{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006640342,0.002068859,0.002494856,0.004087311,0.00220099,0.002597477,0.002039251,0.003562883,0.007763492],"category_scores_gemma":[0.01976003,0.000315948,0.001257162,0.002630294,0.0006680017,0.003245741,0.003167676,0.00278805,0.005003507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534389,"about_ca_system_score_gemma":0.001652645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003958692,"about_ca_topic_score_gemma":0.005742749,"domain_scores_codex":[0.9922161,0.00252054,0.0006119955,0.002209299,0.001822641,0.0006195499],"domain_scores_gemma":[0.9881951,0.005982304,0.0006606737,0.00226681,0.001873381,0.001021807],"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":[0.003529391,0.001820776,0.01337411,0.0009368064,0.0002843827,0.0007359146,0.000653591,0.01414685,0.02669807,0.00301402,0.1438601,0.790946],"study_design_scores_gemma":[0.0008441356,0.001772363,0.02749668,0.000164503,0.0001380355,0.001821412,0.001489748,0.8276279,0.05603148,0.01920738,0.06314675,0.0002596701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7008309,0.006731621,0.221152,0.00338013,0.002648895,0.002274,0.02309043,0.02051274,0.01937933],"genre_scores_gemma":[0.7016178,0.0003747773,0.2361477,0.0005178165,0.0005785145,0.001329482,0.04399881,0.0007399158,0.01469524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007763492,"threshold_uncertainty_score":0.03511792,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002257319,0.0007871951,0.001151169,0.002527709,0.001364307,0.002594987,0.0026355,0.001133262,0.008210323],"category_scores_gemma":[0.01324315,0.0008990831,0.001780415,0.001731791,0.002780628,0.0106758,0.007960602,0.002482116,0.003914162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009361285,"about_ca_system_score_gemma":0.001116417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006397598,"about_ca_topic_score_gemma":0.0009562119,"domain_scores_codex":[0.9965219,0.0009828552,0.0002609327,0.001331649,0.0007615736,0.000140951],"domain_scores_gemma":[0.9927377,0.002695854,0.0005480433,0.00293935,0.0009149378,0.0001641277],"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":[0.0001372648,0.000208457,0.004069059,0.0004526129,0.00009251565,0.0003117262,0.001403857,0.01278914,0.03783691,0.156138,0.005335362,0.7812251],"study_design_scores_gemma":[0.00005878534,0.0002398276,0.004279837,0.000109398,0.00006718389,0.001606548,0.0006309541,0.2947654,0.04757364,0.6088402,0.04167739,0.0001509727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02586637,0.0001502406,0.9597486,0.0002536454,0.0000317592,0.0001293112,0.0001766638,0.005715782,0.007927525],"genre_scores_gemma":[0.3395096,0.0002468633,0.6517268,0.0002852661,0.00006523752,0.0002750227,0.001263776,0.0009392927,0.005688146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008210323,"threshold_uncertainty_score":0.0274663,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005178054,0.002973867,0.001752604,0.005982028,0.0021129,0.002212279,0.001944996,0.002597784,0.06573977],"category_scores_gemma":[0.01622037,0.0004308414,0.000968745,0.003377096,0.0004755766,0.003818185,0.003242898,0.001937899,0.05910979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002059776,"about_ca_system_score_gemma":0.002534974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005964975,"about_ca_topic_score_gemma":0.01163187,"domain_scores_codex":[0.9944972,0.001408125,0.0003914172,0.001320349,0.001904219,0.000478676],"domain_scores_gemma":[0.9877395,0.003196729,0.000657319,0.003028251,0.00368539,0.001692879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000274881,0.0002494185,0.00130262,0.0003800929,0.00004595286,0.0002032245,0.000116532,0.0005225939,0.007073583,0.0005926248,0.8971808,0.09205769],"study_design_scores_gemma":[0.0008353156,0.0006380962,0.02237787,0.0002467152,0.00006931759,0.001799444,0.0008800589,0.04652711,0.03836344,0.005748444,0.8823151,0.0001990659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1110084,0.004705219,0.07035127,0.00651447,0.00699428,0.005201194,0.6307169,0.108423,0.05608533],"genre_scores_gemma":[0.06597897,0.0003711084,0.06933977,0.0007846283,0.0006094271,0.002413827,0.8247645,0.003245558,0.03249218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06573977,"threshold_uncertainty_score":0.2199215,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002502558,0.002704626,0.001330045,0.002983444,0.001445875,0.002621172,0.004011303,0.003177344,0.03518684],"category_scores_gemma":[0.006756513,0.0008121673,0.001941171,0.001501089,0.000589449,0.003791236,0.003667106,0.003013332,0.0212162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001470993,"about_ca_system_score_gemma":0.001851734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009289479,"about_ca_topic_score_gemma":0.01861159,"domain_scores_codex":[0.997256,0.0003619526,0.000206092,0.0008537261,0.0008790279,0.0004432132],"domain_scores_gemma":[0.9976018,0.000582348,0.000103698,0.0007142546,0.000767243,0.0002305885],"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":[0.0006994938,0.0002522389,0.001082416,0.0003653229,0.0001041173,0.0002994185,0.0001679182,0.007426545,0.01680975,0.006062846,0.2121651,0.7545649],"study_design_scores_gemma":[0.0003275067,0.0007246839,0.004778679,0.000169412,0.00007598947,0.001476586,0.000367028,0.4683077,0.06634655,0.04212412,0.4150678,0.0002340455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01689977,0.001347053,0.7790204,0.00100987,0.000889373,0.0007023221,0.006687485,0.1733842,0.02005965],"genre_scores_gemma":[0.0872317,0.0003238775,0.8502287,0.0007042525,0.0003190704,0.000819978,0.02776848,0.007838472,0.02476546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03518684,"threshold_uncertainty_score":0.1177117,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008690692,0.0009364996,0.0009648463,0.002308411,0.001633027,0.002069208,0.000961392,0.002561318,0.01814602],"category_scores_gemma":[0.03295808,0.0002949765,0.0008735941,0.001304255,0.0006097282,0.001882739,0.003225889,0.001112222,0.005866965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001851073,"about_ca_system_score_gemma":0.002755099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01230261,"about_ca_topic_score_gemma":0.01219521,"domain_scores_codex":[0.9936379,0.003371184,0.0005568152,0.0008190224,0.00115846,0.0004565683],"domain_scores_gemma":[0.9621692,0.03037256,0.0008175434,0.002291871,0.003060314,0.001288423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003699759,0.002532091,0.02976628,0.004234587,0.0002520636,0.004989068,0.008227745,0.007444594,0.04392832,0.009633992,0.4688889,0.4164025],"study_design_scores_gemma":[0.002234841,0.001371166,0.06779221,0.0007820956,0.000209523,0.004655318,0.01486208,0.1092433,0.1659043,0.01486749,0.617507,0.0005706467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6042812,0.003643826,0.192541,0.01660577,0.001607796,0.009610724,0.09394334,0.02255045,0.0552159],"genre_scores_gemma":[0.5308822,0.0005998539,0.33551,0.002709293,0.0003000206,0.004422356,0.1015134,0.001571915,0.022491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01814602,"threshold_uncertainty_score":0.06070447,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01169654,0.005433409,0.005671736,0.006951658,0.003139839,0.004039384,0.005494923,0.00429248,0.07951866],"category_scores_gemma":[0.01733146,0.001271359,0.001997624,0.003642356,0.001309434,0.004096706,0.005868278,0.004896162,0.06510126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002409018,"about_ca_system_score_gemma":0.002198223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009873093,"about_ca_topic_score_gemma":0.009922247,"domain_scores_codex":[0.992968,0.001932668,0.0002546411,0.001967723,0.002050337,0.0008265839],"domain_scores_gemma":[0.9885443,0.002316904,0.0003344052,0.002895986,0.003533426,0.002374902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006454732,0.0003660871,0.0002361539,0.0004646527,0.0001442445,0.0003222222,0.00006604579,0.0007024127,0.008200955,0.001022791,0.9329624,0.05486666],"study_design_scores_gemma":[0.003749205,0.001277533,0.0109744,0.0003180782,0.0003749252,0.003936965,0.0002743737,0.03581508,0.04073424,0.01502633,0.8870618,0.0004569903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.08203763,0.02505538,0.1827656,0.01909475,0.02804158,0.007241244,0.268714,0.2698193,0.1172305],"genre_scores_gemma":[0.05785725,0.001848828,0.1299113,0.004139765,0.003171845,0.003926062,0.6984416,0.02544151,0.07526179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07951866,"threshold_uncertainty_score":0.2660164,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004458313,0.002981734,0.001887212,0.005399346,0.001883008,0.002487368,0.002798186,0.003874714,0.02258476],"category_scores_gemma":[0.02198972,0.0007446322,0.001851454,0.002914494,0.001031867,0.001821406,0.003348527,0.003596018,0.01730075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005745175,"about_ca_system_score_gemma":0.007800506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1637793,"about_ca_topic_score_gemma":0.2427776,"domain_scores_codex":[0.9963014,0.00126033,0.000424288,0.0008519634,0.000804278,0.0003577749],"domain_scores_gemma":[0.9924608,0.003196829,0.0003483648,0.001299367,0.002107237,0.000587442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003751818,0.0001259503,0.003793987,0.0008247566,0.0001585105,0.0003645665,0.00007695422,0.00311567,0.002266828,0.0006320035,0.9301212,0.05814441],"study_design_scores_gemma":[0.002851802,0.0009533149,0.09512497,0.002728496,0.001349273,0.005159893,0.002220207,0.2364216,0.03836234,0.01829267,0.5956549,0.0008804429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.06277905,0.008655309,0.03263709,0.009468891,0.003834963,0.001889938,0.8481452,0.01378468,0.01880491],"genre_scores_gemma":[0.06105391,0.0009585207,0.02157593,0.0009851173,0.0003938012,0.0009276579,0.9045098,0.0008897972,0.008705352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1637793,"threshold_uncertainty_score":0.3256521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}