{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025866373,0.00015024055,0.9597486,0.00025364544,0.0000317592,0.0001293112,0.00017666385,0.005715782,0.007927525],"genre_scores_gemma":[0.33950958,0.00024686332,0.6517268,0.00028526608,0.000065237524,0.00027502273,0.0012637762,0.00093929266,0.0056881458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652195,0.0009828552,0.00026093275,0.0013316489,0.00076157355,0.000140951],"domain_scores_gemma":[0.9927377,0.0026958538,0.00054804335,0.0029393497,0.0009149378,0.00016412772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022573187,0.0007871951,0.0011511687,0.0025277091,0.0013643074,0.0025949874,0.0026355004,0.0011332618,0.008210323],"category_scores_gemma":[0.013243145,0.0008990831,0.001780415,0.001731791,0.0027806277,0.010675803,0.007960602,0.0024821162,0.0039141616],"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":[0.0001372648,0.00020845702,0.0040690587,0.00045261288,0.00009251565,0.00031172618,0.0014038567,0.012789138,0.03783691,0.156138,0.005335362,0.7812251],"study_design_scores_gemma":[0.000058785336,0.00023982757,0.0042798375,0.000109398025,0.00006718389,0.0016065477,0.0006309541,0.29476538,0.047573645,0.60884017,0.041677393,0.00015097273],"about_ca_topic_score_codex":0.00063975976,"about_ca_topic_score_gemma":0.0009562119,"teacher_disagreement_score":0.008210323,"about_ca_system_score_codex":0.00093612855,"about_ca_system_score_gemma":0.0011164173,"threshold_uncertainty_score":0.027466297},"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":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08203763,0.025055379,0.18276563,0.019094754,0.028041584,0.007241244,0.26871398,0.26981932,0.11723051],"genre_scores_gemma":[0.057857245,0.0018488283,0.12991133,0.004139765,0.003171845,0.0039260616,0.6984416,0.025441507,0.07526179],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992968,0.0019326679,0.00025464108,0.0019677226,0.0020503374,0.00082658394],"domain_scores_gemma":[0.9885443,0.0023169038,0.00033440517,0.0028959862,0.0035334257,0.002374902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011696542,0.0054334095,0.0056717363,0.006951658,0.003139839,0.004039384,0.0054949233,0.0042924797,0.07951866],"category_scores_gemma":[0.017331464,0.0012713586,0.001997624,0.0036423563,0.0013094342,0.0040967064,0.0058682784,0.004896162,0.06510126],"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":[0.0006454732,0.00036608707,0.00023615394,0.00046465272,0.00014424446,0.00032222224,0.00006604579,0.00070241274,0.008200955,0.0010227913,0.93296236,0.05486666],"study_design_scores_gemma":[0.0037492053,0.0012775325,0.0109744,0.0003180782,0.0003749252,0.0039369655,0.00027437374,0.035815075,0.040734235,0.015026327,0.8870618,0.0004569903],"about_ca_topic_score_codex":0.009873093,"about_ca_topic_score_gemma":0.009922247,"teacher_disagreement_score":0.07951866,"about_ca_system_score_codex":0.0024090183,"about_ca_system_score_gemma":0.0021982235,"threshold_uncertainty_score":0.26601642},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7008309,0.006731621,0.22115201,0.0033801296,0.0026488947,0.0022739999,0.023090431,0.020512737,0.01937933],"genre_scores_gemma":[0.7016178,0.0003747773,0.23614767,0.00051781646,0.00057851453,0.0013294817,0.04399881,0.0007399158,0.014695237],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99221605,0.00252054,0.00061199546,0.002209299,0.0018226415,0.00061954994],"domain_scores_gemma":[0.98819506,0.005982304,0.0006606737,0.00226681,0.0018733813,0.0010218072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006640342,0.0020688588,0.0024948556,0.0040873108,0.0022009904,0.0025974766,0.002039251,0.0035628832,0.007763492],"category_scores_gemma":[0.01976003,0.00031594795,0.0012571621,0.002630294,0.0006680017,0.0032457411,0.0031676756,0.0027880496,0.005003507],"study_design_candidate":"bench_or_experimental","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":[0.0035293915,0.0018207757,0.01337411,0.00093680643,0.0002843827,0.0007359146,0.000653591,0.014146847,0.026698073,0.00301402,0.14386006,0.790946],"study_design_scores_gemma":[0.00084413565,0.0017723631,0.027496684,0.00016450303,0.00013803554,0.0018214125,0.0014897478,0.8276279,0.05603148,0.019207384,0.06314675,0.00025967008],"about_ca_topic_score_codex":0.0039586923,"about_ca_topic_score_gemma":0.005742749,"teacher_disagreement_score":0.007763492,"about_ca_system_score_codex":0.001534389,"about_ca_system_score_gemma":0.0016526452,"threshold_uncertainty_score":0.035117924},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6042812,0.0036438259,0.19254103,0.016605774,0.0016077958,0.009610724,0.093943335,0.022550454,0.055215895],"genre_scores_gemma":[0.53088224,0.0005998539,0.33550996,0.0027092926,0.00030002065,0.0044223564,0.10151339,0.0015719149,0.022490997],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99363786,0.0033711842,0.0005568152,0.0008190224,0.0011584602,0.00045656835],"domain_scores_gemma":[0.96216923,0.030372556,0.0008175434,0.0022918712,0.0030603139,0.001288423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0086906925,0.00093649956,0.00096484635,0.002308411,0.0016330275,0.0020692083,0.000961392,0.002561318,0.018146016],"category_scores_gemma":[0.03295808,0.00029497652,0.0008735941,0.0013042551,0.00060972816,0.0018827395,0.0032258893,0.0011122222,0.005866965],"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":[0.0036997588,0.0025320915,0.029766282,0.0042345873,0.00025206362,0.0049890685,0.008227745,0.007444594,0.04392832,0.009633992,0.4688889,0.41640246],"study_design_scores_gemma":[0.0022348415,0.0013711656,0.067792214,0.0007820956,0.00020952299,0.0046553183,0.014862082,0.10924333,0.16590434,0.01486749,0.61750704,0.0005706467],"about_ca_topic_score_codex":0.01230261,"about_ca_topic_score_gemma":0.012195213,"teacher_disagreement_score":0.018146016,"about_ca_system_score_codex":0.0018510725,"about_ca_system_score_gemma":0.0027550994,"threshold_uncertainty_score":0.06070447},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111008376,0.0047052186,0.070351265,0.00651447,0.0069942805,0.005201194,0.6307169,0.108422965,0.056085333],"genre_scores_gemma":[0.065978974,0.00037110838,0.06933977,0.00078462827,0.00060942705,0.0024138272,0.8247645,0.0032455584,0.032492183],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99449724,0.0014081247,0.0003914172,0.0013203492,0.0019042189,0.00047867603],"domain_scores_gemma":[0.9877395,0.0031967293,0.000657319,0.0030282512,0.00368539,0.0016928794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051780543,0.0029738673,0.0017526037,0.005982028,0.0021128997,0.0022122788,0.0019449957,0.0025977844,0.06573977],"category_scores_gemma":[0.01622037,0.00043084144,0.000968745,0.0033770958,0.00047557655,0.003818185,0.003242898,0.0019378988,0.059109792],"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":[0.00027488096,0.0002494185,0.0013026199,0.00038009294,0.00004595286,0.00020322452,0.000116531985,0.0005225939,0.0070735826,0.0005926248,0.8971808,0.09205769],"study_design_scores_gemma":[0.00083531556,0.00063809624,0.022377871,0.0002467152,0.00006931759,0.0017994443,0.0008800589,0.046527114,0.03836344,0.0057484442,0.8823151,0.00019906591],"about_ca_topic_score_codex":0.005964975,"about_ca_topic_score_gemma":0.01163187,"teacher_disagreement_score":0.06573977,"about_ca_system_score_codex":0.0020597763,"about_ca_system_score_gemma":0.002534974,"threshold_uncertainty_score":0.21992147},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016899774,0.0013470529,0.77902037,0.0010098696,0.00088937295,0.0007023221,0.006687485,0.17338419,0.020059645],"genre_scores_gemma":[0.0872317,0.0003238775,0.8502287,0.00070425245,0.0003190704,0.000819978,0.027768476,0.007838472,0.024765456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997256,0.00036195264,0.00020609202,0.00085372606,0.0008790279,0.00044321315],"domain_scores_gemma":[0.9976018,0.00058234803,0.00010369805,0.0007142546,0.00076724304,0.00023058848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025025583,0.0027046262,0.001330045,0.0029834444,0.0014458748,0.0026211715,0.0040113027,0.0031773443,0.03518684],"category_scores_gemma":[0.006756513,0.0008121673,0.001941171,0.0015010886,0.00058944896,0.0037912359,0.003667106,0.0030133317,0.021216203],"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":[0.0006994938,0.00025223885,0.0010824162,0.00036532292,0.00010411733,0.00029941852,0.0001679182,0.007426545,0.016809754,0.006062846,0.2121651,0.7545649],"study_design_scores_gemma":[0.00032750668,0.00072468386,0.0047786785,0.00016941199,0.00007598947,0.001476586,0.000367028,0.46830767,0.06634655,0.04212412,0.41506776,0.00023404552],"about_ca_topic_score_codex":0.009289479,"about_ca_topic_score_gemma":0.018611591,"teacher_disagreement_score":0.03518684,"about_ca_system_score_codex":0.0014709928,"about_ca_system_score_gemma":0.0018517342,"threshold_uncertainty_score":0.11771166},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062779054,0.008655309,0.032637086,0.009468891,0.003834963,0.001889938,0.8481452,0.013784678,0.01880491],"genre_scores_gemma":[0.061053913,0.0009585207,0.02157593,0.0009851173,0.0003938012,0.00092765794,0.90450984,0.00088979723,0.008705352],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963014,0.0012603301,0.00042428795,0.0008519634,0.00080427795,0.0003577749],"domain_scores_gemma":[0.9924608,0.0031968288,0.00034836485,0.0012993667,0.0021072368,0.000587442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044583133,0.0029817345,0.0018872117,0.0053993464,0.0018830084,0.0024873682,0.0027981861,0.0038747136,0.022584759],"category_scores_gemma":[0.021989718,0.0007446322,0.001851454,0.0029144944,0.0010318668,0.001821406,0.0033485275,0.0035960178,0.017300751],"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":[0.00037518176,0.0001259503,0.0037939872,0.00082475663,0.00015851055,0.00036456645,0.000076954224,0.00311567,0.0022668277,0.00063200353,0.93012124,0.058144405],"study_design_scores_gemma":[0.0028518024,0.0009533149,0.09512497,0.0027284955,0.0013492729,0.005159893,0.0022202067,0.23642163,0.03836234,0.01829267,0.5956549,0.00088044285],"about_ca_topic_score_codex":0.16377932,"about_ca_topic_score_gemma":0.24277763,"teacher_disagreement_score":0.16377932,"about_ca_system_score_codex":0.0057451753,"about_ca_system_score_gemma":0.0078005064,"threshold_uncertainty_score":0.32565206},"labels":[],"label_agreement":null}]}