{"meta":{"query_hash":"cfbfb6b305e9","filters":{"venue":"CLEF (Working Notes)"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/cfbfb6b305e9","api":"https://metacan.xera.ac/api/v1/cohort?venue=CLEF+%28Working+Notes%29"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016276388832739,"score_gpt":0.27136484243506614,"score_spread":0.2550884536023271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121963504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024875518,0.0018977134,0.9677819,0.0030531152,0.00019070914,0.000100417805,0.0000011818918,0.0011943589,0.00090511347],"genre_scores_gemma":[0.7855218,0.000009347699,0.21084453,0.0034722697,0.00011050438,0.0000028234442,0.000009530242,0.0000047844255,0.000024381025],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877954,0.00004869145,0.00018458844,0.00036919044,0.00020763167,0.00041037455],"domain_scores_gemma":[0.99932665,0.00008936141,0.00009258442,0.00037460413,0.000042268966,0.0000745258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027576686,0.00014565929,0.00015361738,0.000078378,0.00016585538,0.00018175229,0.000855519,0.00016912782,0.000018873328],"category_scores_gemma":[0.00006876399,0.00012240752,0.000061243525,0.00036582223,0.000039993927,0.00045196968,0.00016936027,0.00027646605,0.000026976664],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002019769,0.00010573595,0.00060652,0.0000056958297,0.0000067911146,0.00020050163,0.00023039352,0.0000105627105,0.046061933,0.073640294,0.006330645,0.87278074],"study_design_scores_gemma":[0.0014826851,0.0015966742,0.01481753,0.00035274448,0.000038884857,0.0011990286,0.000019280946,0.037559062,0.23713188,0.6830694,0.020586152,0.002146654],"about_ca_topic_score_codex":0.000005315798,"about_ca_topic_score_gemma":5.333111e-7,"teacher_disagreement_score":0.8706341,"about_ca_system_score_codex":0.000052288586,"about_ca_system_score_gemma":0.000015171584,"threshold_uncertainty_score":0.49916342},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04564596631836694,"score_gpt":0.2746131458413928,"score_spread":0.22896717952302587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157296506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033494204,0.00097198086,0.9559782,0.00062210165,0.00045163583,0.00024503152,0.0000018661589,0.0013518566,0.006883091],"genre_scores_gemma":[0.86289793,0.0004383296,0.13382418,0.0014423503,0.00022258336,0.0000143346015,0.0000036884626,0.000028632505,0.0011279907],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99822795,0.00005390377,0.00027982725,0.00057771435,0.00034557027,0.0005150011],"domain_scores_gemma":[0.99848056,0.0002398525,0.00012657185,0.0009170277,0.000084952095,0.00015103404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020583453,0.000228354,0.00024251205,0.00010305189,0.00049729634,0.00007315509,0.0009696632,0.00011790377,0.0000475552],"category_scores_gemma":[0.00018771799,0.00021504308,0.00013526894,0.00060151954,0.00015252637,0.0005107888,0.0006540372,0.00028468794,0.0003063388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014254477,0.00040609716,0.05934547,0.000058007045,0.00008044828,0.0024101008,0.0029614635,0.000092491355,0.06813243,0.011244077,0.07857781,0.77654904],"study_design_scores_gemma":[0.00075644825,0.0002193999,0.028581737,0.00013543482,0.000012307432,0.0007558146,0.000008002942,0.0039807376,0.51865,0.009791122,0.43600518,0.0011038213],"about_ca_topic_score_codex":0.000016841412,"about_ca_topic_score_gemma":0.0000039813817,"teacher_disagreement_score":0.8294037,"about_ca_system_score_codex":0.0001400098,"about_ca_system_score_gemma":0.00004837986,"threshold_uncertainty_score":0.8769202},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.10315380752693581,"score_gpt":0.29994915414585527,"score_spread":0.19679534661891945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293603645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05076475,0.000038976912,0.9313402,0.013352247,0.0004464129,0.0032986891,0.000035183824,0.00053778884,0.00018571332],"genre_scores_gemma":[0.90498495,0.0000037173083,0.092355646,0.0007756526,0.00019878922,0.001114459,0.00031187086,0.00004431329,0.00021061605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970678,0.00027780855,0.0005523541,0.00095521833,0.0004245957,0.0007222387],"domain_scores_gemma":[0.9964428,0.0012146053,0.0005122257,0.0011433911,0.0004081134,0.00027888193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014646399,0.00035442956,0.00037721923,0.00013001193,0.0009618811,0.00048154176,0.00093941164,0.00039927202,0.000021513733],"category_scores_gemma":[0.00038139857,0.0003262409,0.00017945062,0.00042226116,0.0001430345,0.00059894257,0.00012846904,0.00039830361,0.00007133939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014852907,0.0016275141,0.105201766,0.0011154405,0.00023135626,0.0000035238274,0.0038505758,0.0012146521,0.04257915,0.2855915,0.009551205,0.547548],"study_design_scores_gemma":[0.0016928113,0.00038052825,0.12893741,0.00023773602,0.00007977845,0.0000037686607,0.00003199785,0.8069423,0.01942038,0.014924612,0.026478086,0.00087061425],"about_ca_topic_score_codex":0.000062656996,"about_ca_topic_score_gemma":0.0001257959,"teacher_disagreement_score":0.8542202,"about_ca_system_score_codex":0.00035151947,"about_ca_system_score_gemma":0.00015580158,"threshold_uncertainty_score":0.99991894},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03709580862023832,"score_gpt":0.3136849472681744,"score_spread":0.2765891386479361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293627165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9635236,0.0043354677,0.018240042,0.007656865,0.0011693786,0.00023428284,0.0000152299845,0.00025102907,0.004574049],"genre_scores_gemma":[0.9931331,0.00010368196,0.0031407925,0.0020680455,0.0011597783,0.000013421826,0.00008204798,0.000036277957,0.00026284694],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813926,0.00011914742,0.00023032982,0.00048598563,0.00050721556,0.0005180492],"domain_scores_gemma":[0.9988451,0.000089180445,0.00011292739,0.0003768334,0.0001010096,0.00047496284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000638629,0.00023301579,0.00027727472,0.000039160725,0.00013516676,0.00004750994,0.0003445356,0.00038549764,0.000022341655],"category_scores_gemma":[0.0012975241,0.00017967823,0.00006647186,0.00015661676,0.00059459225,0.0000041486355,0.00017316722,0.0003120463,0.000029127154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011529825,0.00032965728,0.13466033,0.00012345072,0.00035910882,0.00041144295,0.0032944267,0.000102722195,0.007849087,0.00081714935,0.11128716,0.73961246],"study_design_scores_gemma":[0.0044483533,0.0022423265,0.01087356,0.00068460166,0.000081938546,0.00053350575,0.0022308002,0.0008887696,0.01549391,0.00019429767,0.96104527,0.0012826545],"about_ca_topic_score_codex":0.00011079756,"about_ca_topic_score_gemma":0.0001563264,"teacher_disagreement_score":0.8497581,"about_ca_system_score_codex":0.000037996495,"about_ca_system_score_gemma":0.00045907477,"threshold_uncertainty_score":0.73270655},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09971323396320451,"score_gpt":0.30798310261268236,"score_spread":0.20826986864947783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407284108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031402092,0.00021499522,0.9562427,0.0069315913,0.0015188543,0.0026019888,0.000017022727,0.00059450633,0.00047627275],"genre_scores_gemma":[0.87376106,0.000010221027,0.122765504,0.00076587807,0.0006034938,0.00073686684,0.00010101591,0.000051204777,0.0012047562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699885,0.00016633928,0.00063015305,0.000946853,0.0003364088,0.0009214121],"domain_scores_gemma":[0.99657804,0.0015459446,0.00040701163,0.0008531056,0.000351099,0.0002648044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016054654,0.0003451543,0.0003434581,0.00016692489,0.0009339014,0.00048313334,0.0010434117,0.00039274327,0.000036182762],"category_scores_gemma":[0.00078399805,0.00033458078,0.00026222633,0.00039418935,0.000085714266,0.00051547104,0.0002749847,0.0003467638,0.00040315208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016980532,0.00018607013,0.014346764,0.0003751654,0.00010446344,0.0000027609372,0.0034810167,0.00034095233,0.08161101,0.3328179,0.011496257,0.55506784],"study_design_scores_gemma":[0.0018815356,0.00028815572,0.01612941,0.0003271121,0.000074201445,0.000019197601,0.00013880528,0.7447481,0.06376625,0.055510025,0.115623936,0.0014932258],"about_ca_topic_score_codex":0.000023712484,"about_ca_topic_score_gemma":0.000015916436,"teacher_disagreement_score":0.84235895,"about_ca_system_score_codex":0.00026763257,"about_ca_system_score_gemma":0.0001135638,"threshold_uncertainty_score":0.9999106},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08771624813871608,"score_gpt":0.28853223120162014,"score_spread":0.20081598306290405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408019706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013030889,0.00047460003,0.9304103,0.005223823,0.0012453451,0.0002530611,0.0000010864135,0.00055988017,0.04880101],"genre_scores_gemma":[0.8495546,0.000002379142,0.14321624,0.0060584405,0.0006693381,0.00001894296,0.0000032154746,0.000025806912,0.00045105306],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784905,0.00007416,0.00028286185,0.0006883865,0.00051700295,0.00058856164],"domain_scores_gemma":[0.99834377,0.00009887432,0.0001176323,0.0008122352,0.000119264434,0.0005082573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078586134,0.00023916355,0.00026608093,0.00014153532,0.00018956246,0.00045947303,0.0013221749,0.00012435908,0.0000070918795],"category_scores_gemma":[0.00026178453,0.00021971793,0.000078027886,0.000822375,0.000049414302,0.00035273188,0.00066258636,0.00027084473,0.00039514227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004775139,0.00044537263,0.0075424667,0.00008295826,0.00005922017,0.00006657845,0.012355389,0.003577071,0.00094946683,0.03065327,0.17878966,0.7654308],"study_design_scores_gemma":[0.0022086934,0.00030036605,0.007818515,0.0005099159,0.000045382978,0.00019383417,0.00031048592,0.11786399,0.0034495366,0.01671364,0.84836143,0.002224199],"about_ca_topic_score_codex":0.000027585984,"about_ca_topic_score_gemma":0.0000024765154,"teacher_disagreement_score":0.8365237,"about_ca_system_score_codex":0.00009441734,"about_ca_system_score_gemma":0.00017889525,"threshold_uncertainty_score":0.8959837},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08263131018549892,"score_gpt":0.3588600078983651,"score_spread":0.2762286977128662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888789047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64823234,0.0027438223,0.34413475,0.00040289675,0.003634626,0.00040100087,0.000008260849,0.00032511307,0.00011721389],"genre_scores_gemma":[0.9445848,0.000050745413,0.053490616,0.00040140565,0.0014002436,0.0000041225067,0.000014471531,0.000034522986,0.000019080673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996864,0.0004434397,0.0006401519,0.00083256984,0.00043403325,0.0007857553],"domain_scores_gemma":[0.9977124,0.00048227428,0.00046920817,0.0007138461,0.00027839298,0.0003439135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011077675,0.00030698034,0.00040912308,0.000089671186,0.0006640822,0.00015914727,0.0007154597,0.00020939756,0.000038328883],"category_scores_gemma":[0.00030297425,0.00031849113,0.00007858011,0.0002971154,0.00026135167,0.00045406228,0.0004916703,0.0004815612,0.0000057995276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034204096,0.0005870591,0.16282028,0.00044322238,0.00009322503,0.00004329991,0.01356368,0.024676006,0.0023026967,0.011874237,0.0007551262,0.78249913],"study_design_scores_gemma":[0.0005272313,0.00046221356,0.025228113,0.00025078963,0.0000130690905,0.000051536546,0.000057305537,0.97170246,0.00011087197,0.000113654656,0.001161773,0.0003210055],"about_ca_topic_score_codex":0.0017427383,"about_ca_topic_score_gemma":0.0015393861,"teacher_disagreement_score":0.94702643,"about_ca_system_score_codex":0.00031876026,"about_ca_system_score_gemma":0.0001921195,"threshold_uncertainty_score":0.99992675},"labels":[],"label_agreement":null}]}