{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":675,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":675,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"155b98093770","filters":{"topic":"Explainable Artificial Intelligence (XAI)"}},"results":[{"id":"W2910705748","doi":"10.1073/pnas.1900654116","title":"Definitions, methods, and applications in interpretable machine learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2077,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Army Research Office; Office of Naval Research; U.S. Army; Natural Sciences and Engineering Research Council of Canada; U.S. Navy; Government of Canada; National Science Foundation","keywords":"Interpretability; Computer science; Artificial intelligence; Categorization; Machine learning; Context (archaeology); Interpretation (philosophy); Modularity (biology); Vocabulary; Data science; Focus (optics)","retraction":null,"screen_n_in":null,"score":{"opus":0.06201937909602152,"gpt":0.3515502138729238,"spread":0.2895308347769023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001997954,0.00006374966,0.000115798,0.0002175154,0.000138181,0.00005147085,0.001012706,0.00004146984,0.000007825643],"category_scores_gemma":[0.0004086655,0.00004635016,0.00002985204,0.00118964,0.000273166,0.0008604758,0.000327164,0.0001798479,0.0000037932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002309355,"about_ca_system_score_gemma":0.00002266908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002340885,"about_ca_topic_score_gemma":2.486071e-7,"domain_scores_codex":[0.9989209,0.00001692007,0.0002652844,0.0002498852,0.0004169442,0.0001300242],"domain_scores_gemma":[0.9992642,0.0003353776,0.0002282459,0.00001182414,0.0001377395,0.00002259752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001340552,0.00002140774,0.02146957,0.00002665397,0.000002468719,1.166932e-9,0.0003325905,0.000371229,0.07048021,0.9053732,0.00001154488,0.001909789],"study_design_scores_gemma":[0.00005887906,0.00003982184,0.01424816,0.00007660213,0.000002707513,0.000005422404,0.0004691725,0.09281341,0.2711298,0.6203507,0.0007083549,0.00009696729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9071169,0.001519399,0.01076744,0.00711316,0.00006103412,0.001152151,0.00000866264,0.00009087585,0.07217034],"genre_scores_gemma":[0.9475317,0.00007825343,0.05215426,0.0001218859,0.000008551966,0.00001750581,4.955887e-8,0.000001874678,0.00008592032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2850225,"threshold_uncertainty_score":0.1890105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209901185","doi":"10.1016/s2589-7500(21)00208-9","title":"The false hope of current approaches to explainable artificial intelligence in health care","year":2021,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1361,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute","funders":"National Heart, Lung, and Blood Institute","keywords":"Transparency (behavior); Argument (complex analysis); Process (computing); Black box; Computer science; Workforce; Health care; Artificial intelligence; Psychology; Risk analysis (engineering); Medicine; Political science; Computer security; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.3739980756580752,"gpt":0.4189385308826105,"spread":0.04494045522453533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002998638,0.0005470834,0.002425744,0.0002457085,0.0005623596,0.0008559903,0.004112043,0.0001145043,0.000002574983],"category_scores_gemma":[0.0004946514,0.000337881,0.0003600552,0.002625854,0.000198448,0.000484353,0.001259043,0.0009365882,0.0001243328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007331017,"about_ca_system_score_gemma":0.003615403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003366628,"about_ca_topic_score_gemma":0.0009257427,"domain_scores_codex":[0.9936048,0.0009396195,0.002168175,0.0009850992,0.0007114874,0.001590832],"domain_scores_gemma":[0.9949148,0.001253652,0.0009815872,0.002366885,0.0001524495,0.0003306732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005455045,0.0000741211,0.00000113109,0.006012534,0.0000109834,0.000004812375,0.003046591,0.0001019079,3.034525e-9,0.2066315,0.0005306547,0.7835803],"study_design_scores_gemma":[0.00001987423,0.0002392857,9.604635e-7,0.01088346,0.000006210078,0.00001756306,0.002976874,0.0003595374,0.000007840085,0.009452533,0.9756694,0.0003664746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00000315969,0.9519777,0.03941862,0.005039571,0.0007294847,0.002130245,0.00008657777,0.00008240087,0.0005322615],"genre_scores_gemma":[0.0007384335,0.9969978,0.0009983521,0.0003859252,0.0003874806,0.0003233108,0.0000523113,0.00004618237,0.00007017864],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9751387,"threshold_uncertainty_score":0.9999073,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201437744","doi":"10.1016/j.cjca.2021.09.004","title":"Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":548,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Hamilton Health Sciences; Public Health Ontario; McMaster University; Population Health Research Institute; University of Toronto","funders":"","keywords":"Interpretability; Black box; Rule of thumb; Machine learning; Artificial intelligence; Medicine; Field (mathematics); Key (lock); Data science; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1166038515118146,"gpt":0.3054948642189832,"spread":0.1888910127071686,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002627563,0.0002440245,0.001740617,0.0004355362,0.000270643,0.0001174946,0.001534967,0.0002317886,0.000003418194],"category_scores_gemma":[0.002562837,0.0001509701,0.000414195,0.0007111515,0.00049574,0.0001992886,0.0001831841,0.001224382,0.000005138768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001867878,"about_ca_system_score_gemma":0.003371056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001029061,"about_ca_topic_score_gemma":0.002942967,"domain_scores_codex":[0.9958973,0.002245966,0.0009313667,0.0002890896,0.0001323717,0.0005039348],"domain_scores_gemma":[0.9959648,0.002306803,0.0006511662,0.0005184839,0.0003404994,0.000218279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003920084,0.000002109343,0.0004743498,0.0005070037,0.0005429852,0.001877593,0.002906217,0.02654635,0.000001913317,0.02045209,0.001802712,0.9448828],"study_design_scores_gemma":[0.00006329673,0.0001060557,0.0000378586,0.0007984478,0.0001404959,0.00254007,0.0008258191,0.0003129953,0.0000024047,0.0005134963,0.994513,0.0001460386],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00006134242,0.9832966,0.01130098,0.001002386,0.0004723983,0.0003572686,0.000005456405,0.000003858255,0.003499744],"genre_scores_gemma":[0.01544387,0.9834648,0.0004804769,0.0000597268,0.0003327967,0.00002584087,0.000004701395,0.00002146208,0.0001663306],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9927103,"threshold_uncertainty_score":0.6156384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313648826","doi":"10.3390/s23020634","title":"Survey of Explainable AI Techniques in Healthcare","year":2023,"lang":"en","type":"review","venue":"Sensors","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":530,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Interpretability; Deep learning; Categorization; Health care; Computer science; Field (mathematics); Artificial intelligence; Data science; Medical imaging","retraction":null,"screen_n_in":null,"score":{"opus":0.172470138057368,"gpt":0.4127461832334518,"spread":0.2402760451760838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002217089,0.0003747116,0.001597642,0.0008540783,0.00006681421,0.00007857048,0.001614337,0.0003777331,0.000005468838],"category_scores_gemma":[0.0006302952,0.000348767,0.0002229147,0.003511382,0.00007732349,0.0002226494,0.0004614295,0.0005776649,0.0002898249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002389671,"about_ca_system_score_gemma":0.0006028484,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01717574,"about_ca_topic_score_gemma":0.004523637,"domain_scores_codex":[0.9960828,0.0009934847,0.001161261,0.0007353073,0.0003870615,0.0006401142],"domain_scores_gemma":[0.9971392,0.0007885475,0.0004296047,0.001225512,0.0003065352,0.0001106095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001425595,0.00003840934,0.00004045642,0.009360183,0.00001954273,0.0001384947,0.0002138225,0.00001690668,2.142815e-7,0.009427355,0.0006102986,0.9801329],"study_design_scores_gemma":[0.00003928703,0.0002131754,0.00006768738,0.01927325,0.00002871998,0.00002833059,0.00009086762,0.001666684,0.0005171569,0.004221426,0.9727986,0.001054783],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001649199,0.9962899,0.001199103,0.0002517221,0.0003495461,0.001076391,0.0000406505,0.0004228719,0.0003533293],"genre_scores_gemma":[0.000084846,0.9976227,0.001288572,0.00006241322,0.00003659938,0.00006993923,0.00002998293,0.00005826459,0.0007467342],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9790781,"threshold_uncertainty_score":0.9998964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399433746","doi":"10.1016/j.compeleceng.2024.109370","title":"A review of Explainable Artificial Intelligence in healthcare","year":2024,"lang":"en","type":"review","venue":"Computers & Electrical Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":438,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Research University Higher School of Economics; Grantová Agentura České Republiky","keywords":"Health care; Computer science; Artificial intelligence; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.05443953291172988,"gpt":0.33828205273502,"spread":0.2838425198232901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009599119,0.0006937796,0.002461269,0.001265435,0.00004527008,0.000153131,0.002381736,0.0003226177,0.000005135204],"category_scores_gemma":[0.0003599549,0.0006448428,0.0006430909,0.006426704,0.00003612389,0.0003225606,0.0006585427,0.001368832,0.0001701127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006617333,"about_ca_system_score_gemma":0.0005980011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007653718,"about_ca_topic_score_gemma":0.00000393251,"domain_scores_codex":[0.995232,0.0001823377,0.002007063,0.00108793,0.0004661518,0.001024467],"domain_scores_gemma":[0.997673,0.0006169011,0.0003016658,0.00102527,0.0001430499,0.000240165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[5.935403e-7,0.00004146573,2.419787e-8,0.1128903,0.00003028003,0.0001334651,0.0000400497,0.0003326467,6.070312e-7,0.1076323,0.0003739002,0.7785243],"study_design_scores_gemma":[0.00001175833,0.0001803336,4.759639e-8,0.2651437,0.0001247522,0.0001239223,0.000002090889,0.2897283,0.00004826642,0.003059823,0.4407691,0.0008078337],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.373471e-8,0.6128464,0.3855343,0.0001934257,0.0005975753,0.0005976254,0.000002113055,0.0002058895,0.00002257572],"genre_scores_gemma":[0.00001584676,0.9818293,0.01751314,0.0002060646,0.0001670786,0.0001724975,0.00001107451,0.00007081481,0.00001411481],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7777165,"threshold_uncertainty_score":0.9996003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000965188","doi":"10.1007/s13218-020-00636-z","title":"Measuring the Quality of Explanations: The System Causability Scale (SCS)","year":2020,"lang":"en","type":"article","venue":"KI - Künstliche Intelligenz","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":386,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"Karl-Franzens-Universität Graz; Medizinische Universität Graz; Austrian Science Fund","keywords":"Computer science; Variety (cybernetics); Relevance (law); Artificial intelligence; Transparency (behavior); Scale (ratio); Quality (philosophy); Domain (mathematical analysis); Usability; Traceability; Data science; Machine learning; Human–computer interaction; Software engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1665657092871626,"gpt":0.3220066411088041,"spread":0.1554409318216415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003230297,0.0002735342,0.0003975425,0.00006136102,0.0005589419,0.000246363,0.003336032,0.0001117022,0.00004251482],"category_scores_gemma":[0.001327459,0.0001697141,0.0002496861,0.001295224,0.0003745005,0.0006140546,0.0006139884,0.0004435809,0.0003926704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710621,"about_ca_system_score_gemma":0.0001720252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001144853,"about_ca_topic_score_gemma":0.0005459733,"domain_scores_codex":[0.9959581,0.0008141426,0.001147464,0.0006586618,0.0009327299,0.0004889008],"domain_scores_gemma":[0.9957101,0.001448929,0.000406105,0.001729269,0.0005227862,0.0001827857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008677775,0.0002904645,0.008520423,0.0005902613,0.0002216484,0.00001840057,0.0501617,0.008339814,0.01591022,0.8729082,0.00266817,0.04028395],"study_design_scores_gemma":[0.000182267,0.0002202462,0.004096488,0.0001666718,0.00006212161,0.00004021449,0.02890957,0.1585536,0.7814516,0.008146344,0.0173109,0.0008599282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1944198,0.000883113,0.7683439,0.02281101,0.0008141864,0.001357597,0.0000221003,0.0006069086,0.01074141],"genre_scores_gemma":[0.996641,0.00003553267,0.002005281,0.0009480364,0.000193836,0.00008729989,0.000001917706,0.00001928828,0.0000678265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8647618,"threshold_uncertainty_score":0.6920739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046399757","doi":"10.1109/mc.2020.2996587","title":"A Research Agenda for Hybrid Intelligence: Augmenting Human Intellect With Collaborative, Adaptive, Responsible, and Explainable Artificial Intelligence","year":2020,"lang":"en","type":"article","venue":"Computer","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":376,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Intellect; Computer science; Human intelligence; Artificial intelligence; Set (abstract data type); Artificial intelligence, situated approach; Symbolic artificial intelligence; Marketing and artificial intelligence; Applications of artificial intelligence; Focus (optics); Artificial general intelligence; Computational intelligence; Cognitive science; Intelligent decision support system; Psychology; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.1797266306899354,"gpt":0.3685186475705217,"spread":0.1887920168805863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002400591,0.0004806597,0.0005502685,0.0005769439,0.001450313,0.001241064,0.001857038,0.0001330527,0.00005660547],"category_scores_gemma":[0.0004816451,0.0004499886,0.0001081327,0.003057108,0.0006165734,0.001256036,0.001337119,0.0007604781,0.0001426527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001564826,"about_ca_system_score_gemma":0.0005217457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000543879,"about_ca_topic_score_gemma":0.0000652866,"domain_scores_codex":[0.9946885,0.0006508476,0.0008682264,0.001673446,0.0008148083,0.00130424],"domain_scores_gemma":[0.9951158,0.001914727,0.0002286746,0.0008131237,0.0014676,0.0004600619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001028292,0.0003073488,0.00005813933,0.0002356098,0.0001521305,0.0003839791,0.01650165,0.007188899,0.004254138,0.722998,0.008020342,0.2388714],"study_design_scores_gemma":[0.0001433888,0.004382981,0.00002684751,0.0002504231,0.00001895913,0.00004789158,0.004584694,0.6966619,0.2171628,0.06611322,0.009756108,0.0008507131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01569683,0.0003138099,0.9776158,0.003193222,0.0002601634,0.001549843,0.00001220279,0.0003238055,0.001034269],"genre_scores_gemma":[0.7376114,0.00004583138,0.2604147,0.0008906846,0.0004714374,0.0002582273,0.000009080054,0.00006227568,0.0002363775],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7219146,"threshold_uncertainty_score":0.9998497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176714582","doi":"10.3390/make3030027","title":"Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability","year":2021,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":345,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Artificial intelligence; Computer science; Machine learning; Cluster analysis; Classifier (UML); Stability (learning theory); Random forest; Popularity; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02470034312009067,"gpt":0.3228493839746241,"spread":0.2981490408545334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005984294,0.0001822311,0.0002135047,0.0001204495,0.0006560164,0.0002644707,0.0002033837,0.00009439039,0.00003747507],"category_scores_gemma":[0.001291952,0.0001940888,0.00007390993,0.0003184442,0.0000625087,0.0007288034,0.0001625006,0.0003456824,0.00004180638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001361015,"about_ca_system_score_gemma":0.0002097431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008050053,"about_ca_topic_score_gemma":0.0004732434,"domain_scores_codex":[0.9984121,0.0001913036,0.0003207921,0.0005779847,0.0001305541,0.0003672179],"domain_scores_gemma":[0.9982202,0.0008977762,0.0001012628,0.0002949321,0.0003566912,0.0001291434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001213053,0.001022469,0.002575329,0.0005061392,0.00007352434,0.00006964559,0.009029557,0.2274281,0.01032489,0.07777836,0.0009866345,0.6700841],"study_design_scores_gemma":[0.0001539294,0.0001189963,0.00009733292,0.00003820856,0.00001961141,0.00005453478,0.0003985194,0.9641029,0.006159951,0.007254877,0.0213902,0.0002109849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01027756,0.0008563484,0.9842946,0.0003959689,0.0003959655,0.0001920114,0.000005268637,0.0002167327,0.003365581],"genre_scores_gemma":[0.9750043,0.00006858991,0.01957118,0.00003964221,0.00006834042,0.0001055869,0.00002718632,0.00001824039,0.005097012],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9647267,"threshold_uncertainty_score":0.7914712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2561412020","doi":"10.1371/journal.pone.0181142","title":"\"What is relevant in a text document?\": An interpretable machine learning approach","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":268,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; National Research Foundation","keywords":"Computer science; Artificial intelligence; Relevance (law); Natural language processing; Categorization; Support vector machine; Convolutional neural network; Classifier (UML); Word (group theory); Machine learning; Document classification; Tracing; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.06341091681322418,"gpt":0.2827673665988876,"spread":0.2193564497856634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007403527,0.0001898291,0.0003006263,0.000159654,0.000464346,0.001983189,0.002147149,0.00008188045,0.0000989874],"category_scores_gemma":[0.0002422617,0.0001871956,0.00004779368,0.0001854029,0.00009268866,0.00545316,0.0007609823,0.0004323881,0.000367292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009770435,"about_ca_system_score_gemma":0.00004658988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001118442,"about_ca_topic_score_gemma":0.0002150719,"domain_scores_codex":[0.9979032,0.0001326474,0.0003311609,0.0006615118,0.0004538044,0.000517717],"domain_scores_gemma":[0.9979693,0.00006234684,0.0001988097,0.001533767,0.00009083211,0.0001449732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004168024,0.02041461,0.1123071,0.001004233,0.0008131425,0.000652649,0.166329,0.004045365,0.1524875,0.1609816,0.0004911917,0.3800569],"study_design_scores_gemma":[0.0002354079,0.0003208811,0.0006678928,0.0003932484,0.00001796276,0.00000614257,0.0006283998,0.8883874,0.09744117,0.01087799,0.0005945688,0.0004289616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9119898,0.001104651,0.06057853,0.005050291,0.0003678482,0.0008753035,0.000002363383,0.0004288636,0.01960233],"genre_scores_gemma":[0.9661341,0.0003391149,0.02907059,0.0003291426,0.00005817412,0.00005265707,0.000003425671,0.00002179687,0.003990995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.884342,"threshold_uncertainty_score":0.9990528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138114698","doi":"10.1126/scitranslmed.abb1655","title":"Reproducibility in machine learning for health research: Still a ways to go","year":2021,"lang":"en","type":"review","venue":"Science Translational Medicine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; TD Bank Group; University of Toronto","funders":"National Institute of Mental Health; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Machine learning; Computer science; Reproducibility; Artificial intelligence; Data science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5508278289633713,"gpt":0.532768470116231,"spread":0.01805935884714038,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04902624,0.0003300075,0.001394694,0.001691283,0.0006014879,0.0001410013,0.002553443,0.0000924406,0.00005275819],"category_scores_gemma":[0.01597384,0.0002644586,0.0001625317,0.01009595,0.0008563627,0.0005983405,0.0002796921,0.00100942,0.00006892021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005772401,"about_ca_system_score_gemma":0.004956218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003748395,"about_ca_topic_score_gemma":0.0006504644,"domain_scores_codex":[0.9908908,0.0006256737,0.001391121,0.003621255,0.002272446,0.001198701],"domain_scores_gemma":[0.9935359,0.002513828,0.0002373739,0.002217048,0.0009748687,0.0005209937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004555542,0.00005952394,0.000009893853,0.001460347,0.000004939489,0.000009797032,0.002907041,0.0003770521,0.000008468051,0.07206228,0.0002893494,0.9228067],"study_design_scores_gemma":[0.0001185345,0.0003945936,0.00002391082,0.008518963,0.000009345213,0.00002079529,0.0000682988,0.008790153,0.00001718879,0.01086529,0.9709039,0.0002690091],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001870435,0.7220171,0.2599781,0.0152752,0.0004654147,0.001799566,0.00001094807,0.00006015976,0.0003915733],"genre_scores_gemma":[0.0004187706,0.9434252,0.05408718,0.000641585,0.0004769167,0.0004882917,0.00007730649,0.00003733327,0.0003474414],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9706146,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888580379","doi":"10.1007/978-3-319-99740-7_21","title":"Explainable AI: The New 42?","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":252,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Exploit; Function (biology); Task (project management); Artificial neural network; Machine learning; Cognitive science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02554129803942862,"gpt":0.267225479299438,"spread":0.2416841812600094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001569185,0.0006780875,0.0005313509,0.0006840983,0.0007837857,0.001600022,0.008783604,0.0003746907,0.000262578],"category_scores_gemma":[0.0002542482,0.0005054731,0.000189691,0.001228884,0.001500735,0.001371978,0.002699469,0.00115105,0.001061767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004320728,"about_ca_system_score_gemma":0.001554366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000200504,"about_ca_topic_score_gemma":0.0004562067,"domain_scores_codex":[0.9946242,0.00006113447,0.0006806917,0.001961745,0.001415319,0.001256936],"domain_scores_gemma":[0.9950741,0.0007122585,0.0003181744,0.003087818,0.0004862775,0.0003213561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001184995,0.00003846077,0.00001840608,0.00003067993,0.00002117243,0.0002096345,0.005663446,0.01791391,0.000235229,0.211918,0.004547774,0.7593915],"study_design_scores_gemma":[0.00009368134,0.0002433961,0.00001138015,0.0002278317,0.000007644244,0.00009093472,0.000001360801,0.2292827,0.0109164,0.6983115,0.06008453,0.000728677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003260356,0.000548709,0.9770159,0.00771268,0.003011493,0.0005373516,0.000001629157,0.0002488408,0.01089075],"genre_scores_gemma":[0.1098753,0.0002462406,0.8051013,0.03773265,0.008588174,0.00006585538,0.00000927458,0.0002445764,0.03813656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7586628,"threshold_uncertainty_score":0.9997397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400810536","doi":"10.1109/access.2024.3431437","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":210,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Computer science; Field (mathematics); Systems engineering; Data science; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2151034924898165,"gpt":0.459124395238327,"spread":0.2440209027485105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001041266,0.0002314254,0.0002817839,0.0004181556,0.0008589418,0.002192084,0.001457857,0.0001593297,0.00002540643],"category_scores_gemma":[0.0003731366,0.0002240535,0.0001424383,0.001244305,0.000117672,0.00171894,0.0004172133,0.0003298424,0.00004009833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458493,"about_ca_system_score_gemma":0.000285106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000343987,"about_ca_topic_score_gemma":0.0005705218,"domain_scores_codex":[0.9973419,0.0001106943,0.000511817,0.0009322559,0.0003277683,0.0007755239],"domain_scores_gemma":[0.9955,0.002901735,0.00006227948,0.0006526283,0.0007140072,0.0001692999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000287012,0.00008307935,0.0000172488,0.0005557672,0.00004997291,0.00003325898,0.002118363,0.0002998526,0.00182643,0.5094329,0.02115368,0.4644008],"study_design_scores_gemma":[0.0000353915,0.0003431575,0.00002215589,0.0002320457,0.0000170738,0.00002524397,0.001083667,0.1507521,0.117002,0.2354422,0.494696,0.0003490201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005039578,0.007150738,0.9719965,0.009211103,0.003719301,0.001643302,0.00001638505,0.0004166623,0.0008064475],"genre_scores_gemma":[0.8975225,0.005920322,0.07811157,0.002309078,0.005703515,0.005050626,0.00002006517,0.000169826,0.00519246],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8938849,"threshold_uncertainty_score":0.9988437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3187467055","doi":"10.1145/3546577","title":"Post-hoc Interpretability for Neural NLP: A Survey","year":2022,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretability; Computer science; Categorization; Artificial intelligence; Post hoc; Machine learning; Data science; Accountability; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1804175306382501,"gpt":0.3942971125104791,"spread":0.213879581872229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.02267497,0.0008798552,0.002336799,0.0004063899,0.0007641572,0.0006684168,0.009256629,0.0003047591,0.000101305],"category_scores_gemma":[0.01225553,0.0008527988,0.00109212,0.001806181,0.0001418606,0.0004584639,0.00626866,0.00109108,0.0001337641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005009563,"about_ca_system_score_gemma":0.0007843031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001738315,"about_ca_topic_score_gemma":0.0007400788,"domain_scores_codex":[0.9837036,0.01055293,0.001762411,0.002062411,0.0006589691,0.001259651],"domain_scores_gemma":[0.970855,0.02312321,0.0009869301,0.004257787,0.0005246151,0.0002524694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006275165,0.0001017709,0.0001019035,0.001995891,0.0000821646,0.00001594912,0.0003109762,0.0000859437,1.43758e-7,0.0005231227,0.0003198607,0.996456],"study_design_scores_gemma":[0.0001468017,0.0008566947,0.0004955076,0.001186734,0.0001159869,0.00008884116,0.00003865868,0.0457655,0.000004083316,0.001216739,0.9482879,0.001796568],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001644114,0.7628838,0.230177,0.0000770268,0.003786387,0.001927196,0.0002638861,0.0006046657,0.0001156],"genre_scores_gemma":[0.00250143,0.9627492,0.03109632,0.0004985003,0.0006399711,0.000445609,0.00137392,0.000322486,0.000372504],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9946594,"threshold_uncertainty_score":0.9993923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197107524","doi":"10.1016/j.cpet.2021.07.001","title":"A Brief History of AI: How to Prevent Another Winter (A Critical Review)","year":2021,"lang":"en","type":"review","venue":"PET Clinics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Intensive care medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1508045333742263,"gpt":0.4157173319597567,"spread":0.2649127985855304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001501432,0.0004189717,0.002279024,0.0001501875,0.00002944184,0.0000710806,0.002078193,0.0001870039,0.0003974071],"category_scores_gemma":[0.004044416,0.0003822179,0.001023788,0.0005113286,0.0001403359,0.0002543923,0.0008662458,0.0006632101,0.0003975736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004907395,"about_ca_system_score_gemma":0.001696236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001127739,"about_ca_topic_score_gemma":0.00001741948,"domain_scores_codex":[0.9959662,0.000670615,0.001386246,0.0009903122,0.000515979,0.0004706516],"domain_scores_gemma":[0.9955392,0.001232886,0.000412879,0.002080598,0.0005322835,0.0002020983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[7.010914e-7,0.0002243892,2.951546e-7,0.01983732,0.00004986576,0.0001392803,0.0001314715,3.529995e-7,1.871606e-7,0.01177797,0.2369436,0.7308945],"study_design_scores_gemma":[0.00001421284,0.0001121773,6.294893e-8,0.0459741,0.0001946703,0.00006114374,0.000004867632,0.0000708174,0.000004223624,0.0002849128,0.9529245,0.0003542663],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.000108e-8,0.9361795,0.05635665,0.003194638,0.002119838,0.0006626598,0.00001483627,0.00006321444,0.001408653],"genre_scores_gemma":[4.698747e-7,0.9705074,0.01140273,0.006641814,0.0002235462,0.000123267,0.000008512306,0.00005180789,0.01104047],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7305403,"threshold_uncertainty_score":0.999863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309630525","doi":"10.1016/j.media.2022.102684","title":"Guidelines and evaluation of clinical explainable AI in medical image analysis","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"BC Cancer Foundation","keywords":"Guideline; Computer science; Data mining; Artificial intelligence; Medical physics; Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.106462754669057,"gpt":0.4673112791791384,"spread":0.3608485245100814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03186496,0.0002342665,0.001226778,0.001799347,0.000241636,0.0001255317,0.001850192,0.0001830551,0.007003912],"category_scores_gemma":[0.01511698,0.000217691,0.0006793704,0.01144297,0.0004437199,0.0007372114,0.00146413,0.000756394,0.00002528405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001319545,"about_ca_system_score_gemma":0.0008804736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260452,"about_ca_topic_score_gemma":0.002236819,"domain_scores_codex":[0.9876338,0.002349663,0.002491142,0.001045174,0.005939686,0.0005405658],"domain_scores_gemma":[0.9955252,0.001023817,0.0004635105,0.001155003,0.001260175,0.0005723198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001374334,0.003131842,0.1890351,0.00009712,0.009828517,0.002493722,0.003499475,0.02091805,0.0006025819,0.007407364,0.01603569,0.7468131],"study_design_scores_gemma":[0.0004191904,0.00008315849,0.008704822,0.00001054392,0.002200094,0.000008409175,0.000725102,0.9841737,0.0003265788,0.002186808,0.000944874,0.0002166758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3209193,0.0007578935,0.6552469,0.02126199,0.0002184164,0.0002837507,0.000008958584,0.00008436309,0.001218361],"genre_scores_gemma":[0.9821557,0.0002305511,0.01441965,0.002694298,0.000126194,0.0001215047,0.00005066841,0.00001384424,0.0001876347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9632557,"threshold_uncertainty_score":0.9968988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081090156","doi":"10.1007/978-3-030-57321-8_1","title":"Explainable Artificial Intelligence: Concepts, Applications, Research Challenges and Visions","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Transparency (behavior); Acknowledgement; Vision; Artificial intelligence; European union; Data science; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1208874855785112,"gpt":0.3665195889072074,"spread":0.2456321033286962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002812716,0.0005819011,0.0006371909,0.001219196,0.0009302624,0.00100064,0.004545227,0.0004506537,0.00003643081],"category_scores_gemma":[0.0003671487,0.0005774387,0.0001067333,0.001350321,0.002332653,0.0009737153,0.003252271,0.001783137,0.0003741877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003644287,"about_ca_system_score_gemma":0.0008136214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002788512,"about_ca_topic_score_gemma":0.0001055688,"domain_scores_codex":[0.9934236,0.0001307506,0.0008489969,0.002724781,0.001713873,0.001157969],"domain_scores_gemma":[0.9950729,0.001576763,0.0002377331,0.001854556,0.000782855,0.000475172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003776998,0.00002281837,7.423517e-7,0.00004324704,0.000004360481,0.00004842485,0.002053023,0.001234775,0.00009102057,0.4792356,0.000008761949,0.5172535],"study_design_scores_gemma":[0.00002609615,0.0002681743,0.000005029796,0.0002578582,0.000004227491,0.00003549699,0.00003089611,0.1526194,0.005756201,0.8322422,0.008196787,0.0005575957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001080238,0.008046805,0.9749053,0.006341897,0.0004756014,0.001100888,0.000004522512,0.0002314942,0.008882677],"genre_scores_gemma":[0.4100168,0.009434678,0.5744992,0.002256391,0.002532754,0.0004138915,0.00001503938,0.0001665583,0.00066459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5166959,"threshold_uncertainty_score":0.9996677,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404817209","doi":"10.3389/frobt.2024.1444763","title":"Enhancing interpretability and accuracy of AI models in healthcare: a comprehensive review on challenges and future directions","year":2024,"lang":"en","type":"review","venue":"Frontiers in Robotics and AI","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Interpretability; Generalizability theory; Computer science; Health care; Transparency (behavior); Artificial intelligence; Data science; Implementation; Healthcare system; Applications of artificial intelligence; Deep learning; Risk analysis (engineering); Medicine; Computer security; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06259688310049519,"gpt":0.352237612523537,"spread":0.2896407294230419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004534427,0.000321501,0.001447882,0.000335213,0.00005129263,0.0000759192,0.0002862608,0.0001965118,3.450527e-7],"category_scores_gemma":[0.00007811799,0.0002660221,0.00009896583,0.0004553196,0.000108695,0.0003009714,0.0003294058,0.0007851187,6.7235e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001044461,"about_ca_system_score_gemma":0.0001471717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008392977,"about_ca_topic_score_gemma":0.0001635459,"domain_scores_codex":[0.997866,0.0002858652,0.0007296129,0.000706594,0.0001490784,0.0002628489],"domain_scores_gemma":[0.9989706,0.0002228947,0.0001794691,0.000444396,0.00008660032,0.00009609186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001732562,0.00003040606,0.000003300031,0.05437226,0.0000243436,0.00001036892,0.0009707727,0.00004767779,3.961911e-8,0.01877128,0.0001478778,0.92562],"study_design_scores_gemma":[0.0001211773,0.000334023,0.00001992221,0.208592,0.0003044611,0.00006133984,0.0006374249,0.0568016,0.000003538297,0.09047274,0.641708,0.0009437439],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002011801,0.9733206,0.01798353,0.00703695,0.0008651409,0.000730243,0.000008099501,0.00002263913,0.00003078812],"genre_scores_gemma":[0.00009075991,0.9920641,0.007300196,0.0004196657,0.00005190849,0.00004704316,0.000002574113,0.00001676456,0.000007011339],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9246762,"threshold_uncertainty_score":0.9999792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297183943","doi":"10.1177/01655515221112844","title":"Knowledge-graph-based explainable AI: A systematic review","year":2022,"lang":"en","type":"review","venue":"Journal of Information Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Cape Breton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Relation (database); Knowledge graph; Selection (genetic algorithm); Information retrieval; Artificial intelligence; Natural language processing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.07343320096530884,"gpt":0.3730624407105773,"spread":0.2996292397452684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01319099,0.0003983372,0.002230589,0.002863101,0.0006868178,0.001113952,0.007158196,0.00009382927,0.0001142335],"category_scores_gemma":[0.00448695,0.0002862251,0.0008238291,0.009190318,0.0002373225,0.01372757,0.0005944537,0.000858004,0.0004197192],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009679322,"about_ca_system_score_gemma":0.006392972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004071411,"about_ca_topic_score_gemma":6.16333e-7,"domain_scores_codex":[0.9925253,0.0004852437,0.003831098,0.0002721215,0.002313911,0.000572346],"domain_scores_gemma":[0.990675,0.0007262712,0.005258337,0.001247261,0.001770539,0.0003225604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000113994,0.00005739853,6.272849e-8,0.7570063,0.00002891083,0.00002259332,0.0005818299,0.0001170193,1.550954e-7,0.01190681,0.001911681,0.228366],"study_design_scores_gemma":[0.00004318155,0.0001364619,3.220065e-8,0.2436807,0.0002101836,0.0004831489,0.0001211608,0.001943523,0.000009313821,0.0002110608,0.7528747,0.0002864992],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.525106e-8,0.8441957,0.1510352,0.0001582289,0.0009762435,0.001112422,0.000002988715,0.00004395155,0.002475205],"genre_scores_gemma":[0.000003708278,0.9943706,0.004176002,0.001193898,0.00004023255,0.0001393311,0.000002895036,0.0000101768,0.00006311468],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.750963,"threshold_uncertainty_score":0.999959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391399751","doi":"10.1613/jair.1.15348","title":"Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Austrian Science Fund; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Canadian Institute for Advanced Research","keywords":"Human-in-the-loop; Reinforcement learning; Position (finance); Loop (graph theory); Computer science; Reinforcement; Artificial intelligence; Business; Psychology; Mathematics; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4886989474982671,"gpt":0.4569376480713653,"spread":0.03176129942690176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01609841,0.0001747721,0.000245735,0.001040339,0.000399817,0.000978554,0.000853067,0.00009481851,0.00002484346],"category_scores_gemma":[0.0006215171,0.0001332765,0.00006062966,0.0006302557,0.000337882,0.001026968,0.0002422873,0.001157163,0.00003799869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000164014,"about_ca_system_score_gemma":0.0002109403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001747567,"about_ca_topic_score_gemma":0.0002119761,"domain_scores_codex":[0.9954813,0.001348796,0.0008657393,0.0003860165,0.001365256,0.0005529216],"domain_scores_gemma":[0.9973912,0.001399598,0.0001405991,0.0003223876,0.0005749958,0.0001712666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007418684,0.0001309756,0.00002582832,0.00008239266,0.00002895186,0.0006581799,0.008379174,0.0007639015,0.001902539,0.6098085,0.0002557014,0.3778896],"study_design_scores_gemma":[0.0002084123,0.01844046,0.003094118,0.003374224,0.00004051615,0.001221167,0.06385919,0.2636647,0.06693105,0.5611815,0.01660659,0.001378051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7477316,0.04249654,0.1380889,0.05591502,0.001609284,0.001782524,0.000004152223,0.0001609901,0.01221098],"genre_scores_gemma":[0.9889548,0.01029009,0.0001776831,0.0001011644,0.0001696334,0.00001189565,0.000001244325,0.00001348956,0.0002799479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3765116,"threshold_uncertainty_score":0.9436218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403334020","doi":"10.1145/3654777.3676450","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1043031927296003,"gpt":0.3456309742213749,"spread":0.2413277814917746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002414408,0.0001908476,0.000196947,0.0001705827,0.0002653303,0.0007339276,0.001124373,0.00006123649,0.0001495506],"category_scores_gemma":[0.00008509173,0.0001109956,0.00006933932,0.0009812253,0.00014131,0.0009803624,0.000217585,0.0001429649,0.00008668765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007011749,"about_ca_system_score_gemma":0.0002319931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003794447,"about_ca_topic_score_gemma":0.0003169961,"domain_scores_codex":[0.9973073,0.0003559139,0.0004060156,0.000522015,0.001099968,0.0003087994],"domain_scores_gemma":[0.9982741,0.0003070982,0.0001210622,0.0007383279,0.0004961723,0.00006320511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001049066,0.0002644316,0.001872475,0.000135329,0.0002440605,0.00001593837,0.01628629,0.002223358,0.01739517,0.8652802,0.003851483,0.09242076],"study_design_scores_gemma":[0.0001480645,0.0006203249,0.002189409,0.000442483,0.0001549717,0.00001952678,0.002853529,0.2013077,0.7298962,0.060121,0.001804742,0.0004420408],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7104168,0.0007533851,0.2503306,0.002016837,0.000520216,0.0008307959,0.000003960851,0.0005702379,0.03455719],"genre_scores_gemma":[0.9958168,0.000007286147,0.003187867,0.00009534427,0.00005931704,0.00005689347,0.000004842114,0.00001376444,0.0007578763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8051592,"threshold_uncertainty_score":0.7077281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224940987","doi":"10.1145/3491102.3501999","title":"Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation","year":2022,"lang":"en","type":"article","venue":"CHI Conference on Human Factors in Computing Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Science Foundation","keywords":"Computer science; Delegation; Testbed; Scalability; Moderation; Benchmark (surveying); Data science; Knowledge management; Artificial intelligence; Machine learning; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1900154621451945,"gpt":0.369592466663248,"spread":0.1795770045180535,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000852439,0.0002591631,0.0004175031,0.0004608227,0.001295709,0.0004173027,0.0006882922,0.00006254687,0.00003494234],"category_scores_gemma":[0.00003876963,0.0002804086,0.00005185379,0.0007148259,0.00006246426,0.000499041,0.0002761044,0.0003962344,0.000004531716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004675535,"about_ca_system_score_gemma":0.0001697958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003274152,"about_ca_topic_score_gemma":0.001167914,"domain_scores_codex":[0.9964155,0.0007806723,0.001057938,0.0006502286,0.0007877407,0.0003079218],"domain_scores_gemma":[0.9980369,0.0001541288,0.0005888063,0.0005869169,0.000556263,0.00007699247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001277278,0.001544039,0.013937,0.00005615732,0.0000493072,0.0003966788,0.0451353,0.436721,0.005910361,0.4958194,0.0001398407,0.0002781024],"study_design_scores_gemma":[0.0007305442,0.001687052,0.002576479,0.00007493219,0.000009207359,0.0001391209,0.04583793,0.9433501,0.00185734,0.003306733,0.0000152919,0.0004152134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8743539,0.00001141159,0.1234045,0.00005941291,0.0006657607,0.001095545,0.00001154586,0.0001146178,0.0002832522],"genre_scores_gemma":[0.9995582,1.188749e-7,0.00008345614,0.00005696958,0.00007197909,0.0001040241,0.00004628189,0.0000151617,0.00006387153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5066292,"threshold_uncertainty_score":0.9999648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387344906","doi":"10.1145/3610219","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"Institut National Du Cancer; Microsoft Research","keywords":"Intuition; Heuristics; Artificial intelligence; Computer science; Empirical evidence; Psychology; Cognitive science; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.109951523065953,"gpt":0.3618635442424757,"spread":0.2519120211765228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006918367,0.0002136259,0.0002351965,0.0006921429,0.0006167041,0.0002592756,0.002475822,0.0000755352,0.00001156504],"category_scores_gemma":[0.0002286457,0.0001471662,0.0001052547,0.001445715,0.0001145587,0.001131279,0.0006881726,0.0004657243,0.00002094321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003738685,"about_ca_system_score_gemma":0.00001985484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006293996,"about_ca_topic_score_gemma":0.00009274853,"domain_scores_codex":[0.9979441,0.0000341539,0.0005876211,0.0004914763,0.0006370809,0.0003056102],"domain_scores_gemma":[0.9979025,0.0004942954,0.0005735767,0.0007152774,0.0002831033,0.00003127201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001247322,0.0003395282,0.002780783,0.00007424364,0.00005530809,0.000004143819,0.01172186,0.01563406,0.0721806,0.8816594,0.003367324,0.01205802],"study_design_scores_gemma":[0.0003006324,0.0009948004,0.006409141,0.00310122,0.00001588563,0.00001401898,0.004108467,0.06990027,0.1677325,0.7469143,0.0001721758,0.000336596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649375,0.000006181976,0.02867799,0.0016695,0.0004639601,0.0005409149,0.000001821539,0.0001827592,0.003519386],"genre_scores_gemma":[0.9981757,0.00000382307,0.001380306,0.0002175678,0.0001208136,0.00004489831,0.000001692435,0.0000218476,0.00003336236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1347451,"threshold_uncertainty_score":0.6001262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3023454035","doi":"10.1109/tvcg.2020.3030354","title":"Explainable Matrix - Visualization for Global and Local Interpretability of Random Forest Classification Ensembles","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Interpretability; Computer science; Visualization; Random forest; Machine learning; Scalability; Artificial intelligence; Data mining; Data visualization; Visual analytics; Focus (optics); Creative visualization; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.03673167126332117,"gpt":0.3144207998614237,"spread":0.2776891285981025,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002865717,0.0002015482,0.0002761623,0.00013851,0.0002678733,0.0001672279,0.0002446327,0.0001274131,0.000003382819],"category_scores_gemma":[0.00002014339,0.0002082618,0.00009422078,0.0008139728,0.0001818326,0.0005953182,0.00001047619,0.00007920167,0.000001277059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003530933,"about_ca_system_score_gemma":0.00005474618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002905835,"about_ca_topic_score_gemma":0.00004937401,"domain_scores_codex":[0.9983678,0.0001530982,0.0005077673,0.0005226258,0.0002392126,0.0002094636],"domain_scores_gemma":[0.9988809,0.0002238469,0.0001705555,0.0002401431,0.0003288809,0.0001557352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002069415,0.0001860241,0.0004131394,0.0002118958,0.00003525164,7.037166e-7,0.001889491,0.004621929,0.0001103695,0.9775581,0.00005448568,0.01471161],"study_design_scores_gemma":[0.0006496389,0.00052613,0.0002638177,0.00003928711,0.0000285012,0.000005116885,0.0002651826,0.984157,0.006865528,0.006715753,0.0002924437,0.0001915508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02003059,0.00006413845,0.9786727,0.0002123223,0.0002323074,0.0005843855,0.00002146544,0.0001652518,0.00001678526],"genre_scores_gemma":[0.9961821,0.0001499793,0.003055503,0.0004951199,0.00003165601,0.00005407043,0.00001257179,0.00001357933,0.000005365034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9795351,"threshold_uncertainty_score":0.849267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386541762","doi":"10.3390/sym15091723","title":"Deep Learning and Neural Networks: Decision-Making Implications","year":2023,"lang":"en","type":"article","venue":"Symmetry","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Canada West","funders":"","keywords":"Interpretability; Generalizability theory; Computer science; Transparency (behavior); Artificial intelligence; Artificial neural network; Deep learning; Machine learning; Management science; Deep neural networks; Decision support system; Data science; Psychology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02013936258471615,"gpt":0.3103942398186536,"spread":0.2902548772339374,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003693164,0.0001013126,0.0001069674,0.0002108854,0.0003999177,0.0002488281,0.0004847988,0.00005608469,0.00001174669],"category_scores_gemma":[0.0004338955,0.0001013149,0.00003937089,0.001684976,0.0000427525,0.000405356,0.0004605529,0.0002013973,0.000145511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002635011,"about_ca_system_score_gemma":0.00001194878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001117874,"about_ca_topic_score_gemma":0.00001767981,"domain_scores_codex":[0.9988548,0.00005516624,0.0001981886,0.0003685712,0.0001493629,0.0003738688],"domain_scores_gemma":[0.9985998,0.0008499494,0.00005957625,0.0003426704,0.00006330817,0.000084639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002001738,0.00000901056,0.01123534,0.000004146911,0.000006529651,0.00001817996,0.0003116028,0.01850666,0.00007800759,0.07720152,0.000382406,0.8922446],"study_design_scores_gemma":[0.00002428696,0.00002546323,0.01093828,0.00001788339,0.000002463494,0.00001703687,0.0002487126,0.9584803,0.00005779664,0.02897436,0.001087759,0.0001256383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04716241,0.0004095254,0.9491691,0.0007431004,0.0003485915,0.00009754326,2.212596e-7,0.0005028075,0.001566701],"genre_scores_gemma":[0.9882717,0.00007421849,0.01123118,0.0002207361,0.00009474174,0.00001466744,0.00000130172,0.00001198056,0.00007945375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9411093,"threshold_uncertainty_score":0.4131502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403457107","doi":"10.1016/j.imu.2024.101587","title":"A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges","year":2024,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"","keywords":"Health care; Data science; Computer science; Management science; Artificial intelligence; Engineering; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.105293366208369,"gpt":0.3654136048190884,"spread":0.2601202386107194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003419224,0.0001868019,0.0004182084,0.0007197173,0.00005074562,0.00005910526,0.0006926072,0.0001168004,0.000009473817],"category_scores_gemma":[0.0005654348,0.000167717,0.00002050176,0.001788932,0.0003147786,0.0006851071,0.0002084063,0.0003560051,0.00002777352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001168375,"about_ca_system_score_gemma":0.0002168109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002412986,"about_ca_topic_score_gemma":0.002216745,"domain_scores_codex":[0.9973577,0.0001636161,0.00140222,0.000270327,0.0004077825,0.0003984153],"domain_scores_gemma":[0.9979225,0.001087452,0.0001604387,0.0005264085,0.0001929116,0.0001102474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009758169,0.00004456769,0.000410674,0.0009586599,0.000006342401,0.00001509887,0.02171372,0.0002349227,0.00002074488,0.5934647,0.00005823372,0.3830625],"study_design_scores_gemma":[0.0001726804,0.0004921221,0.002680259,0.001781724,0.000006964009,0.00003271676,0.01825693,0.7816449,0.002725343,0.1857631,0.005971882,0.0004714039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02205643,0.04579627,0.9066421,0.01977165,0.0007643562,0.001892184,0.00001278339,0.0002714237,0.002792769],"genre_scores_gemma":[0.9848362,0.006894615,0.007806611,0.000254999,0.00004475457,0.0001254444,0.000009301429,0.00001085908,0.00001721211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9627798,"threshold_uncertainty_score":0.6839299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4296708919","doi":"10.1145/3563691","title":"Explainable Convolutional Neural Networks: A Taxonomy, Review, and Future Directions","year":2022,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Taxonomy (biology); Generalization; Relevance (law); Perspective (graphical); Machine learning; Feature (linguistics); Interpretation (philosophy)","retraction":null,"screen_n_in":null,"score":{"opus":0.09707560278384564,"gpt":0.3225294605025278,"spread":0.2254538577186821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.005262788,0.0006813743,0.001818935,0.0003043734,0.001315497,0.0003768279,0.003065442,0.0002236496,0.0001963693],"category_scores_gemma":[0.0007178815,0.0006655076,0.000448318,0.002242206,0.0001302537,0.0004957028,0.00355627,0.001225842,0.00005028443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003341652,"about_ca_system_score_gemma":0.0003515761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002682907,"about_ca_topic_score_gemma":0.0000398612,"domain_scores_codex":[0.9925243,0.003684863,0.001108025,0.001345915,0.0004349492,0.0009019868],"domain_scores_gemma":[0.9942453,0.002711521,0.0007283153,0.001911007,0.0001708853,0.0002329856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[2.776027e-7,0.00004081259,0.00001229817,0.003335632,0.00007688328,0.00003735503,0.00003953683,0.0001371868,3.660409e-9,0.002575463,0.004532075,0.9892125],"study_design_scores_gemma":[0.00003740965,0.0000550816,0.00001953023,0.001602519,0.0001716323,0.0002962303,0.00002065964,0.01861938,3.847602e-8,0.0001430302,0.9784024,0.0006320429],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.093e-7,0.9166324,0.07848931,0.0004114894,0.00233618,0.001275642,0.0000178253,0.0004075213,0.0004291912],"genre_scores_gemma":[0.000006198513,0.991998,0.00581019,0.000422107,0.001007449,0.0003407029,0.000131777,0.00005617881,0.0002273704],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9885804,"threshold_uncertainty_score":0.9999847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213880547","doi":"10.1016/j.jclinepi.2021.11.001","title":"Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based","year":2021,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Schwartz/Reisman Emergency Medicine Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Health care; Evidence-based practice; Evidence-based medicine; Real world evidence; Computer science; Medicine; Alternative medicine; Economics; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.6211548340976271,"gpt":0.5750288304756365,"spread":0.0461260036219906,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09056282,0.0006484656,0.01130788,0.0006776213,0.0001817555,0.00008959671,0.002927485,0.001175545,0.00003577991],"category_scores_gemma":[0.4412723,0.0004429453,0.003307767,0.001123876,0.0002993174,0.0005932054,0.0006586881,0.004023385,0.00001965418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005421545,"about_ca_system_score_gemma":0.003359228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003300598,"about_ca_topic_score_gemma":0.0004399377,"domain_scores_codex":[0.9584046,0.02444491,0.01398937,0.001425411,0.0004985276,0.001237163],"domain_scores_gemma":[0.7735104,0.214801,0.008022286,0.001323839,0.001413443,0.0009290304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001502857,0.000230817,0.005341535,0.007190407,0.000107223,0.0001628347,0.0002312728,0.003348892,4.560598e-7,0.007823633,0.0004554889,0.9749572],"study_design_scores_gemma":[0.000397895,0.002831351,0.0002734164,0.03770582,0.0002039442,0.00007306077,0.0002127911,0.02319166,0.000009648922,0.005940775,0.9283947,0.0007649549],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001731705,0.7024844,0.2370581,0.05729645,0.001980911,0.0009605226,0.000008699441,0.00003206143,0.000005614806],"genre_scores_gemma":[0.0007400512,0.924507,0.06275554,0.01068739,0.001096078,0.00008373316,0.000008607641,0.00004598907,0.00007558095],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9741922,"threshold_uncertainty_score":0.9998022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3095556657","doi":"10.3758/s13423-020-01825-5","title":"Artificial cognition: How experimental psychology can help generate explainable artificial intelligence","year":2020,"lang":"en","type":"review","venue":"Psychonomic Bulletin & Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; Vector Institute","funders":"Vector Institute; Defense Advanced Research Projects Agency; Government of Canada; Canadian Institute for Advanced Research; U.S. Department of Defense","keywords":"Interpretability; Cognition; Psychology; Field (mathematics); Transparency (behavior); Cognitive science; Black box; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1468694019541067,"gpt":0.3790297076235946,"spread":0.2321603056694878,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.001620301,0.001770331,0.004476831,0.0004351908,0.0005956137,0.0009656321,0.004859798,0.0006662928,0.002133246],"category_scores_gemma":[0.0003229716,0.001737555,0.001595954,0.001869875,0.0004011699,0.0003423974,0.0008769582,0.001515654,0.01578587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005039583,"about_ca_system_score_gemma":0.0006173485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000360947,"about_ca_topic_score_gemma":0.00001630744,"domain_scores_codex":[0.9894698,0.001467099,0.003199276,0.003500574,0.0006721978,0.001691103],"domain_scores_gemma":[0.9939727,0.0003970114,0.001751882,0.002825217,0.0002764417,0.0007767832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001205858,0.000277183,2.558168e-8,0.009701151,0.0001471901,0.0002040437,0.0001086887,0.000001764442,0.00001744814,0.01978056,0.04698987,0.92276],"study_design_scores_gemma":[0.00003568893,0.0002829224,1.676002e-8,0.02053326,0.0003923595,0.0003630606,0.00007638997,0.00009912012,0.0005335456,0.003046277,0.9730386,0.001598796],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.149673e-7,0.9336433,0.03325729,0.02318684,0.003592765,0.003513945,0.00006088417,0.0004673574,0.002277298],"genre_scores_gemma":[0.0000222035,0.9793341,0.00888743,0.006848059,0.002006759,0.002146295,0.000187573,0.0002027711,0.0003648719],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9260487,"threshold_uncertainty_score":0.9995042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3125340956","doi":"10.1007/s11192-021-03868-4","title":"Tracking developments in artificial intelligence research: constructing and applying a new search strategy","year":2021,"lang":"en","type":"article","venue":"Scientometrics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Social Sciences and Humanities Research Council of Canada; National Research Foundation; National Natural Science Foundation of China; Engineering and Physical Sciences Research Council; Taishan Scholar Foundation of Shandong Province; National Institutes of Health; National Science Foundation","keywords":"Profiling (computer programming); Computer science; Artificial intelligence; Multidisciplinary approach; Benchmark (surveying); Domain (mathematical analysis); Applications of artificial intelligence; Data science; Social science; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.4453336730238928,"gpt":0.4467547731298974,"spread":0.001421100106004602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006335281,0.0001665677,0.0002230245,0.004123858,0.0004548451,0.001865591,0.001104457,0.0001061077,0.00002667592],"category_scores_gemma":[0.003692796,0.0001855835,0.00003399493,0.03644906,0.0002789177,0.001199151,0.001108782,0.0006624271,0.00009653334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002922515,"about_ca_system_score_gemma":0.001405264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002302765,"about_ca_topic_score_gemma":0.0002715779,"domain_scores_codex":[0.9952483,0.0002984579,0.0005888697,0.0009880553,0.001739848,0.001136536],"domain_scores_gemma":[0.9971406,0.001022142,0.00007365074,0.0005012864,0.0008709335,0.0003914236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002841876,0.00005312263,0.003937588,0.00001918728,0.00000507505,0.0001746604,0.00376975,0.0006089016,0.003750834,0.1571231,0.00001339691,0.8305415],"study_design_scores_gemma":[0.0002008951,0.0001812462,0.006279571,0.0003086363,0.000005074075,0.0002667342,0.04992527,0.1107273,0.6967097,0.1324782,0.001856644,0.001060734],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4258285,0.001148443,0.563968,0.0005838753,0.0007030542,0.0004989257,0.000001560963,0.000122796,0.007144833],"genre_scores_gemma":[0.9118063,0.00009697664,0.08779979,0.00005712172,0.00005854751,0.00001224214,0.000001210846,0.00001105023,0.0001567202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8294808,"threshold_uncertainty_score":0.9991705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3103420222","doi":"10.1007/s11423-020-09858-2","title":"Machine learning for human learners: opportunities, issues, tensions and threats","year":2020,"lang":"en","type":"article","venue":"Educational Technology Research and Development","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"King's College London","keywords":"Accountability; Artificial intelligence; Computer science; Educational technology; Curriculum; Legislature; Machine learning; Knowledge management; Engineering ethics; Psychology; Mathematics education; Pedagogy; Political science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3509394530848094,"gpt":0.4315278848171519,"spread":0.08058843173234254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005301969,0.00009857199,0.000120398,0.0003189932,0.0009578986,0.000119635,0.0003803283,0.00008509934,0.00003416793],"category_scores_gemma":[0.0004993132,0.00009426176,0.000008049541,0.0004467122,0.0003101319,0.0001789363,0.0004800525,0.0003396172,0.00003111604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004732027,"about_ca_system_score_gemma":0.0005928637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002939185,"about_ca_topic_score_gemma":0.00002312815,"domain_scores_codex":[0.9987392,0.00004122869,0.0001861393,0.0004180533,0.000241518,0.0003738888],"domain_scores_gemma":[0.9990303,0.0002155974,0.00003359385,0.0001548228,0.0003717381,0.0001939788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009978734,0.00008764899,0.005572848,0.00003422893,0.00002437152,0.00000845718,0.002653105,0.000004536254,0.001203719,0.9002712,0.003826984,0.08630287],"study_design_scores_gemma":[0.0002884952,0.0007722107,0.001572295,0.00005471895,0.000002416654,0.00005019445,0.008369099,0.003438673,0.01351578,0.4753445,0.4962099,0.0003817085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1182204,0.01208135,0.04268049,0.8228038,0.0001572189,0.001233794,0.00000509302,0.0005323507,0.002285453],"genre_scores_gemma":[0.8951895,0.0009203814,0.09583779,0.000552265,0.0001047421,0.0003308315,0.00005189404,0.00001701539,0.006995598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8222516,"threshold_uncertainty_score":0.7367479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4225137238","doi":"10.1145/3491101.3503727","title":"Human-Centered Explainable AI (HCXAI): Beyond Opening the Black-Box of AI","year":2022,"lang":"en","type":"article","venue":"CHI Conference on Human Factors in Computing Systems Extended Abstracts","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Science Foundation","keywords":"Black box; Computer science; Artificial intelligence; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.09086952091528383,"gpt":0.3404376688759422,"spread":0.2495681479606583,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002445061,0.000614465,0.0008679872,0.000600693,0.001924637,0.0009211173,0.004171956,0.0001493616,0.0001237062],"category_scores_gemma":[0.000146884,0.0005379387,0.0002145137,0.0009113761,0.0003209469,0.0007413659,0.001507038,0.001749027,0.00003451347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005120659,"about_ca_system_score_gemma":0.000324955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001859846,"about_ca_topic_score_gemma":0.000115979,"domain_scores_codex":[0.9936311,0.0008182636,0.001846941,0.001246003,0.001286308,0.001171394],"domain_scores_gemma":[0.9960983,0.0004331271,0.001134574,0.001777626,0.000351065,0.0002053331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002763916,0.0009086261,0.002803073,0.0002297794,0.00009154221,0.0002503844,0.0207937,0.1794077,0.01058926,0.7816602,0.001521079,0.001717012],"study_design_scores_gemma":[0.004745449,0.005134439,0.1318286,0.0040657,0.0001081333,0.0003576139,0.07132116,0.5468822,0.1123994,0.1104928,0.005963286,0.006701182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9763351,0.00008406321,0.006395445,0.0005118119,0.001628311,0.001262339,0.0000189674,0.0002675431,0.01349643],"genre_scores_gemma":[0.9986488,0.00000187354,0.0001752352,0.0003075729,0.0001288302,0.00005489334,0.00002389091,0.0000511113,0.0006078162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6711674,"threshold_uncertainty_score":0.9997072,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213371886","doi":"10.1016/j.ijhcs.2022.102792","title":"The effects of domain knowledge on trust in explainable AI and task performance: A case of peer-to-peer lending","year":2022,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Domain (mathematical analysis); Computer science; Domain knowledge; Subject-matter expert; Artificial intelligence; Knowledge management; Expert system; Field (mathematics); Applications of artificial intelligence; Management","retraction":null,"screen_n_in":null,"score":{"opus":0.02558452781357945,"gpt":0.3466166789103166,"spread":0.3210321510967371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001842855,0.0001594834,0.0003485242,0.0006154909,0.0004083074,0.00009676309,0.001154909,0.00002158539,0.000003657459],"category_scores_gemma":[0.0002265031,0.0001231537,0.00009965553,0.0003370408,0.0001287802,0.0004233714,0.001105179,0.000335056,0.000001985261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002597685,"about_ca_system_score_gemma":0.00006759975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003680231,"about_ca_topic_score_gemma":0.0000509843,"domain_scores_codex":[0.9977549,0.0001900446,0.0007391501,0.0002203682,0.0008538372,0.000241703],"domain_scores_gemma":[0.9972757,0.0008051819,0.0004343423,0.0002141329,0.00121677,0.00005387369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007652406,0.002167346,0.01013433,0.0006079265,0.002112489,0.01037649,0.3158463,0.02736224,0.007257692,0.2973078,0.02666131,0.2994008],"study_design_scores_gemma":[0.01699885,0.05357187,0.03405903,0.007796011,0.0003033405,0.02424083,0.1129058,0.2310802,0.2655341,0.1396518,0.1097148,0.004143261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829216,0.00115209,0.01043392,0.002759132,0.002318368,0.0001868314,0.000002713844,0.000009189257,0.0002161319],"genre_scores_gemma":[0.9973705,0.00009200982,0.001894881,0.0001584097,0.0002006952,0.00002168811,2.976622e-7,0.000008890971,0.0002525732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2952576,"threshold_uncertainty_score":0.502206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964306570","doi":"10.1109/icdmw.2018.00132","title":"Improving the Interpretability of Deep Neural Networks with Knowledge Distillation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Artificial neural network; Deep learning; Decision tree; Scalability; Deep neural networks; Software deployment; Software engineering; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02019924449996864,"gpt":0.2675017723762776,"spread":0.247302527876309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007978382,0.0002531568,0.0002847177,0.00006381463,0.0001412448,0.0002516777,0.001939926,0.0001596926,0.00004000107],"category_scores_gemma":[0.0001590347,0.000151513,0.0001136805,0.0003190521,0.0003553745,0.000291068,0.002556369,0.0004613604,0.00001349118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009325355,"about_ca_system_score_gemma":0.00008900699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005314626,"about_ca_topic_score_gemma":0.001306779,"domain_scores_codex":[0.9980808,0.0002094382,0.0004808929,0.0006807458,0.0002282419,0.0003198162],"domain_scores_gemma":[0.9969651,0.0003486748,0.0003621404,0.001740247,0.0005177375,0.00006617857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001130463,0.0002477987,0.01113124,0.00036582,0.0001186602,0.000005563007,0.0109888,0.2670725,0.0001565867,0.0415468,0.0001648416,0.6680883],"study_design_scores_gemma":[0.00002274486,0.0001039698,0.001235179,0.00003632452,0.0000139604,0.000003070055,0.0001050202,0.9930344,0.001999475,0.003235818,0.00002489563,0.0001851386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0401568,0.0001964186,0.9540012,0.0001850981,0.0009046023,0.00048373,9.638262e-7,0.0001438558,0.003927271],"genre_scores_gemma":[0.9867202,0.000002829519,0.0129384,0.00004198505,0.000191811,0.00003304837,0.000002955499,0.00001356822,0.00005519932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9465634,"threshold_uncertainty_score":0.617852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3160343688","doi":"10.1145/3411764.3445736","title":"Data-Centric Explanations: Explaining Training Data of Machine Learning Systems to Promote Transparency","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Transparency (behavior); Trustworthiness; Formative assessment; Training (meteorology); Perception; Training set; Knowledge management; Machine learning; Artificial intelligence; Psychology; Computer security; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.2186693162107233,"gpt":0.3444446572881982,"spread":0.1257753410774749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001593139,0.0002090682,0.0003735003,0.0002648892,0.0002541842,0.0003207295,0.004194744,0.00006607905,0.0001198982],"category_scores_gemma":[0.00112852,0.0002093181,0.00003433166,0.001780242,0.00002791096,0.002221443,0.001517082,0.0002538598,0.00007031443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004319449,"about_ca_system_score_gemma":0.0003171434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004321489,"about_ca_topic_score_gemma":0.0004895566,"domain_scores_codex":[0.9966748,0.0002378983,0.0008042156,0.001148176,0.0006103533,0.0005244937],"domain_scores_gemma":[0.9959716,0.0003190232,0.000188992,0.003045862,0.0002721126,0.000202412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003948652,0.0008231025,0.002385344,0.0005589144,0.0003591168,0.000960755,0.05232159,0.1175567,0.02078483,0.3086065,0.004410305,0.4911934],"study_design_scores_gemma":[0.0001353318,0.00007901456,0.00003214941,0.0001625496,0.00001813252,0.00004740877,0.004416615,0.949369,0.006322045,0.0001891833,0.03893181,0.0002967326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004781561,0.001168331,0.9880927,0.0009523886,0.0005075938,0.0003317778,0.0001643575,0.000266427,0.003734847],"genre_scores_gemma":[0.8802801,0.0001216862,0.117889,0.0001361361,0.00009968916,0.00002361944,0.0007038504,0.00002540058,0.0007205649],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8754985,"threshold_uncertainty_score":0.8535743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1533957530","doi":"","title":"Visual explanation of evidence in additive classifiers","year":2006,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Machine learning; Naive Bayes classifier; Classifier (UML); Artificial intelligence; Visualization; Python (programming language); Support vector machine; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1151995282124959,"gpt":0.3389553697087794,"spread":0.2237558414962835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003287089,0.00007421526,0.0001049708,0.0001961362,0.00003035809,0.00004103653,0.0003962917,0.00004338547,0.00006117923],"category_scores_gemma":[0.0001424791,0.00006218482,0.00002966568,0.0006565307,0.00005306724,0.001057397,0.00007867804,0.00006660661,0.0000708286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007432984,"about_ca_system_score_gemma":0.00006540105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001474376,"about_ca_topic_score_gemma":0.001032333,"domain_scores_codex":[0.9989485,0.00006413133,0.0002931619,0.0002422492,0.0002556907,0.0001963209],"domain_scores_gemma":[0.99927,0.0003040688,0.00008429751,0.0001979856,0.000116196,0.00002747369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002244142,0.0002409423,0.005628635,0.0000166811,0.000005256952,0.00004210267,0.001124931,0.00176607,0.02249001,0.8781509,0.004336018,0.08617605],"study_design_scores_gemma":[0.0001041079,0.0001745126,0.01792399,0.0001059416,0.000002019581,0.000003693413,0.0008376826,0.2040671,0.7481402,0.02749089,0.0009170722,0.0002328051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1602284,0.00007400236,0.8150923,0.00117597,0.0002152792,0.0002252078,0.000001304492,0.0001096515,0.02287781],"genre_scores_gemma":[0.9921155,0.00001222916,0.007176408,0.00008563991,0.00002730613,0.00001287644,0.000001471409,0.000003169469,0.0005654213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.85066,"threshold_uncertainty_score":0.2535823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997520586","doi":"10.1609/aaai.v34i03.5632","title":"Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Deep neural networks; Relevance (law); Attribution; Computer science; Artificial neural network; Segmentation; Artificial intelligence; Perspective (graphical); Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.128441936677837,"gpt":0.3185824456767782,"spread":0.1901405089989412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001371102,0.0003102397,0.0004873928,0.0001307137,0.0003956437,0.0002830683,0.003249119,0.0001319897,0.00002691109],"category_scores_gemma":[0.002963867,0.0002183255,0.000127947,0.003211395,0.000712688,0.0009254225,0.000971822,0.0009342824,0.00002026337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008769002,"about_ca_system_score_gemma":0.0001469456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006045923,"about_ca_topic_score_gemma":0.0000438242,"domain_scores_codex":[0.9967756,0.0001651878,0.001230541,0.0005866328,0.0006880831,0.000554015],"domain_scores_gemma":[0.9957877,0.0008014201,0.001007069,0.0003148425,0.001963934,0.0001250256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001083424,0.00009781501,0.0006959517,0.00002503089,0.00003470471,0.000001232229,0.02603266,0.01335375,0.006190253,0.9390389,0.00004388867,0.01437752],"study_design_scores_gemma":[0.00003013324,0.0002450914,0.0001906278,0.0001838468,0.00001504122,0.000002613977,0.006302308,0.6871855,0.2809607,0.02469595,0.00001272326,0.000175402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3202744,0.0001785403,0.6429031,0.02862303,0.0005717995,0.002220978,0.00003290692,0.0001712491,0.005023919],"genre_scores_gemma":[0.9985968,0.000009927445,0.000757017,0.000489024,0.00007570843,0.00004855534,0.000002217169,0.00001134797,0.0000094121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9143429,"threshold_uncertainty_score":0.8903056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390604658","doi":"10.1073/pnas.2304406120","title":"Impossibility theorems for feature attribution","year":2024,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Spurious relationship; Computer science; Feature (linguistics); Attribution; Impossibility; Task (project management); Simple (philosophy); Field (mathematics); Artificial intelligence; Machine learning; Theoretical computer science; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06421974591361419,"gpt":0.3520020040083907,"spread":0.2877822580947765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002981346,0.00008392279,0.0001125864,0.0001394566,0.0002485917,0.0001483699,0.001645425,0.0000825094,0.000003149929],"category_scores_gemma":[0.0006138331,0.00005266197,0.0001167013,0.001405305,0.0005852085,0.001297128,0.0002098389,0.0001462202,0.000002657708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006171349,"about_ca_system_score_gemma":0.00007061275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003902174,"about_ca_topic_score_gemma":6.597666e-8,"domain_scores_codex":[0.9983429,0.00000629707,0.0002627704,0.0003631653,0.0008364623,0.0001883809],"domain_scores_gemma":[0.9990922,0.0002798424,0.0001678962,0.00001437759,0.0004157545,0.00002991913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003435911,0.00001554903,0.0003168116,0.00006020458,0.000005565241,2.981229e-9,0.0002231434,0.00004906675,0.1079799,0.8871679,0.001320189,0.002858224],"study_design_scores_gemma":[0.00001727095,0.00003474104,0.003173593,0.0000505995,0.000003019217,0.000003292845,0.00004477432,0.03490362,0.4487636,0.5121389,0.0008189203,0.00004769606],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8700366,0.002104929,0.02515411,0.08651837,0.0006255317,0.001960835,0.0001460079,0.0003529433,0.01310065],"genre_scores_gemma":[0.9889511,0.000009255269,0.01056861,0.0001670399,0.00009277371,0.00001745943,1.1554e-7,0.000002502059,0.0001911166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3750291,"threshold_uncertainty_score":0.3057637,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3205978700","doi":"10.1016/j.envsoft.2021.105226","title":"Sensitivity analysis: A discipline coming of age","year":2021,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Sensitivity (control systems); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02348216521195989,"gpt":0.2383706673188567,"spread":0.2148885021068968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003271019,0.0001814732,0.0003425043,0.0001136821,0.0001723897,0.00006961168,0.0003280187,0.00006832389,0.00004804289],"category_scores_gemma":[0.00003015664,0.0001960172,0.000238012,0.0005998277,0.0001127224,0.0003951153,0.0005116768,0.0001655843,0.00004955706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009762402,"about_ca_system_score_gemma":0.00002726503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008039243,"about_ca_topic_score_gemma":0.00006267693,"domain_scores_codex":[0.9981947,0.0001310723,0.0003758728,0.0005777724,0.0003949,0.000325675],"domain_scores_gemma":[0.9987286,0.0002114649,0.0001345294,0.0007984691,0.00001829144,0.000108617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005916917,0.0002510148,0.007615569,0.00001584079,0.0001630474,0.0003995995,0.001918773,0.9716314,0.01175976,0.001456869,0.000007522594,0.004774674],"study_design_scores_gemma":[0.0000806046,0.00002755354,0.001479654,0.0000267153,0.0001096339,0.00001330389,0.0003501315,0.9178823,0.0756975,0.003948563,0.000117365,0.0002666363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2787966,0.0001941564,0.720682,0.00007203391,0.00006250997,0.00005878572,0.00001773549,0.00006998891,0.0000461767],"genre_scores_gemma":[0.8411489,0.00004017305,0.1584505,0.00007194412,0.00002414878,0.000004853769,0.00003960599,0.00001238239,0.0002075222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5623523,"threshold_uncertainty_score":0.7993348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407192178","doi":"10.3390/make7010012","title":"Advancing AI Interpretability in Medical Imaging: A Comparative Analysis of Pixel-Level Interpretability and Grad-CAM Models","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Interpretability; Artificial intelligence; Pixel; Computer science; Medicine; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0202131925955474,"gpt":0.3656390315843576,"spread":0.3454258389888102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001922605,0.0001906993,0.0005150593,0.0006898745,0.0001522958,0.00009338184,0.0002691548,0.00008734594,0.00002343398],"category_scores_gemma":[0.0007759744,0.000183026,0.00009582112,0.001448565,0.0001979763,0.0008186737,0.0003403228,0.0007230746,0.000002034746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270044,"about_ca_system_score_gemma":0.0001188376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022915,"about_ca_topic_score_gemma":0.004542548,"domain_scores_codex":[0.9977432,0.0005973587,0.0005851795,0.0006188657,0.0001958791,0.0002595417],"domain_scores_gemma":[0.998403,0.0008618791,0.0001485459,0.0002828472,0.0001956978,0.0001080212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001581862,0.0006663212,0.5246098,0.0001957106,0.0002482979,0.000005814775,0.02293624,0.009740095,0.002299818,0.01778678,0.00002468956,0.4213282],"study_design_scores_gemma":[0.0001397612,0.00004183576,0.03180299,0.0001119779,0.00006775525,0.00000486463,0.0007735338,0.9603956,0.0007410088,0.005389987,0.0003933236,0.0001373154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3046402,0.001501066,0.6905249,0.0007190302,0.0001508103,0.0001258746,0.000001704806,0.000065512,0.002270844],"genre_scores_gemma":[0.9979629,0.00007457437,0.001756301,0.00005271082,0.00001053745,0.00001579989,0.000004573178,0.000004248964,0.0001183667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9506556,"threshold_uncertainty_score":0.7463583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402202846","doi":"10.3390/electronics13173497","title":"Explainable AI in Manufacturing and Industrial Cyber–Physical Systems: A Survey","year":2024,"lang":"en","type":"article","venue":"Electronics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick; University of Windsor","funders":"","keywords":"Cyber-physical system; Manufacturing engineering; Engineering; Survey research; Systems engineering; Computer science; Business; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03465311982436982,"gpt":0.2814104456320202,"spread":0.2467573258076504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009753426,0.0001791575,0.0002251424,0.0002115222,0.00009866235,0.0007286887,0.0004866249,0.0001090818,0.000003441739],"category_scores_gemma":[0.00009110409,0.0001743823,0.00003715533,0.000614045,0.00003662108,0.0008478828,0.0002083438,0.0006195569,0.00007717958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00031906,"about_ca_system_score_gemma":0.0003133139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006923857,"about_ca_topic_score_gemma":0.0008871775,"domain_scores_codex":[0.9980467,0.0002036177,0.0002550484,0.000541923,0.0002537484,0.0006989815],"domain_scores_gemma":[0.9991218,0.0003632209,0.0000313131,0.0003567972,0.0000344009,0.00009242235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007445006,0.0002836064,0.001108904,0.0002177605,0.0001069807,0.0006850506,0.005894092,0.004934493,0.002653652,0.7598102,0.006203492,0.2180273],"study_design_scores_gemma":[0.0004264553,0.0006677668,0.001063875,0.0003124017,0.00001621001,0.0001238197,0.0003269005,0.7193784,0.09907631,0.04667806,0.1308971,0.001032715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9587333,0.008186368,0.02949402,0.001128047,0.0008947589,0.0004535125,0.000003748713,0.0003609339,0.000745334],"genre_scores_gemma":[0.9989797,0.0001633687,0.00009280502,0.00006309303,0.0001804665,0.00003712672,0.00000404972,0.00001849452,0.0004608324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7144439,"threshold_uncertainty_score":0.7111105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283268983","doi":"10.6017/ital.v41i2.14683","title":"Explainable Artificial Intelligence (XAI)","year":2022,"lang":"en","type":"article","venue":"Information Technology and Libraries","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Field (mathematics); Set (abstract data type); Library classification; Data science; Knowledge management; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01658781599263557,"gpt":0.2217739927494473,"spread":0.2051861767568117,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003137128,0.0001333782,0.0001409184,0.0008760889,0.001145498,0.0004102929,0.001045248,0.0001025584,0.0001941726],"category_scores_gemma":[0.0001418052,0.0001420718,0.00002843866,0.001732903,0.0002757219,0.006321644,0.001255428,0.0003572547,0.0001584216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003524889,"about_ca_system_score_gemma":0.0001083458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000155215,"about_ca_topic_score_gemma":0.000001962892,"domain_scores_codex":[0.9987713,0.00004265874,0.0004258875,0.0002009374,0.0002233756,0.0003358906],"domain_scores_gemma":[0.9992059,0.00008447868,0.0001539446,0.0004414716,0.00006243679,0.00005177901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009550878,0.00001767293,0.00008700488,0.000009187904,0.000005058045,0.000005251777,0.001939017,0.0003399411,0.00003209048,0.8503582,0.0004736319,0.1467233],"study_design_scores_gemma":[0.00002594895,0.0001753842,0.00002373679,0.00000467402,0.000002203161,0.00006489653,0.009567793,0.02393423,0.04341073,0.8071698,0.115422,0.000198617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01726946,0.0003681271,0.9581357,0.01415703,0.0005155742,0.0003027194,0.0000087315,0.001294997,0.007947723],"genre_scores_gemma":[0.9772211,0.00002676316,0.0211821,0.001133057,0.00002143574,0.0001855826,0.00001147952,0.000005724547,0.0002127012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9599517,"threshold_uncertainty_score":0.8810362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400400027","doi":"10.1016/j.eswa.2024.124710","title":"Survey on Explainable AI: Techniques, challenges and open issues","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Computer science; Data science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.07160439259705363,"gpt":0.3515282223116297,"spread":0.279923829714576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007862095,0.0002046102,0.0002426606,0.0001639612,0.0002879828,0.001173743,0.001279023,0.00008332034,0.000005760847],"category_scores_gemma":[0.00002123318,0.0001617725,0.00001993105,0.0005135197,0.00007189199,0.000878401,0.0003353934,0.0001500059,0.0002182674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008488349,"about_ca_system_score_gemma":0.000100836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003392591,"about_ca_topic_score_gemma":0.00038235,"domain_scores_codex":[0.9982362,0.0001428337,0.0002680571,0.00078778,0.0002551852,0.0003099816],"domain_scores_gemma":[0.9983416,0.0002629571,0.00005292138,0.001053143,0.000156744,0.0001326217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007522675,0.00008936416,0.00002233821,0.00007624341,0.00002866501,0.00001775802,0.002920003,0.0000232286,0.0003920665,0.9026737,0.01811576,0.07563339],"study_design_scores_gemma":[0.00004695473,0.0002402525,0.0001742088,0.0003235853,0.000003043517,0.00004004527,0.0009924666,0.008597127,0.0111669,0.003396826,0.974632,0.000386639],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000165064,0.08396289,0.8665949,0.01385526,0.000269487,0.004446736,0.00002213402,0.001706644,0.02897688],"genre_scores_gemma":[0.9351951,0.00714724,0.02598771,0.0008990611,0.0006011834,0.01817753,0.00003867266,0.0001176631,0.01183579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9565162,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411627694","doi":"10.1073/pnas.2422633122","title":"Generative AI without guardrails can harm learning: Evidence from high school mathematics","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Generative grammar; Harm; Computer science; Artificial intelligence; TUTOR; Productivity; Machine learning; Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06691070461142205,"gpt":0.3490396163586603,"spread":0.2821289117472382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001769555,0.0001504981,0.0002409024,0.0002575573,0.0004522497,0.0002228561,0.003068981,0.00009334527,0.0000207437],"category_scores_gemma":[0.003661889,0.0001072664,0.00008080063,0.00182676,0.0007576513,0.001575279,0.0005914354,0.0003620836,0.000009357683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001071044,"about_ca_system_score_gemma":0.0002304771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001214011,"about_ca_topic_score_gemma":0.000001098361,"domain_scores_codex":[0.997315,0.00002277172,0.0005160801,0.0004719576,0.001424482,0.0002497434],"domain_scores_gemma":[0.9980874,0.0004641439,0.0005323322,0.00003078025,0.0008249636,0.00006035433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008134942,0.00006825708,0.0129654,0.0000620997,0.00003867902,2.536378e-8,0.002206046,0.002095422,0.3386229,0.6413859,0.00167884,0.0008683595],"study_design_scores_gemma":[0.00004483434,0.00003354083,0.00723343,0.000318997,0.000009334774,0.000001133527,0.0004211312,0.03788547,0.6212502,0.3326238,0.00008407104,0.00009405284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9272909,0.0003849521,0.006497722,0.05911487,0.0001438095,0.0005565066,0.00001000171,0.0001002067,0.005901074],"genre_scores_gemma":[0.9530157,0.00003746061,0.04488293,0.001127096,0.00006492039,0.00002064545,6.259768e-8,0.000003507052,0.0008476046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.308762,"threshold_uncertainty_score":0.570298,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4243640523","doi":"10.31219/osf.io/m6gcn","title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Encoder; Computer science; Generative grammar; Artificial intelligence; Speech recognition; Electrical engineering; Engineering; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.05466022564196835,"gpt":0.2753320060763013,"spread":0.2206717804343329,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008038589,0.0002788612,0.0003351863,0.00009800485,0.0001430482,0.0005967719,0.0005762758,0.0002582624,0.00002740947],"category_scores_gemma":[0.00008915138,0.0002703807,0.00006880955,0.000191651,0.00006528574,0.0004074898,0.000947942,0.0003937712,0.00003493501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004213333,"about_ca_system_score_gemma":0.0001168103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002711233,"about_ca_topic_score_gemma":0.001135995,"domain_scores_codex":[0.9978786,0.000180518,0.0003625824,0.0009452221,0.0003226049,0.0003104443],"domain_scores_gemma":[0.9990524,0.0001509102,0.00009798581,0.0003738096,0.0001188005,0.0002060902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001016842,0.0001139851,0.001562127,0.0004157489,0.0001731515,0.00007308945,0.004264704,0.00004590703,0.008239611,0.9013829,0.002138573,0.08148853],"study_design_scores_gemma":[0.0007185218,0.0006748633,0.01463365,0.0002154804,0.00009966759,0.00004981662,0.0004957974,0.2900787,0.0458368,0.6400071,0.00482519,0.002364428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03923064,0.0001329131,0.9534251,0.002453596,0.00231272,0.0005168082,0.00002104734,0.0002409161,0.001666253],"genre_scores_gemma":[0.982805,0.0003909961,0.01567179,0.000311685,0.0002969945,0.0000311716,0.00003745784,0.00002259491,0.0004323625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9435743,"threshold_uncertainty_score":0.9999748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396833700","doi":"10.1145/3613904.3642474","title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Heuristics; Appropriation; Perception; Field (mathematics); Value (mathematics); Psychology; Computer science; Cognition; Social psychology; Artificial intelligence; Cognitive psychology; Epistemology; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03432535491012714,"gpt":0.3172028789804958,"spread":0.2828775240703687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004006885,0.0001048463,0.0001099321,0.0001999702,0.0002114337,0.0007686863,0.0008232863,0.00004984811,0.0001644505],"category_scores_gemma":[0.00005649411,0.00007481837,0.00007117625,0.0009834724,0.0001130592,0.001219111,0.0001710376,0.0002176775,0.0002658516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007004142,"about_ca_system_score_gemma":0.0001313224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003054224,"about_ca_topic_score_gemma":0.003179517,"domain_scores_codex":[0.99885,0.0000731172,0.0002416083,0.0003003079,0.0002588585,0.0002760517],"domain_scores_gemma":[0.9990113,0.0004081351,0.00002370599,0.0003795639,0.0001253004,0.00005201601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.922182e-7,0.00002853616,0.000252688,0.000009014296,0.000008636779,0.000008402179,0.00198062,0.0003787149,0.0008612852,0.9743001,0.01161205,0.01055904],"study_design_scores_gemma":[0.00006355705,0.0001078257,0.005165272,0.0001174661,0.000009148172,0.0000195886,0.009505549,0.8033332,0.005815288,0.1106246,0.06491067,0.0003278708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02735885,0.0004083235,0.8793388,0.07957968,0.0004429597,0.0002528224,0.000005202633,0.0002305324,0.01238282],"genre_scores_gemma":[0.9902675,0.00009849432,0.002282129,0.0006255548,0.00005632147,0.00003930584,0.000001363251,0.000008374675,0.006620924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629087,"threshold_uncertainty_score":0.741246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319165740","doi":"10.1145/3579467","title":"Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Science Foundation","keywords":"Sociotechnical system; Operationalization; Affordance; Context (archaeology); Computer science; Knowledge management; Domain (mathematical analysis); Conceptual framework; Management science; Data science; Sociology; Epistemology; Engineering; Social science; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.1290705136467061,"gpt":0.3893030887555342,"spread":0.2602325751088281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002148143,0.0002765103,0.0003040393,0.0004363673,0.0005173797,0.0005481352,0.005765006,0.0001654027,0.00001649124],"category_scores_gemma":[0.001463917,0.0001728538,0.0001697831,0.002257318,0.0001128369,0.001062873,0.003033863,0.001329515,0.0001654056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003067317,"about_ca_system_score_gemma":0.00003115616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002543983,"about_ca_topic_score_gemma":0.0000830385,"domain_scores_codex":[0.9971786,0.00008782947,0.0007467211,0.0006793138,0.0006299629,0.0006776261],"domain_scores_gemma":[0.9973108,0.0009016776,0.000374946,0.001100572,0.0002469787,0.0000650414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003396735,0.0009704392,0.006598623,0.0003421954,0.0001041575,0.00003680274,0.1148527,0.02548163,0.05172588,0.6631283,0.06094433,0.07547531],"study_design_scores_gemma":[0.0004710631,0.0007834266,0.01683164,0.00297073,0.00002159995,0.00004925402,0.009020353,0.2757226,0.1983806,0.4878279,0.006957756,0.0009631545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9179386,0.0000179624,0.008105711,0.06964734,0.00140242,0.001295999,0.000001030068,0.000324843,0.001266038],"genre_scores_gemma":[0.9937917,0.000007850965,0.002372418,0.003007332,0.0003799955,0.0002509744,5.349748e-7,0.00002822067,0.0001609601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2502409,"threshold_uncertainty_score":0.9996143,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4360991197","doi":"10.1145/3581641.3584033","title":"Understanding Uncertainty: How Lay Decision-makers Perceive and Interpret Uncertainty in Human-AI Decision Making","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Transparency (behavior); Computer science; Uncertainty reduction theory; Probabilistic logic; Decision support system; Decision engineering; R-CAST; Business decision mapping; Decision analysis; Visualization; Process (computing); Management science; Knowledge management; Data science; Artificial intelligence; Psychology; Engineering; Social psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08080955537100197,"gpt":0.3440335552965247,"spread":0.2632239999255227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001366526,0.0003187729,0.0003666519,0.0009034419,0.0004584831,0.0009538336,0.001092793,0.000168002,0.00008702184],"category_scores_gemma":[0.0008073782,0.000286064,0.0001019537,0.002104438,0.0001752367,0.00124345,0.0009720835,0.0003782218,0.0001053555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007297346,"about_ca_system_score_gemma":0.00009984837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003811663,"about_ca_topic_score_gemma":0.004557799,"domain_scores_codex":[0.9969249,0.0001390151,0.0004907213,0.001001523,0.0006381994,0.0008056625],"domain_scores_gemma":[0.9966094,0.002259011,0.00008243786,0.0007558106,0.0001204461,0.0001729311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001891857,0.0001093472,0.006817153,0.00004875041,0.00005538069,0.0008344171,0.0193915,0.1078541,0.002710094,0.696952,0.01770115,0.1473369],"study_design_scores_gemma":[0.0002634694,0.0001378394,0.001009512,0.0005149475,0.000004905074,0.00002013666,0.01178285,0.6195501,0.000245967,0.3655656,0.0004732272,0.0004313984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2130678,0.00003576879,0.7802752,0.002629143,0.000438608,0.0003338934,0.000002813735,0.0004013398,0.002815505],"genre_scores_gemma":[0.991713,0.00004959046,0.007083387,0.0008099368,0.00004128918,0.00002234138,0.000003157314,0.00002576919,0.0002515537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7786452,"threshold_uncertainty_score":0.9999592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3029534136","doi":"10.1007/978-3-030-46150-8_12","title":"Black box explanation by learning image exemplars in the latent feature space","year":2020,"lang":"en","type":"book-chapter","venue":"ISTI Open Portal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Contextual image classification; Feature vector; Black box; Machine learning; Autoencoder; Decision tree; Image (mathematics); Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03182236454546179,"gpt":0.2748861118183661,"spread":0.2430637472729044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005004283,0.0003614643,0.0003614053,0.00009951311,0.0002097758,0.001106754,0.002854615,0.0002498873,0.0002339317],"category_scores_gemma":[0.00008446374,0.0003081524,0.0001053041,0.0001360062,0.0001048022,0.0008503351,0.000726248,0.001072825,0.001105787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000100584,"about_ca_system_score_gemma":0.000133699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002786735,"about_ca_topic_score_gemma":0.0003953025,"domain_scores_codex":[0.997797,0.0000781558,0.0003883991,0.0007862544,0.0006014897,0.0003486591],"domain_scores_gemma":[0.9987041,0.000111164,0.0003466762,0.0006334306,0.00009734283,0.0001072434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002874542,0.00004497775,0.00004948404,0.00003397032,0.00004346536,0.002589711,0.004450928,0.0003526831,0.0005297341,0.635837,0.3527277,0.003311652],"study_design_scores_gemma":[0.0002872107,0.0003314396,0.0001219484,0.0002720075,0.00004320471,0.0001244098,0.0009716694,0.007597859,0.00196395,0.03655129,0.95046,0.001275069],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002776182,0.0003730256,0.03024898,0.02231656,0.0004937121,0.001595718,0.00005645409,0.0001605544,0.9444774],"genre_scores_gemma":[0.1425737,0.0003199853,0.008673001,0.003605314,0.0004494482,0.00009386156,0.0007869535,0.0001677353,0.84333],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5992857,"threshold_uncertainty_score":0.9999371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3103654318","doi":"10.1007/s13347-020-00435-2","title":"What is Interpretability?","year":2020,"lang":"en","type":"article","venue":"Philosophy & Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Cambridge Commonwealth Trust; Ernest Oppenheimer Memorial Trust; Wellcome; Cambridge Trust; Wellcome Trust","keywords":"Interpretability; Interpretation (philosophy); Artificial intelligence; Artificial neural network; Computer science; Context (archaeology); Connectionism; Typology; Epistemology; Machine learning; Cognitive science; Psychology; Sociology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03858859774311926,"gpt":0.2735726670442438,"spread":0.2349840693011246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001260367,0.0002012835,0.0002643989,0.0002148892,0.0001111298,0.0001950613,0.002354444,0.0002049546,0.00009495865],"category_scores_gemma":[0.0001671854,0.0002046432,0.0001039164,0.00140765,0.0002723244,0.001511453,0.00100529,0.000380516,0.001666988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005297064,"about_ca_system_score_gemma":0.00004523287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009126576,"about_ca_topic_score_gemma":0.000002486594,"domain_scores_codex":[0.9981984,0.00003825569,0.0003416703,0.000788486,0.000211226,0.0004219618],"domain_scores_gemma":[0.9984968,0.00005961103,0.00009240818,0.001083793,0.0001300337,0.0001373852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001077149,0.00007200827,0.0004894302,0.0000255698,0.0000260255,0.00005207617,0.002648944,0.00001449723,0.003699548,0.9151726,0.0006869787,0.0771016],"study_design_scores_gemma":[0.00006876555,0.0002856305,0.000008839144,0.00002769003,0.000005250471,0.00001569698,0.0002238677,0.01457541,0.1179888,0.8490345,0.01751092,0.0002546534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01283354,0.001725275,0.3022842,0.6731539,0.0008941618,0.0003806759,0.000002453192,0.002305985,0.006419851],"genre_scores_gemma":[0.9806342,0.0001132699,0.006776264,0.0122738,0.0001262088,0.00003808274,6.024185e-7,0.00001537675,0.00002216596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9678007,"threshold_uncertainty_score":0.9991103,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283521686","doi":"10.3390/diagnostics12071557","title":"Designing an Interpretability-Based Model to Explain the Artificial Intelligence Algorithms in Healthcare","year":2022,"lang":"en","type":"article","venue":"Diagnostics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Fidelity; Transparency (behavior); Process (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.08447499056083677,"gpt":0.3329501289657329,"spread":0.2484751384048961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002249361,0.0002468122,0.0002496551,0.0002939192,0.0006739813,0.0002666684,0.00252969,0.00005988223,0.00002728313],"category_scores_gemma":[0.001387644,0.0002355611,0.00007621269,0.001572691,0.00009525816,0.0004142632,0.000834641,0.0006464463,0.00005708255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004103183,"about_ca_system_score_gemma":0.0004080959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007015512,"about_ca_topic_score_gemma":0.001376073,"domain_scores_codex":[0.9964392,0.0007077266,0.000671014,0.0007928642,0.0006591443,0.0007300195],"domain_scores_gemma":[0.9963968,0.001819093,0.0001128659,0.001253802,0.0001674459,0.0002500406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002621533,0.00030732,0.0007389706,0.0000100052,0.00000277976,0.00006551509,0.008919026,0.8150294,0.0001988686,0.1087233,0.0001246097,0.06585392],"study_design_scores_gemma":[0.00002229593,0.0003768037,0.00005649785,0.00001973451,0.00000299709,0.000004073382,0.002405784,0.9070958,0.01413,0.07542839,0.0001876989,0.0002698873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02519104,0.0001057402,0.9605568,0.01261304,0.0005363477,0.000762856,0.00002468398,0.0001616933,0.000047789],"genre_scores_gemma":[0.9058504,0.000009060652,0.08767409,0.005798056,0.00005846411,0.0005676825,0.000009651923,0.0000250847,0.000007474947],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8806594,"threshold_uncertainty_score":0.9605905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}