{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":7,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":7,"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","author_layer_release":"2026-06-26"},"query_hash":"cfbfb6b305e9","filters":{"venue":"CLEF (Working Notes)"}},"results":[{"id":"W2293603645","doi":"","title":"Proximity based one-class classification with Common N-Gram dissimilarity for authorship verification task Notebook for PAN at CLEF 2013","year":2013,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Ranking (information retrieval); Computer science; Task (project management); Set (abstract data type); Sample (material); Clef; Artificial intelligence; Natural language processing; Class (philosophy); Test set; Information retrieval; Thresholding; Image (mathematics)","authors":[{"name":"Magdalena Jankowska","is_ca":true},{"name":"Vlado Kešelj","is_ca":false},{"name":"Evangelos Milios","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1031538075269358,"gpt":0.2999491541458553,"spread":0.1967953466189195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00146464,0.0003544296,0.0003772192,0.0001300119,0.0009618811,0.0004815418,0.0009394116,0.000399272,0.00002151373],"category_scores_gemma":[0.0003813986,0.0003262409,0.0001794506,0.0004222612,0.0001430345,0.0005989426,0.000128469,0.0003983036,0.00007133939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003515195,"about_ca_system_score_gemma":0.0001558016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000062657,"about_ca_topic_score_gemma":0.0001257959,"domain_scores_codex":[0.9970678,0.0002778085,0.0005523541,0.0009552183,0.0004245957,0.0007222387],"domain_scores_gemma":[0.9964428,0.001214605,0.0005122257,0.001143391,0.0004081134,0.0002788819],"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":[0.001485291,0.001627514,0.1052018,0.001115441,0.0002313563,0.000003523827,0.003850576,0.001214652,0.04257915,0.2855915,0.009551205,0.547548],"study_design_scores_gemma":[0.001692811,0.0003805282,0.1289374,0.000237736,0.00007977845,0.000003768661,0.00003199785,0.8069423,0.01942038,0.01492461,0.02647809,0.0008706143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05076475,0.00003897691,0.9313402,0.01335225,0.0004464129,0.003298689,0.00003518382,0.0005377888,0.0001857133],"genre_scores_gemma":[0.904985,0.000003717308,0.09235565,0.0007756526,0.0001987892,0.001114459,0.0003118709,0.00004431329,0.0002106161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8542202,"threshold_uncertainty_score":0.9999189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121963504","doi":"","title":"Morphological acquisition by Formal Analogy","year":2009,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Analogy; Morpheme; Lexicon; Computer science; Artificial intelligence; Relation (database); Natural language processing; Reading (process); Task (project management); Linguistics","authors":[{"name":"Jean-François Lavallée","is_ca":true},{"name":"Philippe Langlais","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.016276388832739,"gpt":0.2713648424350661,"spread":0.2550884536023271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002757669,0.0001456593,0.0001536174,0.000078378,0.0001658554,0.0001817523,0.000855519,0.0001691278,0.00001887333],"category_scores_gemma":[0.00006876399,0.0001224075,0.00006124353,0.0003658222,0.00003999393,0.0004519697,0.0001693603,0.000276466,0.00002697666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005228859,"about_ca_system_score_gemma":0.00001517158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005315798,"about_ca_topic_score_gemma":5.333111e-7,"domain_scores_codex":[0.9987795,0.00004869145,0.0001845884,0.0003691904,0.0002076317,0.0004103745],"domain_scores_gemma":[0.9993266,0.00008936141,0.00009258442,0.0003746041,0.00004226897,0.0000745258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002019769,0.0001057359,0.00060652,0.00000569583,0.000006791115,0.0002005016,0.0002303935,0.00001056271,0.04606193,0.07364029,0.006330645,0.8727807],"study_design_scores_gemma":[0.001482685,0.001596674,0.01481753,0.0003527445,0.00003888486,0.001199029,0.00001928095,0.03755906,0.2371319,0.6830694,0.02058615,0.002146654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02487552,0.001897713,0.9677819,0.003053115,0.0001907091,0.0001004178,0.000001181892,0.001194359,0.0009051135],"genre_scores_gemma":[0.7855218,0.000009347699,0.2108445,0.00347227,0.0001105044,0.000002823444,0.000009530242,0.000004784426,0.00002438102],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8706341,"threshold_uncertainty_score":0.4991634,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2407284108","doi":"","title":"CNG Text Classification for Authorship Profiling Task Notebook for PAN at CLEF 2013.","year":2013,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Clef; Classifier (UML); Computer science; Artificial intelligence; Natural language processing; Profiling (computer programming); Task (project management); Engineering","authors":[{"name":"Magdalena Jankowska","is_ca":true},{"name":"Vlado Kešelj","is_ca":false},{"name":"Evangelos Milios","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09971323396320451,"gpt":0.3079831026126824,"spread":0.2082698686494778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001605465,0.0003451543,0.0003434581,0.0001669249,0.0009339014,0.0004831333,0.001043412,0.0003927433,0.00003618276],"category_scores_gemma":[0.0007839981,0.0003345808,0.0002622263,0.0003941894,0.00008571427,0.000515471,0.0002749847,0.0003467638,0.0004031521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002676326,"about_ca_system_score_gemma":0.0001135638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002371248,"about_ca_topic_score_gemma":0.00001591644,"domain_scores_codex":[0.9969988,0.0001663393,0.0006301531,0.000946853,0.0003364088,0.0009214121],"domain_scores_gemma":[0.996578,0.001545945,0.0004070116,0.0008531056,0.000351099,0.0002648044],"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":[0.0001698053,0.0001860701,0.01434676,0.0003751654,0.0001044634,0.000002760937,0.003481017,0.0003409523,0.08161101,0.3328179,0.01149626,0.5550678],"study_design_scores_gemma":[0.001881536,0.0002881557,0.01612941,0.0003271121,0.00007420145,0.0000191976,0.0001388053,0.7447481,0.06376625,0.05551003,0.1156239,0.001493226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03140209,0.0002149952,0.9562427,0.006931591,0.001518854,0.002601989,0.00001702273,0.0005945063,0.0004762727],"genre_scores_gemma":[0.8737611,0.00001022103,0.1227655,0.0007658781,0.0006034938,0.0007368668,0.0001010159,0.00005120478,0.001204756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8423589,"threshold_uncertainty_score":0.9999106,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2408019706","doi":"","title":"A MARFCLEF Approach to LifeCLEF 2015 Tasks","year":2015,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Task (project management); Pipeline (software); Set (abstract data type); Artificial intelligence; Modular design; Machine learning; Programming language; Engineering","authors":[{"name":"Serguei A. Mokhov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08771624813871608,"gpt":0.2885322312016201,"spread":0.200815983062904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007858613,0.0002391635,0.0002660809,0.0001415353,0.0001895625,0.000459473,0.001322175,0.0001243591,0.00000709188],"category_scores_gemma":[0.0002617845,0.0002197179,0.00007802789,0.000822375,0.0000494143,0.0003527319,0.0006625864,0.0002708447,0.0003951423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009441734,"about_ca_system_score_gemma":0.0001788953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002758598,"about_ca_topic_score_gemma":0.000002476515,"domain_scores_codex":[0.997849,0.00007416,0.0002828618,0.0006883865,0.0005170029,0.0005885616],"domain_scores_gemma":[0.9983438,0.00009887432,0.0001176323,0.0008122352,0.0001192644,0.0005082573],"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":[0.00004775139,0.0004453726,0.007542467,0.00008295826,0.00005922017,0.00006657845,0.01235539,0.003577071,0.0009494668,0.03065327,0.1787897,0.7654308],"study_design_scores_gemma":[0.002208693,0.0003003661,0.007818515,0.0005099159,0.00004538298,0.0001938342,0.0003104859,0.117864,0.003449537,0.01671364,0.8483614,0.002224199],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01303089,0.0004746,0.9304103,0.005223823,0.001245345,0.0002530611,0.000001086413,0.0005598802,0.04880101],"genre_scores_gemma":[0.8495546,0.000002379142,0.1432162,0.006058441,0.0006693381,0.00001894296,0.000003215475,0.00002580691,0.0004510531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8365237,"threshold_uncertainty_score":0.8959837,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2293627165","doi":"","title":"Bridging Layperson's Queries with Medical Concepts- GRIUM@CLEF2015 eHealth Task 2","year":2015,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Layperson; Computer science; Information retrieval; Task (project management); eHealth; Unified Medical Language System; Bridge (graph theory); Bridging (networking); Readability; Automatic summarization; World Wide Web; Data science; Health care; Medicine","authors":[{"name":"Xiao Jie Liu","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03709580862023832,"gpt":0.3136849472681744,"spread":0.2765891386479361,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000638629,0.0002330158,0.0002772747,0.00003916072,0.0001351668,0.00004750994,0.0003445356,0.0003854976,0.00002234166],"category_scores_gemma":[0.001297524,0.0001796782,0.00006647186,0.0001566168,0.0005945922,0.000004148636,0.0001731672,0.0003120463,0.00002912715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003799649,"about_ca_system_score_gemma":0.0004590748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001107976,"about_ca_topic_score_gemma":0.0001563264,"domain_scores_codex":[0.9981393,0.0001191474,0.0002303298,0.0004859856,0.0005072156,0.0005180492],"domain_scores_gemma":[0.9988451,0.00008918044,0.0001129274,0.0003768334,0.0001010096,0.0004749628],"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":[0.001152982,0.0003296573,0.1346603,0.0001234507,0.0003591088,0.0004114429,0.003294427,0.0001027222,0.007849087,0.0008171494,0.1112872,0.7396125],"study_design_scores_gemma":[0.004448353,0.002242327,0.01087356,0.0006846017,0.00008193855,0.0005335058,0.0022308,0.0008887696,0.01549391,0.0001942977,0.9610453,0.001282654],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9635236,0.004335468,0.01824004,0.007656865,0.001169379,0.0002342828,0.00001522998,0.0002510291,0.004574049],"genre_scores_gemma":[0.9931331,0.000103682,0.003140792,0.002068046,0.001159778,0.00001342183,0.00008204798,0.00003627796,0.0002628469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8497581,"threshold_uncertainty_score":0.7327065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157296506","doi":"","title":"CLaC at ImageCLEFPhoto 2008","year":2008,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Task (project management); Relevance (law); Computer science; Information retrieval; Block (permutation group theory); Relevance feedback; Artificial intelligence; Image retrieval; Mathematics; Image (mathematics); Political science; Engineering","authors":[{"name":"Osama El Demerdash","is_ca":true},{"name":"Leila Kosseim","is_ca":true},{"name":"Sabine Bergler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04564596631836694,"gpt":0.2746131458413928,"spread":0.2289671795230259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002058345,0.000228354,0.000242512,0.0001030519,0.0004972963,0.00007315509,0.0009696632,0.0001179038,0.0000475552],"category_scores_gemma":[0.000187718,0.0002150431,0.0001352689,0.0006015195,0.0001525264,0.0005107888,0.0006540372,0.0002846879,0.0003063388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001400098,"about_ca_system_score_gemma":0.00004837986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001684141,"about_ca_topic_score_gemma":0.000003981382,"domain_scores_codex":[0.998228,0.00005390377,0.0002798272,0.0005777144,0.0003455703,0.0005150011],"domain_scores_gemma":[0.9984806,0.0002398525,0.0001265718,0.0009170277,0.00008495209,0.000151034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001425448,0.0004060972,0.05934547,0.00005800704,0.00008044828,0.002410101,0.002961464,0.00009249135,0.06813243,0.01124408,0.07857781,0.776549],"study_design_scores_gemma":[0.0007564483,0.0002193999,0.02858174,0.0001354348,0.00001230743,0.0007558146,0.000008002942,0.003980738,0.51865,0.009791122,0.4360052,0.001103821],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0334942,0.0009719809,0.9559782,0.0006221017,0.0004516358,0.0002450315,0.000001866159,0.001351857,0.006883091],"genre_scores_gemma":[0.8628979,0.0004383296,0.1338242,0.00144235,0.0002225834,0.0000143346,0.000003688463,0.0000286325,0.001127991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8294037,"threshold_uncertainty_score":0.8769202,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888789047","doi":"","title":"Toronto CL CLEF 2018 eHealth Task 1: Multi-lingual ICD-10 Coding using an Ensemble of Recurrent and Convolutional Neural Networks.","year":2018,"lang":"en","type":"article","venue":"CLEF (Working Notes)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Clef; Convolutional neural network; Computer science; eHealth; Coding (social sciences); Artificial intelligence; Speech recognition; Task (project management); Natural language processing; Mathematics; Engineering","authors":[{"name":"Serena Jeblee","is_ca":false},{"name":"Akshay Budhkar","is_ca":false},{"name":"Saša Milić","is_ca":false},{"name":"J. Vantuil L. Pinto","is_ca":false},{"name":"Chloé Pou-Prom","is_ca":false},{"name":"Krishnapriya Vishnubhotla","is_ca":false},{"name":"Graeme Hirst","is_ca":false},{"name":"Frank Rudzicz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08263131018549892,"gpt":0.3588600078983651,"spread":0.2762286977128662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001107767,0.0003069803,0.0004091231,0.00008967119,0.0006640822,0.0001591473,0.0007154597,0.0002093976,0.00003832888],"category_scores_gemma":[0.0003029743,0.0003184911,0.00007858011,0.0002971154,0.0002613517,0.0004540623,0.0004916703,0.0004815612,0.000005799528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003187603,"about_ca_system_score_gemma":0.0001921195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001742738,"about_ca_topic_score_gemma":0.001539386,"domain_scores_codex":[0.996864,0.0004434397,0.0006401519,0.0008325698,0.0004340333,0.0007857553],"domain_scores_gemma":[0.9977124,0.0004822743,0.0004692082,0.0007138461,0.000278393,0.0003439135],"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":[0.000342041,0.0005870591,0.1628203,0.0004432224,0.00009322503,0.00004329991,0.01356368,0.02467601,0.002302697,0.01187424,0.0007551262,0.7824991],"study_design_scores_gemma":[0.0005272313,0.0004622136,0.02522811,0.0002507896,0.00001306909,0.00005153655,0.00005730554,0.9717025,0.000110872,0.0001136547,0.001161773,0.0003210055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6482323,0.002743822,0.3441347,0.0004028968,0.003634626,0.0004010009,0.000008260849,0.0003251131,0.0001172139],"genre_scores_gemma":[0.9445848,0.00005074541,0.05349062,0.0004014056,0.001400244,0.000004122507,0.00001447153,0.00003452299,0.00001908067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9470264,"threshold_uncertainty_score":0.9999267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}