{"meta":{"query_hash":"56ea10969077","filters":{"venue":"Proceedings of the AAAI Symposium Series"},"cohort_total":35,"direct_labels_cover":0,"predictions_cover":35,"exported":35,"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/56ea10969077","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+AAAI+Symposium+Series"},"results":[{"id":"W4388521737","doi":"10.1609/aaaiss.v1i1.27492","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Machine learning; Artificial intelligence; Probabilistic logic; Computer science; Conformal map; Context (archaeology); Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Data mining; Mathematics","score_opus":0.022766537524749286,"score_gpt":0.25097553267995865,"score_spread":0.22820899515520937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388521737","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":[0.9740704,0.00004590815,0.004871748,0.007885068,0.00040592597,0.00034190743,0.0000063287544,0.0008778461,0.011494854],"genre_scores_gemma":[0.9973531,0.0001016153,0.0015859435,0.000034007626,0.000029086312,0.000025600113,0.000008586716,0.000009712941,0.00085239444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988921,0.0000143576235,0.0002925584,0.00026338006,0.00028900648,0.00024854072],"domain_scores_gemma":[0.9994204,0.000036170037,0.00021745503,0.0001634532,0.00012838752,0.000034116936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006785023,0.00011645241,0.00014081599,0.00016941933,0.00022808627,0.00015050876,0.0007857981,0.00006302823,0.000001454387],"category_scores_gemma":[0.00019197936,0.00009112858,0.00005067354,0.00085116876,0.00006420441,0.0014118631,0.00042251978,0.0002755879,0.00001331337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009745991,0.00005652518,0.18764362,0.00047118674,0.000026306334,6.618738e-7,0.016902052,0.31911886,0.17283739,0.2949265,0.00068113796,0.0072383215],"study_design_scores_gemma":[0.00016346587,0.00004864406,0.019062635,0.0000665385,0.0000049624614,0.0000067141004,0.00048293913,0.9747,0.0033715093,0.0010753035,0.00091812253,0.000099196244],"about_ca_topic_score_codex":0.000043500317,"about_ca_topic_score_gemma":0.000011411038,"teacher_disagreement_score":0.6555811,"about_ca_system_score_codex":0.000036763682,"about_ca_system_score_gemma":0.00003283133,"threshold_uncertainty_score":0.3716116},"labels":[],"label_agreement":null},{"id":"W4388521769","doi":"10.1609/aaaiss.v1i1.27493","title":"Fairness in Machine Learning Meets with Equity in Healthcare","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Harm; Health care; Equity (law); Computer science; Health equity; Artificial intelligence; Machine learning; Risk analysis (engineering); Data science; Psychology; Business; Economics; Social psychology; Political science","score_opus":0.08289221771854285,"score_gpt":0.3831236030337856,"score_spread":0.30023138531524274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388521769","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":[0.9249408,0.00012353562,3.4095518e-7,0.072862886,0.00014297041,0.00041739782,0.0000016389911,0.000067476154,0.0014429548],"genre_scores_gemma":[0.9983578,0.00035690606,0.000076858974,0.00018491503,0.000069899164,0.000063925385,0.0000058223823,0.00002100087,0.0008628731],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99875796,0.000014470422,0.00038460438,0.00022412739,0.00028548102,0.0003333692],"domain_scores_gemma":[0.9994026,0.000048391747,0.00014740013,0.00009491632,0.00023862219,0.00006808968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005827174,0.00012305324,0.00026702296,0.0002187714,0.00010116275,0.000020900463,0.0001669005,0.000086608416,0.000008766635],"category_scores_gemma":[0.00022235801,0.00008547699,0.000037095982,0.0012113017,0.000108783745,0.0002527442,0.00013144736,0.00035961406,0.000010752597],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004908542,0.00006537936,0.9690179,0.0011458952,0.0000075984317,0.000003107683,0.009037541,0.00007995336,0.015363556,0.0028627529,0.00010972459,0.0018157335],"study_design_scores_gemma":[0.0005848563,0.0023028057,0.505107,0.0045673326,0.000070148766,0.00016832024,0.032396305,0.002791517,0.43619218,0.011954267,0.0032550246,0.00061028043],"about_ca_topic_score_codex":0.0035786626,"about_ca_topic_score_gemma":0.0014897916,"teacher_disagreement_score":0.46391094,"about_ca_system_score_codex":0.00014159083,"about_ca_system_score_gemma":0.0001577996,"threshold_uncertainty_score":0.54098916},"labels":[],"label_agreement":null},{"id":"W4388521771","doi":"10.1609/aaaiss.v1i1.27491","title":"XGBoost for Interpretable Alzheimer’s Decision Support","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Natural Sciences and Engineering Research Council of Canada; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Ministère de la Défense Nationale; Alzheimer's Association","keywords":"Interpretability; Recall; Artificial intelligence; Disease; Machine learning; Computer science; Clinical decision support system; Decision support system; Cognition; Process (computing); Medicine; Data science; Psychology; Cognitive psychology; Pathology; Psychiatry","score_opus":0.0205458961332051,"score_gpt":0.2854560813562283,"score_spread":0.2649101852230232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388521771","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":[0.68275523,0.0008581092,0.01826071,0.20566125,0.013355851,0.0073044538,0.00013206426,0.005497775,0.06617455],"genre_scores_gemma":[0.9593939,0.00007012934,0.03560939,0.00051196426,0.00015938793,0.00018308237,0.0000040084497,0.000047803536,0.0040203077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998385,0.000009332425,0.00038525576,0.00041420682,0.00038653237,0.00041967924],"domain_scores_gemma":[0.9987074,0.00019117566,0.00026616798,0.00034455158,0.00041026782,0.00008042626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007131991,0.00017887409,0.00025186467,0.00014734721,0.0003009329,0.00018337579,0.0020021598,0.000083652754,0.000012789393],"category_scores_gemma":[0.00037692566,0.00013242851,0.00014888639,0.0007825713,0.00008583938,0.0009471467,0.0011248032,0.00017499333,0.000046769655],"study_design_candidate":"theoretical_or_conceptual","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":[0.00061417394,0.00015204794,0.07631102,0.0020642567,0.00032184334,0.0000037893726,0.026164513,0.0005976831,0.12350031,0.48567307,0.24342217,0.04117513],"study_design_scores_gemma":[0.0019192296,0.0029626323,0.023423852,0.0013105221,0.00023577978,0.0002823624,0.0013510092,0.12359283,0.36708105,0.123623535,0.35243332,0.0017838788],"about_ca_topic_score_codex":0.000030478337,"about_ca_topic_score_gemma":0.0000040654,"teacher_disagreement_score":0.36204952,"about_ca_system_score_codex":0.000029206878,"about_ca_system_score_gemma":0.0000819182,"threshold_uncertainty_score":0.5400278},"labels":[],"label_agreement":null},{"id":"W4391116674","doi":"10.1609/aaaiss.v2i1.27702","title":"A Neuro-Mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Cisco Systems","keywords":"Generative grammar; Computer science; Artificial intelligence; Cognitive science; Hebbian theory; Field (mathematics); Realization (probability); Cognition; Artificial neural network; Generative model; Representation (politics); Cognitive architecture; Psychology; Mathematics","score_opus":0.007504798073150291,"score_gpt":0.2027236544554505,"score_spread":0.19521885638230022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391116674","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":[0.7721226,0.001134244,0.18118238,0.03274339,0.0007036912,0.001338273,0.000046373178,0.000444441,0.010284595],"genre_scores_gemma":[0.9985331,0.0001864617,0.00096051703,0.000057554527,0.000020031743,0.00001576332,0.0000015021129,0.000009667189,0.00021534902],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993255,0.000012930404,0.00023385623,0.00016834874,0.00017540845,0.00008394582],"domain_scores_gemma":[0.99943197,0.000045156165,0.00021321705,0.0001334622,0.00015835105,0.000017842005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008093111,0.00008340304,0.00011750364,0.00004615522,0.00011991904,0.000065441345,0.00045216875,0.000036858222,6.528888e-7],"category_scores_gemma":[0.000027549317,0.000056039626,0.00004952314,0.00051119423,0.00012163152,0.00040190475,0.0003542705,0.00007100357,7.8193246e-8],"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":[0.00001579693,0.000035184512,0.0010125625,0.00032373072,0.000019821799,4.3154675e-8,0.0013689247,0.006670232,0.5988027,0.38925815,0.00065837405,0.0018344867],"study_design_scores_gemma":[0.000086440086,0.00007053759,0.0002654206,0.00021185163,0.000050256374,0.000010919507,0.000040974715,0.7047217,0.2403859,0.0537116,0.00036545747,0.00007893565],"about_ca_topic_score_codex":0.000022501521,"about_ca_topic_score_gemma":0.000005832999,"teacher_disagreement_score":0.69805145,"about_ca_system_score_codex":0.000006180042,"about_ca_system_score_gemma":0.000016555068,"threshold_uncertainty_score":0.22852297},"labels":[],"label_agreement":null},{"id":"W4391116695","doi":"10.1609/aaaiss.v2i1.27650","title":"Multi-Variable Hard Physical Constraints for Climate Model Downscaling","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Climate variability and models","field":"Environmental 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":"McGill University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Agencia Estatal de Investigación","keywords":"Downscaling; Variable (mathematics); Climate model; Climate change; Scale (ratio); GCM transcription factors; Computer science; Scope (computer science); Climatology; Environmental science; General Circulation Model; Econometrics; Mathematics; Geography; Geology","score_opus":0.019402278280908895,"score_gpt":0.2465382461274216,"score_spread":0.2271359678465127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391116695","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":[0.97991776,0.000028763665,0.001482887,0.0025926414,0.0003404768,0.0008406817,0.00025897115,0.00020631484,0.014331503],"genre_scores_gemma":[0.9705393,0.000038917027,0.028030511,0.00010421804,0.00006160558,0.00010242593,0.0000032303617,0.000029979727,0.0010898523],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987684,0.000004181658,0.00024908755,0.0003946588,0.00021989508,0.0003637629],"domain_scores_gemma":[0.99964345,0.000059603455,0.00007553555,0.00012851898,0.000031018313,0.00006185159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004244931,0.00017668464,0.00021785172,0.00002123075,0.00021258186,0.00012891582,0.00037759793,0.000074030155,0.000070540904],"category_scores_gemma":[0.000064033724,0.0001264754,0.00016331916,0.00019253453,0.0005126932,0.0007039212,0.00040552253,0.00012917919,0.000025983973],"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":[0.00005911724,0.000105738545,0.0009836971,0.0006139298,0.000023567483,9.0624745e-8,0.002183677,0.008751277,0.95644814,0.030029926,0.00071430666,0.00008653736],"study_design_scores_gemma":[0.00030824434,0.00007635705,0.0001314491,0.00021183456,0.00012188097,0.0000135005375,0.00026081275,0.8634704,0.1123078,0.020640485,0.0021735576,0.00028368135],"about_ca_topic_score_codex":0.000019181009,"about_ca_topic_score_gemma":0.0000015094156,"teacher_disagreement_score":0.8547191,"about_ca_system_score_codex":0.000080642465,"about_ca_system_score_gemma":0.000019771269,"threshold_uncertainty_score":0.5157517},"labels":[],"label_agreement":null},{"id":"W4391116973","doi":"10.1609/aaaiss.v2i1.27716","title":"Predicting Individual Survival Distributions Using ECG: A Deep Learning Approach Utilizing Features Extracted by a Learned Diagnostic Model","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; Alberta Health Services","keywords":"Leverage (statistics); Machine learning; Artificial intelligence; Computer science; Predictive modelling; Margin (machine learning); Concordance; Personalized medicine; Population; Data mining; Medicine; Bioinformatics; Internal medicine","score_opus":0.024644755451826875,"score_gpt":0.27396435139700454,"score_spread":0.24931959594517766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391116973","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":[0.91335183,0.003682928,0.067063816,0.0068049636,0.0010819181,0.001101572,0.00009990718,0.00203907,0.004773979],"genre_scores_gemma":[0.977494,0.000090186244,0.021691306,0.000034052722,0.00012987813,0.00006109702,0.00002410756,0.000053787055,0.00042158057],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706525,0.00009111931,0.00054380164,0.00079839956,0.0008240626,0.0006773965],"domain_scores_gemma":[0.9984069,0.0004884649,0.00034610383,0.00028417003,0.00032553292,0.00014885007],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010059694,0.0003758988,0.00038363176,0.00017695331,0.00095604523,0.0010215254,0.0016661667,0.00020936229,0.0000027194258],"category_scores_gemma":[0.0016563778,0.00030895605,0.00018533182,0.0012277755,0.0002031212,0.0017036512,0.001216359,0.0013914175,0.00000197704],"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":[0.00016126047,0.0005364151,0.30507392,0.007492128,0.0007783475,0.000014651877,0.07103103,0.13073781,0.21563889,0.25644732,0.0020348483,0.010053395],"study_design_scores_gemma":[0.0001586187,0.000104398096,0.0027980125,0.0004933168,0.00010684729,0.00015173828,0.0009657169,0.9885862,0.0044069886,0.0015397033,0.00031456936,0.0003739172],"about_ca_topic_score_codex":0.00016539116,"about_ca_topic_score_gemma":0.00000563749,"teacher_disagreement_score":0.85784835,"about_ca_system_score_codex":0.0001447916,"about_ca_system_score_gemma":0.00017395438,"threshold_uncertainty_score":0.9999363},"labels":[],"label_agreement":null},{"id":"W4391117032","doi":"10.1609/aaaiss.v2i1.27709","title":"Bridging Generative Networks with the Common Model of Cognition","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generative grammar; Bridging (networking); Computer science; Cognition; Shadow (psychology); Generative model; Artificial intelligence; Cognitive science; Field (mathematics); Cognitive model; Artificial neural network; Psychology; Mathematics","score_opus":0.01135116480114124,"score_gpt":0.21104834398200312,"score_spread":0.19969717918086188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391117032","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":[0.4853184,0.000931189,0.46879292,0.034388416,0.00077165395,0.0012132142,0.000019139678,0.00052811846,0.008036965],"genre_scores_gemma":[0.9878828,0.000033134384,0.01155618,0.0001452849,0.00011485965,0.000034703397,7.761069e-7,0.000016115499,0.00021614366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987458,0.00001923142,0.00027267708,0.00035143932,0.00037717033,0.00023368598],"domain_scores_gemma":[0.9990663,0.00009000032,0.00018440638,0.00025235035,0.00037247027,0.000034469373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043619695,0.00019047364,0.00024068094,0.000057958776,0.00020753415,0.00029023172,0.0011573638,0.00005250396,0.0000014195556],"category_scores_gemma":[0.000015612564,0.000103692175,0.00010338096,0.00064297824,0.00035660862,0.0008992241,0.00071754924,0.00022984622,9.3808677e-7],"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":[0.00022389558,0.00029706905,0.0024288092,0.0012572107,0.00048801207,0.0000035451856,0.0331261,0.26939735,0.2264736,0.44563022,0.005369267,0.015304915],"study_design_scores_gemma":[0.00008772005,0.00014914195,0.00017362983,0.0001585214,0.00004820155,0.000035628567,0.00012653758,0.91538525,0.073920265,0.009720548,0.000055626853,0.00013896202],"about_ca_topic_score_codex":0.00001718865,"about_ca_topic_score_gemma":0.0000081772205,"teacher_disagreement_score":0.64598787,"about_ca_system_score_codex":0.000037100497,"about_ca_system_score_gemma":0.00006451914,"threshold_uncertainty_score":0.4228444},"labels":[],"label_agreement":null},{"id":"W4391117034","doi":"10.1609/aaaiss.v2i1.27686","title":"Bridging Cognitive Architectures and Generative Models with Vector Symbolic Algebras","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Generative grammar; Bridging (networking); Computer science; Cognition; Cognitive science; Cognitive architecture; Cognitive model; Artificial intelligence; Set (abstract data type); Generative model; Theoretical computer science; Psychology","score_opus":0.008378286763685062,"score_gpt":0.2084268212199097,"score_spread":0.20004853445622464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391117034","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":[0.95675886,0.00092515035,0.014485412,0.024268223,0.000113892886,0.00046091215,0.000011552342,0.00023968588,0.0027363244],"genre_scores_gemma":[0.9960718,0.00006565856,0.003133561,0.00018997912,0.000090327754,0.00006450775,4.017447e-7,0.000013781876,0.00036995512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992219,0.0000052037844,0.00010975776,0.0003226353,0.00016480674,0.00017568216],"domain_scores_gemma":[0.9996692,0.000043250693,0.00006108076,0.00008759926,0.0000923615,0.000046508263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006645573,0.00014333882,0.00013573936,0.00005011233,0.00019315672,0.00035135276,0.0003724255,0.000026302252,7.968546e-7],"category_scores_gemma":[0.0000051590137,0.000086072956,0.00003913556,0.0003879925,0.0001817253,0.0005191888,0.00027544156,0.00013565777,0.0000010824084],"study_design_candidate":"theoretical_or_conceptual","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":[0.000027105289,0.000020561929,0.0002943155,0.00016655518,0.00008964116,0.0000014144655,0.0064365645,0.00044570622,0.08613342,0.9026161,0.00057745224,0.0031911887],"study_design_scores_gemma":[0.00037108778,0.00044719662,0.0025154578,0.0012725056,0.00015269336,0.00049526675,0.00036081567,0.26027358,0.5890782,0.14350013,0.0008120948,0.0007209631],"about_ca_topic_score_codex":0.000009294814,"about_ca_topic_score_gemma":0.000002893627,"teacher_disagreement_score":0.75911593,"about_ca_system_score_codex":0.00000914102,"about_ca_system_score_gemma":0.00002876911,"threshold_uncertainty_score":0.35099533},"labels":[],"label_agreement":null},{"id":"W4391117154","doi":"10.1609/aaaiss.v2i1.27713","title":"SurvivalEVAL: A Comprehensive Open-Source Python Package for Evaluating Individual Survival Distributions","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Python (programming language); Open source; R package; Computer science; Software package; Open source software; Software engineering; Software; Data science; Programming language","score_opus":0.06270916326131269,"score_gpt":0.360950210917829,"score_spread":0.29824104765651627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391117154","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":[0.9343036,0.0007517572,0.00033511617,0.014364555,0.0033486797,0.0043748314,0.0007935611,0.0005819409,0.041145965],"genre_scores_gemma":[0.99443775,0.00022485391,0.0010694701,0.00008873212,0.00036627025,0.00034912335,0.000031351952,0.00006077192,0.0033717002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971331,0.00011940347,0.0005186751,0.0005451846,0.0010761388,0.0006075259],"domain_scores_gemma":[0.998151,0.00035540998,0.0003079886,0.000236592,0.00084556796,0.000103439554],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030896023,0.0002780387,0.0004111589,0.00013114007,0.0014769862,0.0012561047,0.0017652119,0.00012548936,0.00003198611],"category_scores_gemma":[0.00048127092,0.00023051818,0.00032218828,0.0010933208,0.00085416116,0.0012098744,0.0009678625,0.00023806182,0.000010220785],"study_design_candidate":"theoretical_or_conceptual","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":[0.00026958165,0.00027081103,0.05450869,0.0018093545,0.0008685675,0.0000014710569,0.043805107,0.000027859387,0.025624136,0.8492508,0.020431569,0.0031320434],"study_design_scores_gemma":[0.0021928826,0.0010393546,0.10212449,0.0017867263,0.0020641063,0.000013765807,0.08809705,0.0004935248,0.027350279,0.078469396,0.6942441,0.0021243626],"about_ca_topic_score_codex":0.0009028264,"about_ca_topic_score_gemma":0.00034888816,"teacher_disagreement_score":0.7707814,"about_ca_system_score_codex":0.00012164673,"about_ca_system_score_gemma":0.00017899516,"threshold_uncertainty_score":0.999823},"labels":[],"label_agreement":null},{"id":"W4398160794","doi":"10.1609/aaaiss.v3i1.31228","title":"Federated Variational Inference: Towards Improved Personalization and Generalization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Generalization; Inference; Computer science; Generative model; Machine learning; Personalization; Generative grammar; Bayesian inference; Artificial intelligence; Approximate inference; Process (computing); Stateless protocol; Bayesian probability; Bayes' theorem; State (computer science); Algorithm; Mathematics","score_opus":0.013532602168565657,"score_gpt":0.24594615126854744,"score_spread":0.23241354909998177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13452171,0.0017532668,0.48389593,0.36541006,0.0026381654,0.0012718156,0.00009952575,0.00358009,0.0068294555],"genre_scores_gemma":[0.9178284,0.0004137044,0.08096284,0.00015343359,0.000081237835,0.000044114226,0.0000135090395,0.000019172507,0.00048359408],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989657,0.000008872784,0.0002216435,0.00036627916,0.00027251648,0.00016503427],"domain_scores_gemma":[0.99909747,0.000031653773,0.00011418085,0.00042051493,0.00030921947,0.00002693791],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00026515263,0.00014101824,0.00012358747,0.00010938162,0.00019648054,0.00075816776,0.0037528954,0.000103006016,0.000007582653],"category_scores_gemma":[0.0020667699,0.00010571802,0.000034005927,0.00070901064,0.00012464394,0.0020963599,0.012153356,0.00012092245,0.0000017803766],"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":[0.00002176761,0.000038908143,0.0034558126,0.0007516276,0.000104036146,6.2553585e-7,0.0017226391,0.000014385838,0.4784966,0.47316298,0.039083946,0.0031466545],"study_design_scores_gemma":[0.00012847337,0.00007808021,0.0017890874,0.00016337003,0.000023619616,0.00003237745,0.00006582196,0.7103857,0.11547281,0.16995199,0.0016903048,0.00021837385],"about_ca_topic_score_codex":0.000029392088,"about_ca_topic_score_gemma":0.0000018998373,"teacher_disagreement_score":0.78330666,"about_ca_system_score_codex":0.000053273165,"about_ca_system_score_gemma":0.0001064295,"threshold_uncertainty_score":0.99583614},"labels":[],"label_agreement":null},{"id":"W4398160805","doi":"10.1609/aaaiss.v3i1.31261","title":"Remote Possibilities: Where There Is a WIL, Is There a Way? AI Education for Remote Learners in a New Era of Work-Integrated-Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Collaboration in agile enterprises","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Science Foundation","keywords":"Bridge (graph theory); Work (physics); Diversity (politics); Knowledge management; Computer science; Distance education; Engineering management; Engineering; World Wide Web; Sociology; Pedagogy","score_opus":0.008206577704504331,"score_gpt":0.23865002970913296,"score_spread":0.23044345200462862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160805","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":[0.8856048,0.004299394,0.0002299999,0.08536245,0.001254753,0.0017949914,0.000017901175,0.000339236,0.02109649],"genre_scores_gemma":[0.96316063,0.00040670874,0.0015653762,0.001223666,0.0006228878,0.000026974738,0.0000071531304,0.000098239834,0.032888368],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984347,0.0000075240655,0.00054707995,0.0004237826,0.00031213812,0.0002747494],"domain_scores_gemma":[0.998618,0.0000657211,0.00040794842,0.0001922111,0.0006981628,0.000017978704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003582396,0.00028096864,0.00033436538,0.0002449279,0.00013998657,0.0006522286,0.00048960664,0.00012587386,0.00020356291],"category_scores_gemma":[0.00026962112,0.000215153,0.00018596613,0.0016008312,0.00012221134,0.0019542493,0.0001959275,0.00037426886,0.000016137232],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035771006,0.00040559328,0.11342428,0.026164293,0.0006908373,0.0000023531604,0.08816004,0.00053011655,0.044417337,0.05173042,0.5422404,0.12865724],"study_design_scores_gemma":[0.0013789837,0.00024091413,0.0017298233,0.021779519,0.0004176296,0.000010906907,0.07214911,0.012373607,0.01682125,0.05519102,0.8167268,0.001180451],"about_ca_topic_score_codex":0.0019563506,"about_ca_topic_score_gemma":0.00017328288,"teacher_disagreement_score":0.2744864,"about_ca_system_score_codex":0.00010441944,"about_ca_system_score_gemma":0.00034623756,"threshold_uncertainty_score":0.8773685},"labels":[],"label_agreement":null},{"id":"W4398160811","doi":"10.1609/aaaiss.v3i1.31252","title":"AI-Assisted Talk: A Narrative Review on the New Social and Conversational Landscape","year":2024,"lang":"en","type":"review","venue":"Proceedings of the AAAI Symposium Series","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Narrative; Generative grammar; Cognitive science; Computer science; Psychology; Artificial intelligence; Linguistics","score_opus":0.03304525573850861,"score_gpt":0.3136400603324124,"score_spread":0.28059480459390373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160811","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005094438,0.8722532,0.000006231078,0.12196603,0.00066510594,0.000880025,0.000023431601,0.000097889555,0.004102995],"genre_scores_gemma":[0.000041053623,0.99342424,0.00021343442,0.0021614793,0.00031262575,0.00016441537,0.0000049968153,0.000031564694,0.0036461945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982325,0.00004427448,0.0005538786,0.00049160846,0.00046573207,0.00021203766],"domain_scores_gemma":[0.9985102,0.00019485409,0.0006697488,0.00025362545,0.00031474864,0.000056816636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032972978,0.00041262497,0.000869352,0.00010117798,0.00037240866,0.0004167602,0.001688162,0.00015084655,0.000044748303],"category_scores_gemma":[0.00010358314,0.00021121674,0.00043208367,0.00085247884,0.0001684274,0.0006995629,0.0009076396,0.0006419636,0.000044925844],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012344297,0.00005003038,0.0000023351217,0.057108607,0.00067435065,0.000001765694,0.01003181,7.217472e-8,0.000037922757,0.2241258,0.68205076,0.025904173],"study_design_scores_gemma":[0.000045228946,0.000059846298,0.000003126656,0.032373298,0.00065157283,0.00019241712,0.00027117308,0.000018903998,0.000023121811,0.0021146922,0.9640073,0.00023930828],"about_ca_topic_score_codex":0.0000127296435,"about_ca_topic_score_gemma":0.000004816232,"teacher_disagreement_score":0.28195652,"about_ca_system_score_codex":0.00008629408,"about_ca_system_score_gemma":0.00036014797,"threshold_uncertainty_score":0.8613169},"labels":[],"label_agreement":null},{"id":"W4398160813","doi":"10.1609/aaaiss.v3i1.31270","title":"Toward Autonomy: Metacognitive Learning for Enhanced AI Performance","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Metacognition; Cognition; Autonomy; Psychology; Computer science; Cognitive science; Cognitive psychology; Artificial intelligence","score_opus":0.009139621173747512,"score_gpt":0.20689810620682078,"score_spread":0.19775848503307328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160813","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":[0.9482802,0.0021262118,0.0010473707,0.0013936971,0.000867129,0.00047021869,0.000014543329,0.0007435923,0.045057025],"genre_scores_gemma":[0.9953687,0.00038447618,0.00041590387,0.00005005315,0.00013348047,0.00017991624,0.0000018868237,0.000045457295,0.0034200775],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918205,0.0000029396008,0.00021501284,0.00019794797,0.00013199438,0.00027005625],"domain_scores_gemma":[0.9995745,0.000064714455,0.00004871757,0.000045762263,0.00023432747,0.000031979078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014636843,0.00019347169,0.00022992218,0.00008305992,0.000115987255,0.00010222923,0.0002333043,0.000064391046,0.000013311623],"category_scores_gemma":[0.000054778186,0.00014457147,0.0001290048,0.00037778006,0.000095996395,0.0009314691,0.00003766796,0.0002496908,0.000010573915],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010448462,0.000011985376,0.0003341083,0.003909061,0.00035174002,2.3852834e-7,0.012973009,0.0008594824,0.9668468,0.008540402,0.0013093102,0.004759359],"study_design_scores_gemma":[0.00011680064,0.00015987201,0.00016793095,0.00035166484,0.000088919536,0.0000064024525,0.0006312845,0.018204695,0.9631198,0.0006243074,0.01632271,0.00020563086],"about_ca_topic_score_codex":8.803755e-7,"about_ca_topic_score_gemma":3.2187546e-7,"teacher_disagreement_score":0.047088537,"about_ca_system_score_codex":0.00008466727,"about_ca_system_score_gemma":0.00004233494,"threshold_uncertainty_score":0.58954537},"labels":[],"label_agreement":null},{"id":"W4398160865","doi":"10.1609/aaaiss.v3i1.31253","title":"Social Smarts with Tech Sparks: Harnessing LLMs for Youth Socioemotional Growth","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Engineering Education and Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Socioemotional selectivity theory; Transformative learning; Disconnection; Social emotional learning; Social competence; Psychology; Competence (human resources); Social change; Social learning; Social skills; Public relations; Social psychology; Political science; Developmental psychology; Economic growth; Pedagogy; Economics","score_opus":0.010234733520226105,"score_gpt":0.21849271156710015,"score_spread":0.20825797804687404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160865","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":[0.6583076,0.0005817109,0.07605762,0.24183606,0.0042811073,0.0014750363,0.000043331227,0.0038028033,0.013614751],"genre_scores_gemma":[0.9855752,0.0000070475276,0.013299246,0.000068424786,0.00016345418,0.00005101086,0.0000015346618,0.00001875988,0.00081531896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923337,0.0000020890918,0.00014401623,0.0002489897,0.00017616605,0.00019537292],"domain_scores_gemma":[0.9995787,0.000024116765,0.00007133979,0.00008222433,0.00022052473,0.000023103285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015635346,0.00012446144,0.00012886632,0.0001080133,0.00021140066,0.00023080893,0.0006250588,0.000078416786,0.0000017227554],"category_scores_gemma":[0.000029155872,0.00008727246,0.000070883405,0.00041445968,0.00014888003,0.0006288898,0.00015046733,0.0001300777,0.0000020986183],"study_design_candidate":"theoretical_or_conceptual","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":[0.000011805113,0.00003660169,0.00068729086,0.00044962534,0.00005007079,1.9324793e-7,0.0068428013,0.000005854627,0.016911445,0.9713864,0.0031710993,0.00044686077],"study_design_scores_gemma":[0.0013460759,0.00089459604,0.0072886725,0.0016130215,0.00031943945,0.0003745838,0.00536207,0.012507536,0.7028139,0.23641503,0.029301198,0.0017638586],"about_ca_topic_score_codex":0.0000034273082,"about_ca_topic_score_gemma":5.01129e-7,"teacher_disagreement_score":0.73497134,"about_ca_system_score_codex":0.000042387008,"about_ca_system_score_gemma":0.000086524655,"threshold_uncertainty_score":0.3558868},"labels":[],"label_agreement":null},{"id":"W4398160873","doi":"10.1609/aaaiss.v3i1.31256","title":"The Impacts of Text-to-Image Generative AI on Creative Professionals According to Prospective Generative AI Researchers: Insights from Japan","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Generative grammar; Generative model; Psychology; Artificial intelligence; Computer science","score_opus":0.02575015745906898,"score_gpt":0.32340933341082173,"score_spread":0.29765917595175273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160873","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":[0.88797337,0.00043298345,0.0028590232,0.09419564,0.00086427724,0.0030846251,0.000057022597,0.00021650956,0.0103165405],"genre_scores_gemma":[0.98983926,0.000047871374,0.0059295557,0.0013384579,0.00027452066,0.0003841614,0.0000012996155,0.000043651366,0.0021412214],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99673045,0.00012544339,0.0006120693,0.00089022645,0.0010356514,0.0006061561],"domain_scores_gemma":[0.99650794,0.00060119067,0.00025837604,0.00049008935,0.0019104345,0.00023197572],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000775311,0.00039780483,0.00045124858,0.00030688389,0.0008815407,0.0011420221,0.0022384033,0.00011582701,0.00001086446],"category_scores_gemma":[0.0012445467,0.00022947125,0.00017067556,0.002120362,0.0004482467,0.0028279624,0.0015331539,0.0005788781,0.00007370676],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028909967,0.000100082834,0.00039479637,0.000060665538,0.00015473238,0.0000022674599,0.086552665,0.00008868236,0.6842115,0.22299573,0.004663326,0.00048643615],"study_design_scores_gemma":[0.00007378488,0.0008495909,0.000678965,0.0007666721,0.000019115272,0.0000027915562,0.015518862,0.0019607255,0.93251485,0.046647687,0.0007033184,0.00026363926],"about_ca_topic_score_codex":0.0003268723,"about_ca_topic_score_gemma":0.000095970645,"teacher_disagreement_score":0.24830332,"about_ca_system_score_codex":0.0003483989,"about_ca_system_score_gemma":0.00040490238,"threshold_uncertainty_score":0.9998949},"labels":[],"label_agreement":null},{"id":"W4398184421","doi":"10.1609/aaaiss.v3i1.31276","title":"Pushing the Limits of Learning from Limited Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; NOMIS Stiftung","keywords":"Mechanism (biology); Process (computing); Limit (mathematics); Computer science; Data science; Cognitive psychology; Psychology; Artificial intelligence; Epistemology; Mathematics","score_opus":0.029607464782294618,"score_gpt":0.24680613859428152,"score_spread":0.2171986738119869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398184421","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":[0.90618795,0.005735353,0.0005986419,0.047031444,0.0018210885,0.0006155029,0.0001447421,0.0011343445,0.036730938],"genre_scores_gemma":[0.99698305,0.00007909975,0.0019678704,0.00010006846,0.00008937875,0.000007865582,0.000007019608,0.000022479011,0.0007431765],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99857646,0.000012457254,0.0003048426,0.00043317606,0.00044578896,0.0002272809],"domain_scores_gemma":[0.99876714,0.00020191529,0.00019322119,0.0006061654,0.00018245826,0.000049084694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030379495,0.00016778907,0.00019131947,0.000074725605,0.00015005123,0.0009951583,0.004292329,0.00003504665,0.000003196894],"category_scores_gemma":[0.00042441566,0.00010123167,0.00010372457,0.0006968471,0.000244799,0.0042712125,0.0024888369,0.00020626804,0.000010292726],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107376974,0.00034900787,0.03230652,0.0014702005,0.0008061223,0.0000086093,0.018499123,0.0003628696,0.61683136,0.2827442,0.031109616,0.015404997],"study_design_scores_gemma":[0.00046537555,0.00034104034,0.007154862,0.0029043397,0.00053314475,0.000097449396,0.0023141187,0.06428892,0.7920735,0.045169022,0.08373034,0.00092792703],"about_ca_topic_score_codex":0.000057222307,"about_ca_topic_score_gemma":0.0000022688382,"teacher_disagreement_score":0.23757517,"about_ca_system_score_codex":0.00001428157,"about_ca_system_score_gemma":0.00007239572,"threshold_uncertainty_score":0.95963347},"labels":[],"label_agreement":null},{"id":"W4404187966","doi":"10.1609/aaaiss.v4i1.31812","title":"The Need for a Feminist Approach to Artificial Intelligence","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Sociology; Artificial intelligence","score_opus":0.04611434491320839,"score_gpt":0.33502690298696064,"score_spread":0.28891255807375227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404187966","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050262224,0.0004718537,0.00025019053,0.42765066,0.0027784063,0.0023179688,0.00004463113,0.00029249123,0.5159316],"genre_scores_gemma":[0.99070776,0.00016562021,0.0009033629,0.0005031362,0.0007257757,0.00012098992,4.3561485e-7,0.000023052022,0.006849862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868304,0.000015234012,0.00027114264,0.00021977542,0.00043064705,0.00038019224],"domain_scores_gemma":[0.9989218,0.00032341576,0.00008798357,0.00009457842,0.00046872743,0.000103486134],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018977621,0.00012248376,0.00015136748,0.0000415973,0.0017990066,0.0012710631,0.00087728765,0.00012226618,0.000002921047],"category_scores_gemma":[0.001370245,0.00007516967,0.00016317867,0.0005771391,0.0008258524,0.00041649467,0.00015875734,0.00020332795,0.0000072032317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005067185,0.000021582164,0.000029615489,0.0000850957,0.000025107598,3.220871e-8,0.062081393,0.00000245259,0.0051981006,0.9264799,0.0049683857,0.0010577001],"study_design_scores_gemma":[0.000026412963,0.00018766685,0.000024753877,0.00015016353,0.00006647273,0.0000020531343,0.0965078,0.00016467088,0.028489968,0.51968753,0.3544279,0.0002646214],"about_ca_topic_score_codex":0.00025618734,"about_ca_topic_score_gemma":0.00012235447,"teacher_disagreement_score":0.94044554,"about_ca_system_score_codex":0.00006670964,"about_ca_system_score_gemma":0.00022567433,"threshold_uncertainty_score":0.9997657},"labels":[],"label_agreement":null},{"id":"W4410822982","doi":"10.1609/aaaiss.v5i1.35613","title":"Dialectic Preference Bias in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Preference; Dialectic; Linguistics; Philosophy; Mathematics; Epistemology; Statistics","score_opus":0.018722294054562987,"score_gpt":0.25396809364420436,"score_spread":0.23524579958964137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410822982","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":[0.88536906,0.007881883,0.021258615,0.019272752,0.0009588941,0.0016669927,0.000016399688,0.001903695,0.06167173],"genre_scores_gemma":[0.9636812,0.0000526967,0.03397445,0.00026438275,0.00001695177,0.000047391815,3.4516626e-7,0.0000091735055,0.0019533613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987859,0.000015238879,0.0002927743,0.0003430777,0.00025231548,0.00031067437],"domain_scores_gemma":[0.999265,0.00004934002,0.00017697144,0.000287829,0.00019352368,0.000027316355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004145143,0.0001722264,0.00023287944,0.00022011744,0.00011028101,0.0001897288,0.0020007298,0.00009414772,0.0000021763888],"category_scores_gemma":[0.00020728126,0.00012314247,0.0000689411,0.0012172884,0.00008202851,0.0015818628,0.0010559094,0.00025896486,0.0000013877005],"study_design_candidate":"theoretical_or_conceptual","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":[0.000038480637,0.00010164742,0.006258806,0.00046396872,0.00001798405,0.0000016590493,0.007602151,0.000009082843,0.17415313,0.8094579,0.00078393775,0.0011112551],"study_design_scores_gemma":[0.00027386294,0.00005673115,0.00062750914,0.0005889345,0.000014515605,0.000010087173,0.00025897997,0.0040643876,0.7382526,0.2554139,0.00020226877,0.00023623883],"about_ca_topic_score_codex":0.00006587225,"about_ca_topic_score_gemma":0.000028745333,"teacher_disagreement_score":0.5640995,"about_ca_system_score_codex":0.00006525699,"about_ca_system_score_gemma":0.0000852765,"threshold_uncertainty_score":0.50216043},"labels":[],"label_agreement":null},{"id":"W4412841080","doi":"10.1609/aaaiss.v6i1.36060","title":"Human-Clinical AI Agent Collaboration","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science","score_opus":0.014355619209005568,"score_gpt":0.3358554955921447,"score_spread":0.32149987638313915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412841080","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":[0.6107613,0.0003125908,0.0010755681,0.32126495,0.003942178,0.0011989792,0.000005642506,0.0006204372,0.06081838],"genre_scores_gemma":[0.985694,0.000029672081,0.0040326184,0.0018494735,0.00011115384,0.00003542797,5.777109e-7,0.000009816831,0.008237293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99858713,0.000037450296,0.0005150672,0.00035366756,0.0002955302,0.00021115023],"domain_scores_gemma":[0.99862725,0.000049254482,0.00029956386,0.0003211171,0.0006532919,0.00004955372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006663489,0.00013780573,0.00023369562,0.00009283371,0.0003438519,0.00023077965,0.0014658585,0.000101601094,0.000006747242],"category_scores_gemma":[0.00029114453,0.00010495638,0.00009752828,0.00085969956,0.00013962423,0.00072203035,0.0007525388,0.00030862237,0.000008365654],"study_design_candidate":"theoretical_or_conceptual","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":[0.000024470255,0.00008635823,0.14579582,0.00047997205,0.000042886975,4.0834053e-7,0.0019180016,0.000048614904,0.01860865,0.8012943,0.030849116,0.0008513478],"study_design_scores_gemma":[0.002372496,0.0018178831,0.3629222,0.0017298474,0.00018915797,0.000047427602,0.0015055095,0.015868204,0.19165678,0.13337018,0.28707075,0.0014495496],"about_ca_topic_score_codex":0.000040648007,"about_ca_topic_score_gemma":0.0000112903035,"teacher_disagreement_score":0.66792417,"about_ca_system_score_codex":0.000055615412,"about_ca_system_score_gemma":0.00015376678,"threshold_uncertainty_score":0.42799968},"labels":[],"label_agreement":null},{"id":"W4412841121","doi":"10.1609/aaaiss.v6i1.36064","title":"Creative Thought Embeddings: A Framework for Instilling Creativity in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Creativity; Cognitive science; Epistemology; Computer science; Psychology; Philosophy; Social psychology","score_opus":0.012895686172021036,"score_gpt":0.2732768155577451,"score_spread":0.26038112938572405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412841121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34951824,0.00035037898,0.62474465,0.005237433,0.00039004488,0.00090244913,0.000017442002,0.00018905374,0.01865031],"genre_scores_gemma":[0.8478425,0.000034964054,0.15030482,0.00025172855,0.00005107492,0.00012498802,4.8306157e-7,0.0000123451155,0.0013770517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985892,0.000013472171,0.00036169606,0.00044686272,0.00021858356,0.00037016554],"domain_scores_gemma":[0.9990656,0.0001663456,0.00021852512,0.0002859307,0.0002286952,0.00003494079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056553946,0.0002003717,0.00033789556,0.00016256998,0.00018578765,0.00016080329,0.0012505654,0.0001289988,0.0000018183138],"category_scores_gemma":[0.00039280264,0.00015698321,0.00012605186,0.0007282024,0.00007015458,0.0014041889,0.00069780875,0.00023827112,5.4561167e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051659285,0.00006987636,0.002838544,0.0002505917,0.000028135466,3.1260143e-7,0.016491344,0.0006894639,0.007842186,0.9712381,0.00007655797,0.00042327747],"study_design_scores_gemma":[0.00079490093,0.00009439644,0.00059502886,0.0015749164,0.000043191532,0.000005230706,0.0042014876,0.29410982,0.18486646,0.5126116,0.0007021551,0.00040080104],"about_ca_topic_score_codex":0.00004261457,"about_ca_topic_score_gemma":0.00001305925,"teacher_disagreement_score":0.4983243,"about_ca_system_score_codex":0.00008076247,"about_ca_system_score_gemma":0.00007534074,"threshold_uncertainty_score":0.64015895},"labels":[],"label_agreement":null},{"id":"W4416553071","doi":"10.1609/aaaiss.v7i1.36928","title":"Filtered-ViT: A Robust Defense Against Multiple AdversarialPatch Attacks","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Adversarial system; Robustness (evolution); Transformer; Noise (video); Motion planning; Exploit","score_opus":0.010541494932510626,"score_gpt":0.22739906790148495,"score_spread":0.21685757296897432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553071","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":[0.5928453,0.0028366998,0.054458734,0.091211624,0.034112483,0.0075135445,0.00021488203,0.0018622107,0.21494451],"genre_scores_gemma":[0.96432334,0.0003905267,0.020541625,0.0008957452,0.0005361741,0.00008647902,0.0000047321873,0.00010287995,0.013118483],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99369514,0.00014396838,0.0017213721,0.0017808231,0.0012308739,0.0014278159],"domain_scores_gemma":[0.9947773,0.0004747728,0.0017126679,0.0013028008,0.0014842584,0.00024819415],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001474184,0.0011222381,0.0013207478,0.0005088519,0.0018305903,0.001049767,0.0063858693,0.00060320157,0.000047559053],"category_scores_gemma":[0.0022371984,0.0009788915,0.0008211476,0.0030449617,0.0013352383,0.0033455216,0.006982911,0.001545739,0.000039634855],"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":[0.0042856266,0.001827118,0.20869786,0.008581916,0.0028124033,0.000041699677,0.053296227,0.17488287,0.25117815,0.23025355,0.045430683,0.01871191],"study_design_scores_gemma":[0.011618139,0.0012174547,0.0153913265,0.010173899,0.0020106828,0.00019412622,0.007882043,0.60909677,0.26075926,0.011067266,0.065074116,0.0055149267],"about_ca_topic_score_codex":0.00020517397,"about_ca_topic_score_gemma":0.000028345214,"teacher_disagreement_score":0.43421388,"about_ca_system_score_codex":0.00040271573,"about_ca_system_score_gemma":0.0006349565,"threshold_uncertainty_score":0.99998724},"labels":[],"label_agreement":null},{"id":"W4416553074","doi":"10.1609/aaaiss.v7i1.36913","title":"LLM-QUBO: An End-to-End Framework for Automated QUBOTransformation from Natural Language Problem Descriptions","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Memorial University of Newfoundland; Lakehead University","funders":"","keywords":"Quantum annealing; Workflow; Scalability; Correctness; Quadratic unconstrained binary optimization; Quantum computer; Transformation (genetics); Optimization problem; Decomposition","score_opus":0.0066484821827630216,"score_gpt":0.24999212599082804,"score_spread":0.24334364380806503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553074","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":[0.84789145,0.001223056,0.0960228,0.043181866,0.005170912,0.0034836675,0.00039427567,0.0015772996,0.0010546796],"genre_scores_gemma":[0.75980186,0.000023802902,0.23875207,0.00057186827,0.00027569637,0.00010464837,0.000017150096,0.00003435663,0.00041853773],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968017,0.000046119218,0.00093051634,0.00089481764,0.0005707195,0.0007561512],"domain_scores_gemma":[0.9978418,0.00020112601,0.00051464746,0.0005373531,0.00072614825,0.00017896076],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00056250085,0.0005684871,0.00060760387,0.00033630614,0.0011556254,0.0011867569,0.0026593017,0.0003012864,0.000010817418],"category_scores_gemma":[0.00018806537,0.00045252917,0.00034262938,0.0017225696,0.00030676532,0.0018506689,0.000756128,0.0006812577,0.0000058946116],"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":[0.00064014527,0.0008291834,0.0006156936,0.0023147713,0.00061218615,0.0000015895741,0.14542514,0.0063560246,0.4423218,0.34505352,0.0027963289,0.05303362],"study_design_scores_gemma":[0.00069599436,0.00077209424,0.0021920272,0.002642656,0.00024693907,0.000022614498,0.002170718,0.81664234,0.12293839,0.04923398,0.0016833434,0.00075889897],"about_ca_topic_score_codex":0.00025107927,"about_ca_topic_score_gemma":0.00003200028,"teacher_disagreement_score":0.81028634,"about_ca_system_score_codex":0.000120561344,"about_ca_system_score_gemma":0.00024326963,"threshold_uncertainty_score":0.9998501},"labels":[],"label_agreement":null},{"id":"W4416553080","doi":"10.1609/aaaiss.v7i1.36924","title":"Predicting Glucose Test Ordering in Hospitalized Patients Using Temporal Models of Clinical Context Embeddings","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Hyperglycemia and glycemic control in critically ill and hospitalized patients","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Context (archaeology); Test (biology); Random forest; Task (project management); Feature (linguistics); Deep learning; Identification (biology); Predictive modelling","score_opus":0.02056152968424357,"score_gpt":0.30262097462882986,"score_spread":0.2820594449445863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553080","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":[0.9841763,0.0012002349,0.000016280961,0.0012774648,0.0020972537,0.0019457953,0.000106811436,0.000049176128,0.0091306865],"genre_scores_gemma":[0.9970084,0.00085285655,0.0006661178,0.0002835563,0.00018472633,0.00005152064,0.000008965219,0.00007269444,0.000871164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9928542,0.0000628847,0.00423354,0.0009494137,0.00094758987,0.00095241785],"domain_scores_gemma":[0.9947303,0.00058523443,0.0016838711,0.00045536036,0.002287576,0.00025764646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012716278,0.0007287448,0.0025525338,0.00040670024,0.0003004965,0.0000976082,0.0009508023,0.00067534694,0.000034322296],"category_scores_gemma":[0.0044901036,0.00059581205,0.00081958366,0.0012506074,0.0012133457,0.0011758818,0.0010136908,0.000978475,0.0000015813474],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004238364,0.002064622,0.9681014,0.0031393913,0.00040358127,0.0000026884736,0.0035077373,0.00006305517,0.014623798,0.0028450266,0.00009364303,0.00091669103],"study_design_scores_gemma":[0.1145236,0.017216025,0.37118873,0.09043035,0.009519391,0.000059098216,0.025022946,0.21578646,0.1347917,0.014451897,0.0027552587,0.00425455],"about_ca_topic_score_codex":0.00077417947,"about_ca_topic_score_gemma":0.000023176828,"teacher_disagreement_score":0.5969127,"about_ca_system_score_codex":0.00020026563,"about_ca_system_score_gemma":0.00058763684,"threshold_uncertainty_score":0.99964935},"labels":[],"label_agreement":null},{"id":"W4416553086","doi":"10.1609/aaaiss.v7i1.36918","title":"CORE-Coma: Deep Learning Framework for Coma Prognosis fromAuditory Event-Related Potentials","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Cardiac Arrest and Resuscitation","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Coma (optics); Electroencephalography; Mismatch negativity; Sensitivity (control systems); Glasgow Coma Scale; Scalp; Oddball paradigm","score_opus":0.009903404354399329,"score_gpt":0.27012196990171444,"score_spread":0.2602185655473151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553086","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":[0.9333626,0.007846249,0.00066379574,0.019491045,0.025215471,0.0055370983,0.000049529182,0.00028751607,0.0075467005],"genre_scores_gemma":[0.98870933,0.0013243981,0.0019815203,0.00017671875,0.001376385,0.00038697472,0.000027393276,0.00009774404,0.0059195603],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9962219,0.000053821503,0.0014105657,0.00077548216,0.0007425262,0.0007957045],"domain_scores_gemma":[0.9961223,0.00054085796,0.001353746,0.00029665628,0.0015129836,0.00017343565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009897304,0.00062236027,0.001219455,0.00031541227,0.0010876188,0.00020379809,0.0006665283,0.0007896173,0.000058468377],"category_scores_gemma":[0.0020260431,0.0004989072,0.0010733337,0.0011988357,0.00080486154,0.0005624316,0.0004904031,0.0009772985,0.00001876275],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060740863,0.0010207137,0.38468933,0.0116476305,0.0051444354,0.0000040810382,0.01412293,0.0003346644,0.46662146,0.083685726,0.023276653,0.0033782965],"study_design_scores_gemma":[0.012675837,0.003200501,0.25241357,0.032156203,0.018679287,0.000053669533,0.027538944,0.0063868114,0.43594962,0.16548124,0.04272229,0.0027420304],"about_ca_topic_score_codex":0.000021126842,"about_ca_topic_score_gemma":0.000002245245,"teacher_disagreement_score":0.13227575,"about_ca_system_score_codex":0.00021281981,"about_ca_system_score_gemma":0.00025397536,"threshold_uncertainty_score":0.99974626},"labels":[],"label_agreement":null},{"id":"W4416553095","doi":"10.1609/aaaiss.v7i1.36916","title":"MedPerturbing LLMs: A Comparative Study of Toxicity, PromptTuning, and Jailbreaks in Medical QA","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Software deployment; Vulnerability (computing); Guard (computer science); Adversarial system; Key (lock); Risk assessment; Baseline (sea); Risk management","score_opus":0.06459046417549213,"score_gpt":0.38510230665759876,"score_spread":0.3205118424821066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553095","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":[0.97022605,0.0014834348,0.0000016147221,0.01889156,0.0007923724,0.0021628363,0.0000035823189,0.000020517904,0.0064180577],"genre_scores_gemma":[0.99752027,0.0008725889,0.000051112434,0.00023677776,0.00015496725,0.0001214076,0.0000010246055,0.000018283443,0.0010235929],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9963868,0.0000789967,0.0016785268,0.000549883,0.0008399596,0.00046581123],"domain_scores_gemma":[0.9975394,0.00037621136,0.0006836303,0.00024638275,0.0009729031,0.00018147791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014502464,0.00035573836,0.0010732609,0.00041342035,0.00027316972,0.000058596623,0.00058190624,0.0003139127,0.00006722042],"category_scores_gemma":[0.0012504823,0.0002703346,0.000097587785,0.0012883246,0.00091120345,0.00046091562,0.0005824897,0.0007108943,0.0000018123803],"study_design_candidate":"qualitative","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":[0.0016519785,0.00331137,0.59327364,0.0044516106,0.00033979,0.0000027418514,0.3450384,0.000008755316,0.042894933,0.004874825,0.0008994482,0.0032524813],"study_design_scores_gemma":[0.0008231313,0.003968101,0.04029776,0.012109482,0.0005747703,0.000051441115,0.4943348,0.002138812,0.4413314,0.003495153,0.00045301244,0.0004221598],"about_ca_topic_score_codex":0.0022785123,"about_ca_topic_score_gemma":0.00069025945,"teacher_disagreement_score":0.5529759,"about_ca_system_score_codex":0.00016059984,"about_ca_system_score_gemma":0.0007278063,"threshold_uncertainty_score":0.9999749},"labels":[],"label_agreement":null},{"id":"W4416553097","doi":"10.1609/aaaiss.v7i1.36930","title":"Transfer Learning for Subject-Independent Sleep DeprivationDetection from Resting-State EEG","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; International Institute for Sustainable Development; Western University","funders":"","keywords":"Electroencephalography; Transfer of learning; Wakefulness; Convolutional neural network; Sleep deprivation; Neurophysiology; Pattern recognition (psychology)","score_opus":0.012113191983847471,"score_gpt":0.23567156061211256,"score_spread":0.2235583686282651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416553097","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":[0.9857688,0.00018776431,0.0014930994,0.006158998,0.002539868,0.0013178363,0.000045631357,0.00018670589,0.0023013207],"genre_scores_gemma":[0.9905583,0.00018492599,0.00041072824,0.00040945542,0.00016309001,0.00010373769,0.0000022593103,0.00005800415,0.008109446],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996539,0.00006657438,0.0010154962,0.0011127654,0.0006004423,0.00066574337],"domain_scores_gemma":[0.9979181,0.00061518303,0.00046863197,0.00027397324,0.0006360466,0.00008802593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064730406,0.0005285313,0.00057303626,0.00028277744,0.0011937458,0.0006528213,0.0014289342,0.0002381638,0.000022132424],"category_scores_gemma":[0.00090218784,0.00044867737,0.00038803884,0.0009819992,0.00044574542,0.0016263641,0.00051385147,0.00071042485,0.000006274605],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010083431,0.00011298442,0.006763255,0.00064236985,0.00010729464,4.1710788e-7,0.0055706087,0.0025963834,0.97924304,0.0023375922,0.00025382554,0.0013638657],"study_design_scores_gemma":[0.0009439451,0.0005503804,0.0040432634,0.00078923325,0.00019599414,0.000011962663,0.0010024403,0.008280452,0.97532064,0.0044193855,0.004039129,0.00040318505],"about_ca_topic_score_codex":0.00013277656,"about_ca_topic_score_gemma":0.000028029743,"teacher_disagreement_score":0.0058081253,"about_ca_system_score_codex":0.0001446069,"about_ca_system_score_gemma":0.000123317,"threshold_uncertainty_score":0.9997965},"labels":[],"label_agreement":null},{"id":"W7106480312","doi":"10.1609/aaaiss.v7i1.36923","title":"Fine-Tuning Large Language Models for Structured ClinicalReport Generation Using GRPO","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Institute for Sustainable Development; Western University","funders":"","keywords":"Relevance (law); Adaptation (eye); Language model; Disk formatting; Medical care; Baseline (sea); Complement (music); English language","score_opus":0.03647737372343484,"score_gpt":0.29663727927137035,"score_spread":0.2601599055479355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106480312","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":[0.64076686,0.0007530425,0.34816697,0.004432353,0.003137825,0.001317582,0.000037517522,0.000117851945,0.0012699678],"genre_scores_gemma":[0.91918725,0.000041023606,0.07770415,0.000303342,0.0005297564,0.000043373762,0.0000037806449,0.00003345097,0.002153882],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964972,0.0000265099,0.001375171,0.0009438851,0.0005046918,0.00065249996],"domain_scores_gemma":[0.99717945,0.00007740769,0.0010545611,0.00062239415,0.0009784155,0.00008778368],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012999361,0.00042099535,0.0006409287,0.00018880353,0.00077986764,0.00054988783,0.0017119079,0.0002989786,0.0000066550333],"category_scores_gemma":[0.00039338335,0.00035895864,0.0003798658,0.0007008818,0.00016559593,0.002055355,0.001433864,0.00034270246,4.5128579e-7],"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":[0.00012606557,0.000103505176,0.0024414922,0.0011144126,0.00020458351,0.0000010862128,0.0096518975,0.016796755,0.71717155,0.24985595,0.0006280935,0.0019045791],"study_design_scores_gemma":[0.0005767926,0.00007454055,0.000052266823,0.00037752968,0.00018013014,0.000019683555,0.0004106749,0.8263391,0.15942334,0.01193993,0.00030921475,0.00029680057],"about_ca_topic_score_codex":0.0000523973,"about_ca_topic_score_gemma":0.000025968204,"teacher_disagreement_score":0.80954236,"about_ca_system_score_codex":0.00013316408,"about_ca_system_score_gemma":0.00040264617,"threshold_uncertainty_score":0.9998862},"labels":[],"label_agreement":null},{"id":"W7106481403","doi":"10.1609/aaaiss.v7i1.36867","title":"Do AI Chatbot Firms Practice What They Preach?","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"","keywords":"Chatbot; Rhetoric; The Internet","score_opus":0.008724836396925463,"score_gpt":0.2690277040742776,"score_spread":0.26030286767735217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106481403","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04201113,0.005536371,0.0006608094,0.7969498,0.018055554,0.002641571,0.000027231064,0.0005008127,0.1336167],"genre_scores_gemma":[0.9499674,0.006628736,0.005756792,0.008704223,0.00053956057,0.00024325421,0.0000015622052,0.000087872584,0.028070593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99506605,0.00008893724,0.001365964,0.0013515601,0.0011595392,0.00096793234],"domain_scores_gemma":[0.9928646,0.00059835415,0.0016133892,0.0013711465,0.0033689188,0.00018357058],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00125941,0.0007864743,0.0007753516,0.00036615794,0.0011609964,0.0050552795,0.0062451,0.00039569446,0.00007753057],"category_scores_gemma":[0.0009552359,0.00062986684,0.0004988463,0.0019529236,0.00058640033,0.026999773,0.004771588,0.0012491315,0.00011576922],"study_design_candidate":"theoretical_or_conceptual","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":[0.0012100703,0.0019492145,0.0045873835,0.0033970647,0.0016592996,0.0000065960767,0.10460771,0.00020988243,0.11542993,0.7069448,0.046760987,0.013237045],"study_design_scores_gemma":[0.001478971,0.0012269043,0.0015239305,0.01152418,0.0016196598,0.0007354675,0.04482136,0.007368808,0.3388121,0.08308611,0.505747,0.0020555004],"about_ca_topic_score_codex":0.00028747812,"about_ca_topic_score_gemma":0.000034153236,"teacher_disagreement_score":0.9079563,"about_ca_system_score_codex":0.00032462762,"about_ca_system_score_gemma":0.00051340717,"threshold_uncertainty_score":0.99961525},"labels":[],"label_agreement":null},{"id":"W7106481835","doi":"10.1609/aaaiss.v7i1.36943","title":"Evaluating Uncertainty in Deep Q-Network Ensembles forTrustworthy Anomaly Detection in Medical Imaging","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Anomaly detection; Trustworthiness; Anomaly (physics); Usability; Medical imaging; Software deployment","score_opus":0.009250932867616976,"score_gpt":0.27869043535183247,"score_spread":0.2694395024842155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106481835","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":[0.9352047,0.0018093653,0.027746646,0.020245153,0.0013527704,0.002378874,0.0000045103366,0.00032221436,0.010935761],"genre_scores_gemma":[0.99461186,0.0005043043,0.0035325733,0.0003819372,0.0001507316,0.00036580357,6.5749344e-7,0.000024112818,0.0004280254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613374,0.000072427196,0.001381698,0.00089503295,0.0007667335,0.0007503447],"domain_scores_gemma":[0.99810976,0.00016184866,0.0007051034,0.00043175396,0.0004909118,0.000100635356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024881754,0.00040740447,0.0005666458,0.000458245,0.000558749,0.0003009027,0.0018384688,0.00028144268,0.000027414222],"category_scores_gemma":[0.0003630029,0.00036767498,0.00023279594,0.0041020755,0.00041794492,0.0011222038,0.0013941203,0.0007455755,0.000002403884],"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":[0.0006935923,0.0006661234,0.2699611,0.0015327996,0.00014268655,0.000007883132,0.006046887,0.012847529,0.08821591,0.14325067,0.0005516803,0.47608313],"study_design_scores_gemma":[0.0009161683,0.0002289993,0.025815133,0.0022374713,0.000082480015,0.00008342775,0.0009739186,0.84851384,0.08080447,0.038128827,0.0015927377,0.00062256056],"about_ca_topic_score_codex":0.0006866702,"about_ca_topic_score_gemma":0.0011801183,"teacher_disagreement_score":0.8356663,"about_ca_system_score_codex":0.0003598328,"about_ca_system_score_gemma":0.00034718114,"threshold_uncertainty_score":0.9998775},"labels":[],"label_agreement":null},{"id":"W7106482260","doi":"10.1609/aaaiss.v7i1.36931","title":"From Bias to Breakdown: Benchmarking Failure Mode Analysisof Single-cell RNA Sequencing Foundation Models in AcuteMyeloid Leukemia","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; York University","keywords":"Benchmarking; Myeloid leukemia; Disease; Foundation (evidence); Set (abstract data type); Benchmark (surveying); Myeloid","score_opus":0.015118186843663842,"score_gpt":0.22297528231364996,"score_spread":0.20785709546998613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106482260","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":[0.9843255,0.0005350815,0.0013191034,0.002781835,0.00071299926,0.0007460938,0.000086845896,0.000028438533,0.009464104],"genre_scores_gemma":[0.9928812,0.0005388481,0.0039546117,0.00043195792,0.00044028758,0.000053029707,0.000091320384,0.00006785272,0.0015409257],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963147,0.000056325567,0.0012647058,0.0011899824,0.00046434833,0.00070996315],"domain_scores_gemma":[0.9980085,0.000048887836,0.00063491345,0.000514134,0.0006451979,0.00014835595],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045298346,0.0006944906,0.0008355847,0.00038098067,0.00035230853,0.00039368815,0.0012596684,0.00061251107,0.000017137523],"category_scores_gemma":[0.00010917041,0.00064674864,0.00046716363,0.0012742854,0.0002623361,0.00017285165,0.0006884945,0.0004469319,0.0000032348414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000646168,0.00014922307,0.00444045,0.00045032025,0.00028849326,8.161372e-7,0.003373204,0.013369752,0.9754072,0.00035184206,0.00044473633,0.0010778331],"study_design_scores_gemma":[0.0009310177,0.00031189487,0.00014882548,0.00091568206,0.00045045532,0.0000045314914,0.0019109567,0.014815155,0.9761724,0.002012855,0.0016825908,0.0006436709],"about_ca_topic_score_codex":0.0021340202,"about_ca_topic_score_gemma":0.00088485325,"teacher_disagreement_score":0.0085556675,"about_ca_system_score_codex":0.00071801746,"about_ca_system_score_gemma":0.0006377005,"threshold_uncertainty_score":0.9995984},"labels":[],"label_agreement":null},{"id":"W7106483534","doi":"10.1609/aaaiss.v7i1.36920","title":"Embedding vs Image-Based AI: A Comparative Fairness Studyin Chest X-ray Analysis","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Gruppo Nazionale per il Calcolo Scientifico; Korea Health Industry Development Institute; Ministero della Salute; Istituto Nazionale di Alta Matematica \"Francesco Severi\"; Canada First Research Excellence Fund; National Science Foundation","keywords":"Embedding; Medical imaging; Scalability; Point (geometry); Medical diagnosis; Image (mathematics); Chest radiograph","score_opus":0.018164016067384187,"score_gpt":0.3231877708658944,"score_spread":0.3050237547985102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106483534","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":[0.68632066,0.0013639384,0.00052445475,0.30213058,0.0015535572,0.0036387758,0.00013090906,0.00035732437,0.0039798226],"genre_scores_gemma":[0.9842185,0.00018524678,0.0015247695,0.008875347,0.0002661859,0.00033818028,0.000014788042,0.0000876135,0.00448939],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99378693,0.00012109773,0.0019055037,0.0016034516,0.0014242174,0.0011587936],"domain_scores_gemma":[0.99308974,0.0009242193,0.0014831151,0.0009698774,0.0032332253,0.00029984702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015488303,0.0011748582,0.0030373284,0.0016973453,0.0010305181,0.0007023405,0.0018523806,0.0004134424,0.00024355939],"category_scores_gemma":[0.0012149896,0.0009673723,0.0014151427,0.008605295,0.001865693,0.0012421025,0.0011637664,0.001090987,0.00003384983],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008057608,0.0052499752,0.31355742,0.017327016,0.019303825,0.000018908831,0.043241747,0.011639467,0.5048656,0.00469513,0.07185895,0.0001843638],"study_design_scores_gemma":[0.0071018394,0.0017529452,0.07065064,0.009552716,0.043841273,0.000009229005,0.022652686,0.047841255,0.76778436,0.00053282303,0.026394485,0.0018857367],"about_ca_topic_score_codex":0.00043356244,"about_ca_topic_score_gemma":0.00005664791,"teacher_disagreement_score":0.29789785,"about_ca_system_score_codex":0.00080255984,"about_ca_system_score_gemma":0.0012367682,"threshold_uncertainty_score":0.99927765},"labels":[],"label_agreement":null},{"id":"W7106484071","doi":"10.1609/aaaiss.v7i1.36902","title":"Quantum Variational Rewinding for Time Series Anomaly Detection","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Bank of Canada; Agnostiq (Canada)","funders":"","keywords":"Series (stratigraphy); Anomaly (physics); Anomaly detection; Quantum; Transmon; Parameterized complexity; Noise (video); Qubit; Quantum computer","score_opus":0.006799866180215701,"score_gpt":0.22477121029056518,"score_spread":0.2179713441103495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106484071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11431107,0.0007562881,0.7387995,0.093344964,0.00533286,0.008805874,0.0003426738,0.001737019,0.036569767],"genre_scores_gemma":[0.945638,0.0001565219,0.02378031,0.0002458141,0.00029878618,0.00074363966,0.0000037447799,0.000041743297,0.02909144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974869,0.000019226409,0.0008760036,0.0007635719,0.00037667423,0.00047765952],"domain_scores_gemma":[0.9973545,0.00010418347,0.0008683562,0.00042001027,0.0011801796,0.00007274834],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006808848,0.0003943817,0.0004542018,0.00031860627,0.0015439655,0.0005893366,0.0016038371,0.0002800446,0.000028705097],"category_scores_gemma":[0.00017113195,0.00035406815,0.00039031848,0.0017636551,0.0003663212,0.0022423088,0.00079608324,0.00026656734,0.000012240382],"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":[0.00020655298,0.00010781387,0.0005225101,0.00043778945,0.00012564116,5.0232448e-8,0.00067824253,0.000022940078,0.46733585,0.5266659,0.0022176052,0.0016791082],"study_design_scores_gemma":[0.00036948232,0.00057843555,0.0019337952,0.0003357776,0.0002047071,0.000042238178,0.00019790746,0.027643679,0.856182,0.07583261,0.036223687,0.0004557056],"about_ca_topic_score_codex":0.00003553098,"about_ca_topic_score_gemma":0.000004450511,"teacher_disagreement_score":0.83132696,"about_ca_system_score_codex":0.00019464531,"about_ca_system_score_gemma":0.00023288565,"threshold_uncertainty_score":0.9998911},"labels":[],"label_agreement":null},{"id":"W7106484130","doi":"10.1609/aaaiss.v7i1.36936","title":"Hermes: A Modular Multi-Agent System for StructuringClinical Text","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Modular design; Unstructured data; Structuring; Bridging (networking); Graph; Architecture; Knowledge graph; Natural language; Semantic network","score_opus":0.020438566578698265,"score_gpt":0.26123595357397716,"score_spread":0.2407973869952789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106484130","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":[0.80316865,0.0024446722,0.14241152,0.024457583,0.014964791,0.0063823774,0.00008864103,0.00066880934,0.005412937],"genre_scores_gemma":[0.94882345,0.000097781696,0.044251084,0.00020829498,0.0002834771,0.00018195617,5.266327e-7,0.00004245535,0.0061109834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956692,0.000033548426,0.0015815634,0.0012796419,0.00061171904,0.00082436245],"domain_scores_gemma":[0.9968855,0.00014407258,0.00089345814,0.0008784719,0.0010440166,0.00015448281],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010311782,0.0005838216,0.00092293456,0.00020477678,0.00071152917,0.0006261078,0.0039271354,0.00035617832,0.00000444535],"category_scores_gemma":[0.0003663244,0.00046500532,0.00064534956,0.0007146099,0.00040577646,0.0011437028,0.0024939962,0.00041964103,0.0000058199316],"study_design_candidate":"theoretical_or_conceptual","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":[0.0007853873,0.0006257094,0.008883446,0.025664724,0.001161309,0.000003066032,0.015420153,0.0049272594,0.2521789,0.6791447,0.0014188893,0.009786477],"study_design_scores_gemma":[0.003098068,0.0004667422,0.0017767947,0.0050162193,0.00055538287,0.00007080254,0.003065655,0.6542554,0.31854036,0.006053963,0.006060702,0.0010399392],"about_ca_topic_score_codex":0.000038235845,"about_ca_topic_score_gemma":0.0000037388595,"teacher_disagreement_score":0.6730907,"about_ca_system_score_codex":0.00028855127,"about_ca_system_score_gemma":0.00034574623,"threshold_uncertainty_score":0.9997802},"labels":[],"label_agreement":null},{"id":"W7106484585","doi":"10.1609/aaaiss.v7i1.36941","title":"How Missing Medication Data Contributes to Bias in Alzheimer’s Disease Machine Learning Models","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; International Development Research Centre","funders":"","keywords":"Medical prescription; Prescription drug; Test (biology); Receiver operating characteristic; Disease; Missing data; Data collection; MEDLINE","score_opus":0.06761014979259704,"score_gpt":0.32014842758378165,"score_spread":0.2525382777911846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106484585","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36040807,0.035700403,0.0007600591,0.58250475,0.0009655883,0.005500593,0.0002885949,0.00013752155,0.0137344515],"genre_scores_gemma":[0.9875462,0.0027227332,0.00022642205,0.0008433208,0.00012271121,0.0001341087,0.000102812286,0.000045025434,0.008256666],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99616015,0.00010237257,0.0008311702,0.00096884253,0.0010965916,0.00084087695],"domain_scores_gemma":[0.9972843,0.00023769739,0.00044081602,0.0005962972,0.0010617075,0.00037918193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002258065,0.00046528535,0.00075155444,0.0006871706,0.00047349348,0.00055125146,0.0016526568,0.00015525999,0.00004090406],"category_scores_gemma":[0.003521122,0.0003651321,0.00015097107,0.0017145914,0.00053600455,0.0018170428,0.0026093912,0.00073402154,0.000006665517],"study_design_candidate":"observational","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":[0.005651192,0.0011407756,0.83076125,0.0032992435,0.0015107209,0.000011597211,0.002386826,0.0000719983,0.12008345,0.012742965,0.0062505333,0.016089473],"study_design_scores_gemma":[0.014417288,0.0020281828,0.28028372,0.032249637,0.011548776,0.000028776338,0.014588694,0.16495332,0.37119624,0.026747128,0.0799736,0.001984624],"about_ca_topic_score_codex":0.00015075113,"about_ca_topic_score_gemma":0.000020056723,"teacher_disagreement_score":0.62713814,"about_ca_system_score_codex":0.00016703413,"about_ca_system_score_gemma":0.00068570086,"threshold_uncertainty_score":0.9998801},"labels":[],"label_agreement":null},{"id":"W7106487133","doi":"10.1609/aaaiss.v7i1.36919","title":"Category-Aware Fine-Tuning and Cross-Age Transferability inImage Memorability Prediction","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Vector Institute","funders":"","keywords":"Generalization; Transferability; Training set; Transfer of learning; Adaptation (eye); Transfer (computing); Image (mathematics)","score_opus":0.012310493598765812,"score_gpt":0.26099163434755773,"score_spread":0.2486811407487919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106487133","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":[0.9794334,0.00021882434,0.0036978154,0.0075719357,0.0022725293,0.001052303,0.00004969421,0.0002461457,0.005457336],"genre_scores_gemma":[0.9963596,0.00015290063,0.00027394097,0.00012990595,0.00008300844,0.000060847273,0.0000021810765,0.000018877054,0.0029187223],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964748,0.00008759459,0.0011703488,0.0011534747,0.0005936425,0.0005201303],"domain_scores_gemma":[0.99784404,0.00007343075,0.00038582072,0.00050376053,0.0010561256,0.00013683787],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015593297,0.00047895944,0.0006228321,0.00021478863,0.0012007115,0.0010142379,0.0012146275,0.00030468393,0.000027845088],"category_scores_gemma":[0.000285101,0.00040007534,0.00031530653,0.0015087615,0.0014662518,0.0030850447,0.0008704282,0.00058785704,0.0000031133743],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009486748,0.0008789529,0.3151771,0.007510862,0.000250219,0.0000018816177,0.017450584,0.00009443305,0.6080263,0.04080653,0.00058715313,0.008267254],"study_design_scores_gemma":[0.002014418,0.0013582857,0.43391845,0.0010262785,0.00035857843,0.00006976415,0.0016159052,0.03254179,0.49749705,0.027227169,0.0014711462,0.0009011833],"about_ca_topic_score_codex":0.00012626992,"about_ca_topic_score_gemma":0.000034922086,"teacher_disagreement_score":0.11874132,"about_ca_system_score_codex":0.00017229911,"about_ca_system_score_gemma":0.00017502745,"threshold_uncertainty_score":0.9998451},"labels":[],"label_agreement":null}]}