.0008034965,0.00001531395,0.000007349074,0.0005187819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818434,"threshold_uncertainty_score":0.699689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400676476","doi":"10.1016/j.ipm.2024.103831","title":"Homogeneous graph neural networks for third-party library recommendation","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Homogeneous; Computer science; Graph; Third party; Artificial neural network; World Wide Web; Information retrieval; Theoretical computer science; Artificial intelligence; Internet privacy; Combinatorics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01385868293302533,"gpt":0.2466361661788818,"spread":0.2327774832458565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003258338,0.0001429155,0.0001090833,0.0003118982,0.0002139386,0.002215098,0.0004283212,0.0000541777,0.00000849676],"category_scores_gemma":[0.000002714858,0.0001247319,0.0000737875,0.0005082298,0.00001106507,0.00715573,0.0001948233,0.00009194115,0.00001542102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003332887,"about_ca_system_score_gemma":0.0000195361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002539705,"about_ca_topic_score_gemma":4.318476e-7,"domain_scores_codex":[0.998965,0.0000220398,0.0004376576,0.0001987111,0.0001477382,0.0002288459],"domain_scores_gemma":[0.9995295,0.0000283391,0.0001312194,0.0002214563,0.00004309437,0.00004640621],"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":[0.000003017067,0.00000906364,0.000007931631,0.0004299824,0.00001924082,0.000001570373,0.0003614743,0.0004898176,3.235435e-7,0.03513505,0.05697139,0.9065711],"study_design_scores_gemma":[0.00008948681,0.00002738838,0.00003926222,0.00008715472,0.000007955492,0.000009511847,0.00004356513,0.6496555,0.00006146517,0.007861371,0.341989,0.00012845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005855713,0.0002941955,0.9730971,0.003044887,0.0008510451,0.0005764747,0.000003713268,0.001609834,0.0204642],"genre_scores_gemma":[0.8010054,0.0002131766,0.1918158,0.004344475,0.0002607286,0.0009038458,0.000324741,0.00003208529,0.001099746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9064427,"threshold_uncertainty_score":0.9988207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076846377","doi":"10.1016/j.ipm.2012.12.001","title":"CIDER: Concept-based image diversification, exploration, and retrieval","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina; Memorial University of Newfoundland","funders":"","keywords":"Information retrieval; Computer science; Image retrieval; Query expansion; Visual Word; Web query classification; Key (lock); Automatic image annotation; Filter (signal processing); Web search query; Image (mathematics); Search engine; Artificial intelligence; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.01259878672133456,"gpt":0.2497941533249294,"spread":0.2371953666035949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001801174,0.000121518,0.00009016964,0.0001900973,0.000259713,0.0009503443,0.0003472645,0.00003396349,0.00002339717],"category_scores_gemma":[0.00004107808,0.0001151787,0.00002058021,0.0004625583,0.00006899778,0.01489243,0.0001620643,0.0000682728,0.0001258517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000479429,"about_ca_system_score_gemma":0.00002624007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005287876,"about_ca_topic_score_gemma":7.270558e-8,"domain_scores_codex":[0.9990106,0.00001828532,0.0003285662,0.0001720384,0.0003002806,0.0001702951],"domain_scores_gemma":[0.9990283,0.0000174543,0.0002194737,0.0002804682,0.0003920547,0.00006226039],"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":[0.000006494893,0.00002177487,0.00002814325,0.0001572985,0.000007874157,0.000001235649,0.001348036,0.00005716726,0.0001435498,0.01157726,0.005715747,0.9809354],"study_design_scores_gemma":[0.003981317,0.0003730208,0.01578673,0.0005283742,0.00007635699,0.00001690773,0.004170022,0.3744732,0.1756141,0.1842136,0.238686,0.002080372],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002116078,0.00007296753,0.9926592,0.002683401,0.00004635876,0.0004659822,0.000001061654,0.0004576819,0.003401787],"genre_scores_gemma":[0.4676257,0.0001043859,0.5286964,0.003100917,0.00002488512,0.00009672657,0.00004794027,0.00000880815,0.0002942298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.978855,"threshold_uncertainty_score":0.9988858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390628433","doi":"10.1016/j.ipm.2023.103618","title":"Learning dual disentangled representation with self-supervision for temporal knowledge graph reasoning","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Dual (grammatical number); Computer science; Graph; Knowledge representation and reasoning; Representation (politics); Knowledge graph; Self representation; Artificial intelligence; Natural language processing; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.009978764082536066,"gpt":0.2720464982081892,"spread":0.2620677341256531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002849075,0.0001806129,0.000125876,0.0003816127,0.0003911447,0.00108905,0.0002757263,0.000040884,0.000002054017],"category_scores_gemma":[0.00001310337,0.0001509047,0.00006041029,0.001267439,0.00002375975,0.006065512,0.000172626,0.0001564966,0.00002353207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007671351,"about_ca_system_score_gemma":0.00003483568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002081287,"about_ca_topic_score_gemma":0.000001815839,"domain_scores_codex":[0.9986764,0.00003019869,0.0003688225,0.0003112563,0.0003296009,0.0002837157],"domain_scores_gemma":[0.9993651,0.00005358538,0.0001501747,0.0002238098,0.0001442406,0.0000631083],"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":[0.0000367026,0.00003269617,0.0003868862,0.0009105211,0.00005478278,0.00001322434,0.006380739,0.01500078,0.000006621246,0.02783925,0.0009035282,0.9484342],"study_design_scores_gemma":[0.0006077387,0.0001364841,0.0007866361,0.0006159233,0.00004014597,0.00001664208,0.0008565345,0.9631639,0.0001020162,0.003753599,0.02962868,0.0002917318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005865911,0.0003037466,0.9873315,0.0003159165,0.0003034587,0.000652806,8.942719e-7,0.001331661,0.003894123],"genre_scores_gemma":[0.8065377,0.00004278866,0.1925904,0.0001184751,0.00006772834,0.0002045783,0.00008120011,0.00001800741,0.0003391604],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9481631,"threshold_uncertainty_score":0.9999479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400762117","doi":"10.1016/j.ipm.2024.103842","title":"ChatGPT paraphrased product reviews can confuse consumers and undermine their trust in genuine reviews. Can you tell the difference?","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":20,"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":"Product (mathematics); Psychology; Sociology; Marketing; Law and economics; Computer science; Public relations; Business; Epistemology; Positive economics; Actuarial science; Economics; Political science; Philosophy; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04092221032332152,"gpt":0.3111341930348229,"spread":0.2702119827115014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002064819,0.0001920501,0.0002456482,0.0002791212,0.0004110668,0.000862186,0.0002423094,0.00004387758,0.00009789975],"category_scores_gemma":[0.0002016987,0.0001218307,0.00004437201,0.0008228475,0.0002082178,0.001167391,0.00005193755,0.000167363,0.00005543602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001403894,"about_ca_system_score_gemma":0.0001568848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003435323,"about_ca_topic_score_gemma":0.0008517092,"domain_scores_codex":[0.9983481,0.0001319761,0.0007272298,0.0001513674,0.000323393,0.0003178905],"domain_scores_gemma":[0.9993079,0.00003352454,0.000272486,0.0002178102,0.0000600745,0.0001081703],"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":[0.000005219662,0.0000115706,0.0001081898,0.001095709,0.00001118478,8.889675e-7,0.1160853,0.000004001707,0.000002713789,0.002776864,0.003771483,0.8761268],"study_design_scores_gemma":[0.0002943164,0.00001266159,0.003827301,0.0008432271,0.00003365162,0.000002704849,0.01708879,0.001137989,0.00003247032,0.000425157,0.9760896,0.0002121197],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3464905,0.1030494,0.006007892,0.1325915,0.003054745,0.02538629,0.0001765537,0.001462865,0.3817802],"genre_scores_gemma":[0.9578727,0.03344631,0.0002142187,0.00468225,0.00006952172,0.0001059136,0.00007686501,0.00001058589,0.003521612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9723181,"threshold_uncertainty_score":0.831408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318318000","doi":"10.1016/j.ipm.2023.103269","title":"What users’ musical preference on Twitter reveals about psychological disorders","year":2023,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Mental Health via Writing","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Guelph; McMaster University","funders":"","keywords":"Psychology; Preference; Semantics (computer science); Social media; Lyrics; Anxiety; Vocabulary; Cognitive psychology; Sentiment analysis; Applied psychology; Computer science; Natural language processing; World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.09394319717978734,"gpt":0.395566762991283,"spread":0.3016235658114957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006725863,0.0002047577,0.0001721272,0.0003499113,0.0002794177,0.000392294,0.0003216919,0.0001179203,0.0007212816],"category_scores_gemma":[0.00002365656,0.0001853578,0.00004998229,0.0006437568,0.00006413107,0.001595523,0.0001308183,0.0002587155,0.009554151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000932484,"about_ca_system_score_gemma":0.000006932391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006240672,"about_ca_topic_score_gemma":0.000001410913,"domain_scores_codex":[0.9978827,0.00008276002,0.0006646938,0.0003224272,0.0004846937,0.0005626887],"domain_scores_gemma":[0.9991396,0.00005832797,0.0002691394,0.0003734964,0.00004412738,0.0001152876],"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":[0.0001074032,0.0001297389,0.0006487344,0.0005382828,0.00002100234,0.000008383951,0.008552574,0.00006793941,0.000002178507,0.008197046,0.02619967,0.9555271],"study_design_scores_gemma":[0.00279663,0.0004156091,0.7671874,0.001711554,0.00004024718,0.00001169688,0.03125206,0.001503895,0.000009997546,0.008551031,0.1857629,0.0007569983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6772091,0.00005423362,0.001845175,0.003709735,0.00250583,0.001423595,0.000004160773,0.0009351152,0.312313],"genre_scores_gemma":[0.9838122,0.0001090133,0.0004674294,0.01111586,0.00008083601,0.0004398701,0.00009630644,0.00001766273,0.003860795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.95477,"threshold_uncertainty_score":0.991217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3204615515","doi":"10.1016/j.ipm.2021.102746","title":"A semantic approach to post-retrieval query performance prediction","year":2021,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Semantic similarity; Cohesion (chemistry); Query expansion; Graph; Semantics (computer science); Relevance (law); Natural language processing; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01312576929361862,"gpt":0.2335895568102155,"spread":0.2204637875165969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005143846,0.0001626262,0.0001349847,0.0003928554,0.0003685263,0.001148619,0.0005236614,0.00005796588,0.00001718775],"category_scores_gemma":[0.00003950108,0.000154457,0.00005321381,0.001418003,0.00002078901,0.007665143,0.0004009522,0.0001516571,0.0004453999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001312495,"about_ca_system_score_gemma":0.0001525764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002681555,"about_ca_topic_score_gemma":1.756742e-7,"domain_scores_codex":[0.9979709,0.00002778796,0.0005615205,0.000209589,0.0008740927,0.0003560823],"domain_scores_gemma":[0.9985998,0.000008809991,0.0001530367,0.0003983661,0.0006999767,0.0001400374],"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":[0.000062983,0.0001991222,0.0003542008,0.001666767,0.00003682407,0.000008547613,0.008538534,0.005476059,0.000135269,0.02077506,0.001865245,0.9608814],"study_design_scores_gemma":[0.001642982,0.000224307,0.0652001,0.0003627675,0.00005356526,0.000158234,0.003111959,0.8341853,0.006646714,0.000288548,0.08727865,0.0008468669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05616999,0.00002680526,0.8935589,0.0008982045,0.0003643969,0.0005502522,0.000007889792,0.0004560323,0.04796749],"genre_scores_gemma":[0.9347273,0.00002817829,0.05967727,0.003554652,0.00004778978,0.00007148514,0.0001606687,0.00000854569,0.001724145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9600345,"threshold_uncertainty_score":0.9998883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1547627874","doi":"10.1016/s0306-4573(99)00048-5","title":"Passage-based query refinement","year":2000,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Query expansion; Task (project management); Set (abstract data type); Interface (matter); Construct (python library); Relevance feedback; Function (biology); Term (time); Artificial intelligence; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.01105825729091549,"gpt":0.2256217825757446,"spread":0.2145635252848291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000304112,0.0001136361,0.00008124186,0.000158979,0.0001704172,0.0004967003,0.0005200091,0.00002928117,0.0001453994],"category_scores_gemma":[0.000003902423,0.0001084719,0.00003159877,0.0003002924,0.00001259666,0.00226171,0.00008350247,0.00006881224,0.0003914949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007895874,"about_ca_system_score_gemma":0.00003866623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009172597,"about_ca_topic_score_gemma":7.95476e-7,"domain_scores_codex":[0.9988099,0.0000154088,0.0003803901,0.000159313,0.0004128227,0.0002221654],"domain_scores_gemma":[0.9993706,0.000006562733,0.0001090616,0.0004080653,0.00005666124,0.00004901322],"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":[0.000002881267,0.00001711687,0.00001491613,0.0001176869,0.000004694369,0.00000199428,0.0003306249,0.01459855,6.904581e-7,0.009579666,0.0009991897,0.974332],"study_design_scores_gemma":[0.0005072736,0.00001594553,0.0006508075,0.0001017096,0.000007319525,0.000001651009,0.00006000839,0.6701916,0.00009925999,0.00209033,0.3260739,0.0002001878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001447855,0.00003137556,0.8688098,0.002002307,0.0001006526,0.0001883685,4.462928e-7,0.0003670645,0.1270521],"genre_scores_gemma":[0.7477475,0.00001687217,0.2427081,0.006905735,0.00004173433,0.0001087548,0.00001847795,0.000007360783,0.002445396],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9741318,"threshold_uncertainty_score":0.5032006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101143571","doi":"10.1016/j.ipm.2013.08.005","title":"You have e-mail, what happens next? Tracking the eyes for genre","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; Arts and Humanities Research Council; National Natural Science Foundation of China","keywords":"Disk formatting; Computer science; Metric (unit); Eye tracking; Information retrieval; Natural language processing; Representation (politics); Interpretation (philosophy); Tracking (education); Block (permutation group theory); Artificial intelligence; World Wide Web; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03575201494546505,"gpt":0.2791742121898664,"spread":0.2434221972444013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007258931,0.00014228,0.0001013738,0.0001238292,0.0006639536,0.005390839,0.0007186913,0.00005058055,0.00002838547],"category_scores_gemma":[0.00003512372,0.0001041247,0.00006070387,0.0002627888,0.00003469687,0.01653673,0.0002056739,0.0001104305,0.0002657694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005612923,"about_ca_system_score_gemma":0.000029032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006933923,"about_ca_topic_score_gemma":0.000001242979,"domain_scores_codex":[0.9987447,0.00002803366,0.0004202287,0.0001629439,0.0003247517,0.000319313],"domain_scores_gemma":[0.9990451,0.00004440823,0.0002734956,0.0003209021,0.000258801,0.00005728586],"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":[0.000002388167,0.000008152403,0.00002412821,0.0001574412,0.00001190695,2.294113e-7,0.004004942,0.0003715541,0.000006457792,0.03173919,0.00127051,0.9624031],"study_design_scores_gemma":[0.0006592249,0.00004099531,0.002897265,0.0003074193,0.00003067882,0.000007997246,0.01632308,0.644284,0.001118914,0.01880548,0.315073,0.0004518985],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001583513,0.0002767261,0.984196,0.007965466,0.000390256,0.0009707466,0.000001019523,0.0002420274,0.004374247],"genre_scores_gemma":[0.9453433,0.00008006245,0.04738606,0.005572483,0.00007748402,0.0004492449,0.00004052364,0.000009961789,0.00104084],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9619512,"threshold_uncertainty_score":0.9972185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991547055","doi":"10.1016/j.ipm.2013.08.002","title":"An investigation into the application of ensemble learning for entailment classification","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"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":"Invest Northern Ireland","keywords":"Ensemble learning; Artificial intelligence; Natural language processing; Computer science; Textual entailment; Logical consequence; Machine learning; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.01624298343117253,"gpt":0.2641613966963166,"spread":0.2479184132651441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004144228,0.00009766335,0.00007748193,0.0001962327,0.0003140537,0.0004556287,0.0006758583,0.00004656944,0.000003098465],"category_scores_gemma":[0.00002133041,0.00007611208,0.00002734063,0.0004241472,0.00006198425,0.004365013,0.00008647625,0.00006625592,0.00005052456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007296225,"about_ca_system_score_gemma":0.00002616651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000331738,"about_ca_topic_score_gemma":0.00000173273,"domain_scores_codex":[0.9989577,0.00002749278,0.0004440363,0.0001614916,0.0002764468,0.000132859],"domain_scores_gemma":[0.9987262,0.00002834992,0.0005171546,0.00042001,0.0002784225,0.00002985018],"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":[0.000001703744,0.00001607095,0.0002855588,0.0001031973,0.000005348565,4.184065e-9,0.002998224,0.0005840923,0.001474796,0.1610728,0.0002376478,0.8332206],"study_design_scores_gemma":[0.0003370895,0.00008286645,0.01977593,0.00003114904,0.00001475632,4.142528e-7,0.006715403,0.8732471,0.01055735,0.07088366,0.01817918,0.0001750394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01869374,0.00002392762,0.9756303,0.003318352,0.00004785634,0.001052921,1.602449e-7,0.000346279,0.0008864488],"genre_scores_gemma":[0.9311954,0.00001397484,0.0671566,0.0002558943,0.000009644406,0.001214602,0.00005058853,0.00000401027,0.00009928241],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9125017,"threshold_uncertainty_score":0.4393638,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057348139","doi":"10.1016/j.ipm.2013.07.004","title":"An empirical investigation of Web session workloads: Can self-similarity be explained by deterministic chaos?","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":false,"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":"Session (web analytics); Computer science; Similarity (geometry); CHAOS (operating system); Self-similarity; Information retrieval; Empirical research; Data mining; World Wide Web; Artificial intelligence; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01252282015519443,"gpt":0.2760930668669224,"spread":0.2635702467117279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002333235,0.0001722637,0.0001933474,0.0001827379,0.0001839988,0.0002545651,0.0002361458,0.00004250702,0.0001691943],"category_scores_gemma":[0.000003022402,0.000162449,0.0000513466,0.0003929803,0.00004453635,0.001563246,0.00008859049,0.0001065464,0.00001172462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005756883,"about_ca_system_score_gemma":0.00004693732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005482432,"about_ca_topic_score_gemma":0.000003202027,"domain_scores_codex":[0.9986882,0.00005278671,0.000579224,0.0001559144,0.0003177344,0.000206127],"domain_scores_gemma":[0.9989864,0.00001538885,0.0004489305,0.0002716289,0.0001794142,0.00009818938],"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":[0.0000263295,0.000429036,0.09233819,0.0008569767,0.0002324389,6.656925e-7,0.01054269,0.0007521972,0.0009109111,0.00202129,0.05325731,0.838632],"study_design_scores_gemma":[0.001810068,0.0002327691,0.05304037,0.000718046,0.0004336572,0.000001172984,0.007460277,0.8799985,0.006823783,0.02436648,0.02380619,0.001308711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8810711,0.00002129089,0.1050348,0.001247214,0.00006337004,0.001065119,0.0000260914,0.0005099773,0.01096105],"genre_scores_gemma":[0.989122,0.000002724973,0.009769435,0.0004533342,0.00004043998,0.0001726992,0.0003880588,0.000009604298,0.00004175823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8792463,"threshold_uncertainty_score":0.662448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969174204","doi":"10.1016/s0306-4573(03)00007-4","title":"A nearly-optimal Fano-based coding algorithm","year":2003,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; University of Windsor","funders":"","keywords":"Huffman coding; Fano plane; Algorithm; Lossless compression; Computer science; Shannon–Fano coding; Coding (social sciences); Data compression; Theoretical computer science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.009329930075609541,"gpt":0.2300662805095044,"spread":0.2207363504338949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003870346,0.0001509642,0.0001095882,0.0002223517,0.0003502201,0.00103312,0.0005339948,0.00004140626,0.00002569041],"category_scores_gemma":[0.00001479032,0.000137888,0.0000386567,0.0004716975,0.00002391147,0.004611252,0.0001737779,0.00009905601,0.0001572131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006350296,"about_ca_system_score_gemma":0.00006659489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004527163,"about_ca_topic_score_gemma":1.073681e-7,"domain_scores_codex":[0.9986721,0.00002870003,0.0003549959,0.0001960958,0.0004618576,0.0002862863],"domain_scores_gemma":[0.9992136,0.00001392626,0.000197045,0.0003837971,0.0001121559,0.0000794831],"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":[0.000001820417,0.00002766205,0.000009163417,0.00008637738,0.00000655625,0.000004492271,0.0003433031,0.002159501,0.000002647096,0.01557544,0.001229006,0.980554],"study_design_scores_gemma":[0.0005388582,0.00002355864,0.0002301631,0.00008889313,0.000007023364,0.000005652603,0.0001268761,0.8058408,0.0004566408,0.0004768281,0.1919979,0.0002068834],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001552316,0.00004712106,0.985248,0.0001591536,0.0002346954,0.0002047314,0.00000277505,0.0002887019,0.01365959],"genre_scores_gemma":[0.08142995,0.000009084544,0.9168441,0.001305021,0.0000226165,0.00005493753,0.00003502975,0.000007534042,0.0002916971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9803472,"threshold_uncertainty_score":0.9962395,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406915783","doi":"10.1016/j.ipm.2025.104069","title":"Bridging in-task emotional responses with post-task evaluations in digital library search interface user studies","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bridging (networking); Digital library; Task (project management); Computer science; Interface (matter); Human–computer interaction; User interface; Information retrieval; World Wide Web; Cognitive psychology; Psychology; Engineering; Programming language; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1273030418214271,"gpt":0.442975381671413,"spread":0.3156723398499859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001784515,0.0002047583,0.0002396823,0.002808244,0.0002470616,0.002175668,0.0006062583,0.00004426445,0.0001007576],"category_scores_gemma":[0.0003214386,0.0001622068,0.00004983972,0.002394503,0.0001106324,0.01522901,0.0005016456,0.0001947174,0.0003703909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001820342,"about_ca_system_score_gemma":0.0001845282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005838674,"about_ca_topic_score_gemma":0.00001583811,"domain_scores_codex":[0.9967345,0.00007571664,0.001163588,0.000267296,0.001441264,0.0003176305],"domain_scores_gemma":[0.998744,0.0001986451,0.0002684461,0.0003015062,0.0004404174,0.00004701856],"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":[0.0005737157,0.0001844603,0.1068203,0.0004151305,0.00008291922,0.00001241864,0.01179586,0.02571141,0.000005634211,0.006125369,0.01208356,0.8361893],"study_design_scores_gemma":[0.002857304,0.00009889391,0.8250878,0.001563111,0.00005028156,0.000005876017,0.06219769,0.04692636,0.00009227389,0.004074784,0.05646846,0.0005771052],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9290705,0.0002416596,0.03307049,0.00803827,0.0001952709,0.001095951,0.00006709842,0.0001779437,0.02804283],"genre_scores_gemma":[0.9896278,0.00002716012,0.001163962,0.001349882,0.00001156215,0.0000940027,0.00009412714,0.000007240955,0.007624255],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8356122,"threshold_uncertainty_score":0.9988602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3124933699","doi":"10.1016/j.ipm.2021.102503","title":"Learning to rank implicit entities on Twitter","year":2021,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Relevance (law); Graph; Representation (politics); Rank (graph theory); Learning to rank; Context (archaeology); Feature (linguistics); Natural language processing; Entity linking; Artificial intelligence; Knowledge base; Ranking (information retrieval); Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01515660422481049,"gpt":0.2522781744710504,"spread":0.2371215702462399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195519,0.00009121808,0.00007846071,0.0001758679,0.000181813,0.0008029549,0.0003114384,0.00002152013,0.00002266428],"category_scores_gemma":[0.00001975079,0.00009185184,0.00002674863,0.0003148091,0.000005184373,0.001559361,0.0002950678,0.00009190649,0.0003535998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005903408,"about_ca_system_score_gemma":0.00002616488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002981721,"about_ca_topic_score_gemma":4.379555e-7,"domain_scores_codex":[0.9990379,0.00001713162,0.0002603829,0.0001588398,0.0003323971,0.0001933448],"domain_scores_gemma":[0.9994909,0.000009542304,0.0000809367,0.0002621548,0.0001105847,0.00004586506],"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":[0.000003028679,0.0000127499,0.00005112208,0.000178879,0.00001134326,0.000006781855,0.007767369,0.02926256,0.00001981536,0.02620356,0.001270392,0.9352124],"study_design_scores_gemma":[0.001015018,0.0000931877,0.003760432,0.0005631181,0.00002045052,0.00001958781,0.005373918,0.3833522,0.003018784,0.007257625,0.5948372,0.0006884485],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01508348,0.00001538641,0.9190452,0.002251711,0.0002118502,0.0001213044,1.573491e-7,0.0002201783,0.06305071],"genre_scores_gemma":[0.9225938,0.000007018598,0.06533907,0.008180067,0.00004326705,0.0000455549,0.000007366144,0.000005507395,0.003778359],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9345239,"threshold_uncertainty_score":0.7742912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106388373","doi":"10.1016/j.ipm.2006.07.006","title":"Contextual feature selection for text classification","year":2006,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Computer science; Feature selection; Selection (genetic algorithm); Set (abstract data type); Filter (signal processing); Feature (linguistics); Information retrieval; Artificial intelligence; Data set; Simple (philosophy); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01355166644046986,"gpt":0.2484269728550914,"spread":0.2348753064146216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002119197,0.0001242126,0.00008759966,0.0002985961,0.0003129859,0.0007585027,0.0004569902,0.00007986478,0.000004744578],"category_scores_gemma":[0.0000169741,0.000116957,0.00004045977,0.0005321605,0.00003147667,0.003606564,0.00007274961,0.0000726302,0.00007328501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001135724,"about_ca_system_score_gemma":0.00002842137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004926117,"about_ca_topic_score_gemma":0.00000290776,"domain_scores_codex":[0.9990277,0.000009441575,0.000320624,0.000185944,0.0002538463,0.0002024165],"domain_scores_gemma":[0.9992192,0.00001722092,0.0003003244,0.0002337918,0.0002090713,0.00002035495],"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":[0.000005299148,0.00002154999,0.00006723826,0.00007507172,0.000004753474,4.280996e-8,0.00009465446,0.00008718928,0.00008632907,0.405114,0.02218106,0.5722628],"study_design_scores_gemma":[0.0009453513,0.00005582329,0.02061323,0.00004525199,0.0000187537,0.000004343916,0.0006796308,0.2236008,0.002159437,0.03635827,0.715178,0.0003411766],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005657965,0.00004761372,0.9747341,0.003883165,0.0001336529,0.0005448034,0.000001902325,0.00104335,0.01904564],"genre_scores_gemma":[0.9032106,0.000007654725,0.09319261,0.0003962839,0.00004024611,0.000353814,0.00007857781,0.000005585226,0.00271464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9026448,"threshold_uncertainty_score":0.7314259,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1966199653","doi":"10.1016/j.ipm.2009.10.008","title":"Online community information seeking: The queries of three communities in Southwestern Ontario","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Utah State University","keywords":"World Wide Web; Computer science; Sample (material); Agency (philosophy); Focus group; Data collection; Data science; Knowledge management; Business; Sociology; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.03771764017864286,"gpt":0.2807180141593612,"spread":0.2430003739807183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002180373,0.000136145,0.0001857334,0.0004329849,0.001348245,0.0003635289,0.0005368516,0.00006440236,0.00002418733],"category_scores_gemma":[0.00004564011,0.0001106907,0.00004866672,0.0006226847,0.0002878972,0.005804908,0.0001308745,0.0003195119,0.00002018371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002071775,"about_ca_system_score_gemma":0.0001103149,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08584607,"about_ca_topic_score_gemma":0.3448034,"domain_scores_codex":[0.9980112,0.0001427029,0.0009432757,0.00002979406,0.0006169099,0.0002561032],"domain_scores_gemma":[0.9985417,0.00006668066,0.0006793136,0.0002947485,0.0003888856,0.00002873872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0000213648,0.00006433675,0.02282198,0.0002495338,0.00002376965,9.939478e-8,0.8120217,0.0005948646,9.422237e-8,0.02681756,0.0001531658,0.1372315],"study_design_scores_gemma":[0.0004402072,0.00003536797,0.3798689,0.0002746671,0.00001638634,6.989826e-7,0.5264881,0.0003971271,0.000001170135,0.004009642,0.088316,0.000151706],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6926445,0.00007163836,0.008547064,0.002985244,0.0002902481,0.00151326,0.00002118612,0.0002468784,0.29368],"genre_scores_gemma":[0.9982352,0.00002958172,0.0004275263,0.001029266,0.00001225885,0.00003304558,0.0001033604,0.000002029849,0.0001277242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3570469,"threshold_uncertainty_score":0.9999518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404797297","doi":"10.1016/j.ipm.2024.103991","title":"Trust driven On-Demand scheme for client deployment in Federated Learning","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Software deployment; Scheme (mathematics); Computer science; On demand; Computer network; Computer security; Business; Operating system; Multimedia","retraction":null,"screen_n_in":null,"score":{"opus":0.02108962788082614,"gpt":0.2834194271554673,"spread":0.2623297992746412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006007924,0.0001637967,0.0001253732,0.0005513678,0.0002234058,0.001506493,0.003692542,0.00006783026,0.000005061714],"category_scores_gemma":[0.0006949393,0.0001539099,0.00003526438,0.0007308755,0.00002658924,0.002925881,0.007428916,0.0002292758,0.00009908804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002582908,"about_ca_system_score_gemma":0.00004602653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002955846,"about_ca_topic_score_gemma":0.000001381717,"domain_scores_codex":[0.9985265,0.00001997056,0.0004551462,0.0003104269,0.0003589444,0.0003290573],"domain_scores_gemma":[0.9987894,0.00004771526,0.0001198098,0.0009487195,0.00005979527,0.00003457992],"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":[0.00001784312,0.00005255947,0.0001794536,0.001067733,0.00003814015,0.00001309397,0.0006423564,0.004153402,0.00001701929,0.02124765,0.04104313,0.9315276],"study_design_scores_gemma":[0.0003830395,0.00005697679,0.0003137432,0.0004826125,0.000005061432,0.000001980246,0.0001879556,0.9086087,0.000364146,0.01416194,0.07525384,0.0001799694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006815152,0.0001491105,0.9733808,0.009949552,0.0003484433,0.0007724618,0.000003560454,0.00181815,0.006762768],"genre_scores_gemma":[0.7420679,0.00007621323,0.256391,0.0006835915,0.0000240012,0.0004442045,0.00006702501,0.00001704158,0.0002290158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9313477,"threshold_uncertainty_score":0.99953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7102416460","doi":"10.1016/j.ipm.2025.104460","title":"Text-free inductive knowledge graph embedding via meta graph-based prompt learning","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Central China Normal University; China Postdoctoral Science Foundation; National Social Science Fund of China; Natural Science Foundation of Hubei Province; Ministry of Education of the People's Republic of China; National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; National Natural Science Foundation of China","keywords":"Embedding; Graph; Knowledge graph; Node (physics); Inductive bias; Construct (python library); Bridge (graph theory); Entity linking","retraction":null,"screen_n_in":null,"score":{"opus":0.01363896010083808,"gpt":0.2767357352978942,"spread":0.2630967751970561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004744678,0.000304644,0.0002824781,0.001137758,0.0006271331,0.000635245,0.001366257,0.00008073502,0.000007005689],"category_scores_gemma":[0.00003712722,0.0002794549,0.0001572667,0.002969985,0.00008529184,0.004925395,0.0007211422,0.0003795154,0.00003067997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009401307,"about_ca_system_score_gemma":0.00005113104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003240475,"about_ca_topic_score_gemma":0.000001962391,"domain_scores_codex":[0.998098,0.00007808366,0.0005989728,0.0003799435,0.0004015774,0.00044348],"domain_scores_gemma":[0.9985432,0.00006226667,0.0004044024,0.000643502,0.000274451,0.00007215956],"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":[0.00001666329,0.00006504763,0.00006211209,0.0005009265,0.0002513272,0.000003625707,0.001128539,0.07999313,0.00001829189,0.04167547,0.001642125,0.8746427],"study_design_scores_gemma":[0.001786328,0.00009006985,0.001374674,0.0005301058,0.0003135045,0.000004176378,0.0004346938,0.7905546,0.001074373,0.1282654,0.07473745,0.0008345998],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004273395,0.0005504582,0.980009,0.0007000549,0.0003409125,0.0005821279,6.621563e-7,0.0007033614,0.01668609],"genre_scores_gemma":[0.7791265,0.00004377469,0.2180574,0.001597855,0.00003451382,0.0004645259,0.00002476295,0.0000196466,0.0006310017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8738081,"threshold_uncertainty_score":0.9999658,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}