{"meta":{"query_hash":"155b98093770","filters":{"topic":"Explainable Artificial Intelligence (XAI)"},"cohort_total":675,"direct_labels_cover":1,"predictions_cover":675,"exported":675,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/155b98093770","api":"https://metacan.xera.ac/api/v1/cohort?topic=Explainable+Artificial+Intelligence+%28XAI%29"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11519952821249592,"score_gpt":0.33895536970877943,"score_spread":0.22375584149628353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533957530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16022843,0.00007400236,0.8150923,0.0011759698,0.00021527923,0.00022520784,0.0000013044923,0.000109651475,0.022877807],"genre_scores_gemma":[0.9921155,0.0000122291585,0.0071764076,0.00008563991,0.00002730613,0.000012876436,0.0000014714094,0.0000031694685,0.0005654213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894845,0.00006413133,0.00029316192,0.00024224924,0.00025569074,0.00019632094],"domain_scores_gemma":[0.99926996,0.00030406882,0.000084297506,0.00019798556,0.00011619604,0.000027473692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032870893,0.000074215255,0.00010497082,0.00019613617,0.000030358085,0.00004103653,0.00039629173,0.00004338547,0.000061179235],"category_scores_gemma":[0.00014247913,0.000062184816,0.000029665684,0.0006565307,0.000053067244,0.001057397,0.000078678044,0.00006660661,0.000070828595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022441423,0.00024094233,0.005628635,0.000016681102,0.0000052569517,0.00004210267,0.0011249308,0.0017660699,0.022490013,0.8781509,0.004336018,0.08617605],"study_design_scores_gemma":[0.00010410789,0.00017451258,0.01792399,0.000105941646,0.0000020195805,0.0000036934127,0.00083768263,0.2040671,0.7481402,0.027490888,0.0009170722,0.00023280513],"about_ca_topic_score_codex":0.0014743764,"about_ca_topic_score_gemma":0.0010323327,"teacher_disagreement_score":0.85065997,"about_ca_system_score_codex":0.00007432984,"about_ca_system_score_gemma":0.00006540105,"threshold_uncertainty_score":0.25358233},"labels":[],"label_agreement":null},{"id":"W2022040790","doi":"10.1017/s0140525x01280145","title":"Feature development, object concepts, and the scope slip","year":2001,"lang":"en","type":"article","venue":"Behavioral and Brain Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scope (computer science); Architecture; Cognitive science; Feature (linguistics); Slip (aerodynamics); Cognition; Computer science; Object (grammar); Cognitive psychology; Artificial intelligence; Psychology; Engineering; Neuroscience; Geography; Philosophy; Programming language; Linguistics","score_opus":0.061164517267824604,"score_gpt":0.34380906369069963,"score_spread":0.282644546422875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022040790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97053254,0.002264822,0.0061261095,0.01770542,0.0002777632,0.00030103317,7.868392e-7,0.00009948143,0.0026920403],"genre_scores_gemma":[0.9854952,0.0001657498,0.010732611,0.0013669508,0.00005205965,0.000023480156,5.272603e-7,0.0000037819996,0.0021596085],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998608,0.0001001295,0.00014786821,0.0004553157,0.0003306861,0.0003580084],"domain_scores_gemma":[0.99939144,0.00019267412,0.00006615784,0.0001972973,0.00005146917,0.000100940735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167216,0.00013760349,0.00014763464,0.00007028398,0.0009930208,0.0007092719,0.0007888028,0.00004919526,0.00001595148],"category_scores_gemma":[0.00006040078,0.00007961684,0.000026162244,0.00069195277,0.0013644884,0.0008056456,0.00033813974,0.000118375276,0.000019334062],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033891116,0.000095735755,0.024260346,0.000009556306,0.0000065535423,0.00006965396,0.011535459,0.000011667409,0.0027105093,0.12684093,0.005455927,0.8289698],"study_design_scores_gemma":[0.0038336667,0.0018516402,0.17220055,0.00040463844,0.000067563065,0.0016418236,0.01923148,0.01608732,0.08023184,0.048541017,0.6524289,0.0034795583],"about_ca_topic_score_codex":0.00017453029,"about_ca_topic_score_gemma":0.0002478426,"teacher_disagreement_score":0.8254902,"about_ca_system_score_codex":0.000012809238,"about_ca_system_score_gemma":0.000118929565,"threshold_uncertainty_score":0.7637614},"labels":[],"label_agreement":null},{"id":"W2022696841","doi":"10.1371/journal.pone.0044877","title":"Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Wake Forest School of Medicine; University of California, San Diego; Genentech; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Synarc; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Support vector machine; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Dimensionality reduction; Voxel; Linear classifier; Linear regression; Computer science; Curse of dimensionality; Machine learning; Kernel (algebra); Overfitting; Feature vector; Classifier (UML); Mathematics; Sample size determination; Statistics; Artificial neural network","score_opus":0.08252367714996078,"score_gpt":0.28126696201081397,"score_spread":0.1987432848608532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022696841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98880213,0.0024574855,0.004438448,0.0031021908,0.00006955511,0.0005251546,0.000027634615,0.00003904427,0.0005383464],"genre_scores_gemma":[0.9929591,0.000022982174,0.0068677054,0.000043796663,0.00006319237,0.000023459197,0.0000039543324,0.0000068107106,0.000009021866],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99884045,0.00012028159,0.00027259495,0.00021398423,0.00033680152,0.00021588709],"domain_scores_gemma":[0.9986893,0.0002129216,0.00018020562,0.0005486953,0.00029667348,0.0000721839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002295705,0.00009379105,0.00016291071,0.000059790837,0.000048740443,0.000026889402,0.0006253026,0.000030820906,0.000026844888],"category_scores_gemma":[0.00019218119,0.00007112124,0.00004039252,0.00034755666,0.00014121672,0.00063109444,0.000121095865,0.00010481061,0.000020209818],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010878286,0.0025795135,0.2928277,0.000060886057,0.00040968112,0.0000031978236,0.04888063,0.000528997,0.3965339,0.25533658,0.00012319317,0.0026069267],"study_design_scores_gemma":[0.00013972197,0.00005652286,0.5190196,0.00013072742,0.00009977635,1.9105202e-7,0.0025632891,0.0419642,0.40324235,0.032595344,0.000005527004,0.00018274543],"about_ca_topic_score_codex":0.0009224695,"about_ca_topic_score_gemma":0.00007152424,"teacher_disagreement_score":0.22619191,"about_ca_system_score_codex":0.00004909798,"about_ca_system_score_gemma":0.000051895568,"threshold_uncertainty_score":0.29002398},"labels":[],"label_agreement":null},{"id":"W2062263159","doi":"10.3819/ccbr.2009.40005","title":"Metacognition in animals: Trends and challenges","year":2009,"lang":"en","type":"article","venue":"Comparative Cognition & Behavior Reviews","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health","keywords":"Metacognition; Comparative cognition; Psychology; Cognition; Animal cognition; Cognitive psychology; Comparative psychology; Field (mathematics); Cognitive science; Neuroscience; Mathematics","score_opus":0.34309039507197653,"score_gpt":0.4087742746890878,"score_spread":0.06568387961711125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062263159","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29658425,0.5238011,0.080305524,0.01238578,0.000789259,0.005746598,0.000035924477,0.0009579916,0.07939359],"genre_scores_gemma":[0.97153807,0.02278739,0.004921453,0.00031855013,0.000042144293,0.00030807886,0.000014840395,0.0000062847985,0.000063185376],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997859,0.00042489992,0.0006096662,0.000590359,0.00020185215,0.00031419387],"domain_scores_gemma":[0.99908864,0.00008244506,0.00021233641,0.00032316777,0.00017266154,0.00012077095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006762392,0.0002599946,0.00055508275,0.00037838865,0.00012154566,0.00014444305,0.00033447656,0.00006873739,0.0000864262],"category_scores_gemma":[0.000059513866,0.00024158992,0.000096458505,0.00077143114,0.000075664095,0.0009357255,0.000065404754,0.00019934699,0.00026697398],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010025611,0.00031645873,0.00007531184,0.000020555854,0.0000035425155,0.000028842993,0.0017224159,7.931523e-7,0.0038529143,0.022434983,0.00018220657,0.9713519],"study_design_scores_gemma":[0.0030037176,0.004587641,0.508744,0.002553551,0.00062202016,0.00037893452,0.003307615,0.0075902585,0.10569729,0.082862146,0.27626762,0.0043852427],"about_ca_topic_score_codex":0.0000045246625,"about_ca_topic_score_gemma":0.0000676979,"teacher_disagreement_score":0.9669667,"about_ca_system_score_codex":0.000044387525,"about_ca_system_score_gemma":0.000017274093,"threshold_uncertainty_score":0.9851751},"labels":[],"label_agreement":null},{"id":"W2116864659","doi":"10.1111/j.0963-7214.2006.00424.x","title":"Evaluating Explanations in Law, Science, and Everyday Life","year":2006,"lang":"en","type":"article","venue":"Current Directions in Psychological Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Psychology; Coherence (philosophical gambling strategy); Everyday life; Simple (philosophy); Artificial neural network; Cognitive science; Computational model; Epistemology; Artificial intelligence; Management science; Cognitive psychology; Computer science","score_opus":0.13322540174186823,"score_gpt":0.46400078439192444,"score_spread":0.33077538265005624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116864659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9354775,0.000648891,0.022201953,0.0012078803,0.0023885136,0.00044518395,0.0000017733167,0.00021176721,0.037416536],"genre_scores_gemma":[0.9921186,0.0000550538,0.0074856672,0.00017052327,0.000051891562,0.000089426525,4.0776348e-7,0.0000030677077,0.000025382364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9965897,0.00011071877,0.00046210393,0.0011289176,0.0009903387,0.00071819354],"domain_scores_gemma":[0.99866104,0.00022851756,0.00008988034,0.00050870446,0.00032221442,0.00018961611],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0045988653,0.00014726257,0.0001560593,0.0009629364,0.0008931151,0.0005200886,0.0015035298,0.000048135033,0.000019622787],"category_scores_gemma":[0.0018110176,0.00012980265,0.000025355477,0.010045672,0.0027795741,0.0020000166,0.00037854354,0.00031279094,0.000042405496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000405538,0.0007105425,0.0146466885,0.000004053794,4.468701e-7,0.000006772711,0.00040016146,0.0015507414,0.0076064244,0.83826566,0.0001836513,0.13662083],"study_design_scores_gemma":[0.00054050476,0.00029367,0.5594837,0.00013916625,0.000003841879,0.000047736095,0.00035919072,0.22415213,0.0049927537,0.20215544,0.0070093414,0.0008225407],"about_ca_topic_score_codex":0.00033545532,"about_ca_topic_score_gemma":0.00039162842,"teacher_disagreement_score":0.6361102,"about_ca_system_score_codex":0.0003514744,"about_ca_system_score_gemma":0.00024467002,"threshold_uncertainty_score":0.9999343},"labels":[],"label_agreement":null},{"id":"W2155478180","doi":"10.1609/aaai.v27i3.19009","title":"Model AI Assignments 2013","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; Variety (cybernetics); Dissemination; Artificial intelligence; Multimedia; Core (optical fiber); World Wide Web; Telecommunications","score_opus":0.08977113249345287,"score_gpt":0.29854480852091986,"score_spread":0.208773676027467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155478180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22735582,0.00010255334,0.6285674,0.05691194,0.0019569197,0.0035560788,0.000014261207,0.00078820385,0.080746844],"genre_scores_gemma":[0.9873146,0.00004686079,0.0089960825,0.0013590512,0.000071350136,0.00015934205,4.4866653e-7,0.000027985947,0.0020242843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628824,0.000031855117,0.0009695924,0.0008780856,0.0010124999,0.0008197518],"domain_scores_gemma":[0.9968468,0.00011260444,0.00052189647,0.00076875737,0.0015052111,0.00024471554],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005697196,0.00042472026,0.0004063131,0.00023485396,0.0003881241,0.00080189743,0.0045321938,0.00018060466,0.0003680483],"category_scores_gemma":[0.00038733505,0.00032446248,0.0002164308,0.0010469571,0.00043270626,0.0020845614,0.0009136864,0.0005569761,0.0020596774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015736634,0.00023151604,0.00012719756,0.000025237478,0.00001855496,4.792075e-7,0.0010422107,0.0013428801,0.0762662,0.880408,0.0044952934,0.036026698],"study_design_scores_gemma":[0.000009960877,0.00008427611,0.000036358426,0.00006955159,0.000005124488,0.000002005455,0.00024448516,0.37169522,0.312713,0.31485772,0.00008312617,0.00019915217],"about_ca_topic_score_codex":0.00031904058,"about_ca_topic_score_gemma":0.000022228787,"teacher_disagreement_score":0.7599588,"about_ca_system_score_codex":0.00011603067,"about_ca_system_score_gemma":0.00018238268,"threshold_uncertainty_score":0.9999207},"labels":[],"label_agreement":null},{"id":"W2400907344","doi":"10.2139/ssrn.2960292","title":"Identification of Biased Beliefs in Games of Incomplete Information Using Experimental Data","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bank of Canada; University of Toronto","funders":"","keywords":"Identification (biology); Complete information; Computer science; Econometrics; Data science; Psychology; Data mining; Mathematical economics; Mathematics","score_opus":0.061692251354559545,"score_gpt":0.34158043403264476,"score_spread":0.27988818267808524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400907344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6946066,0.00034109078,0.3044718,0.00022041221,0.00017053231,0.00011006865,0.000005072455,0.000008269015,0.00006618741],"genre_scores_gemma":[0.99818367,0.00015783022,0.0015951731,0.000011129439,0.000032549164,0.0000012650837,0.0000039992137,0.000004125105,0.000010250653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981734,0.00006471915,0.0006703045,0.00014665994,0.00030741157,0.0006374701],"domain_scores_gemma":[0.9978366,0.00003120833,0.000955919,0.001010471,0.00013461235,0.000031212156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022466173,0.00008430138,0.00015500751,0.00023825765,0.00020822075,0.00018720486,0.0023195515,0.000038877624,0.0000038895732],"category_scores_gemma":[0.00023715837,0.000085248816,0.00003657678,0.00015975045,0.000085308355,0.004618532,0.0003991311,0.00035034516,0.0000067884926],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077843455,0.00034742567,0.0060047554,0.000048309492,0.00009051542,0.000004227017,0.0050912015,0.0034044597,0.3939912,0.48845947,0.000028519951,0.10245206],"study_design_scores_gemma":[0.0005849803,0.00027588962,0.0038685142,0.0001244306,0.000010301675,0.00011340346,0.0039036428,0.39329422,0.49824402,0.099218264,0.000104082625,0.00025826285],"about_ca_topic_score_codex":0.0006747595,"about_ca_topic_score_gemma":0.00045757348,"teacher_disagreement_score":0.38988975,"about_ca_system_score_codex":0.00032258953,"about_ca_system_score_gemma":0.0008704678,"threshold_uncertainty_score":0.43103427},"labels":[],"label_agreement":null},{"id":"W2479734208","doi":"10.1016/j.media.2016.07.012","title":"Learning in data-limited multimodal scenarios: Scandent decision forests and tree-based features","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Aging; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Decision tree; Computer science; Artificial intelligence; Classifier (UML); Feature (linguistics); Machine learning; Decision tree learning; Random forest; Pattern recognition (psychology); Tree (set theory); Incremental decision tree; Data mining; Mathematics","score_opus":0.018317545149545804,"score_gpt":0.30574153267386384,"score_spread":0.287423987524318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479734208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19457772,0.00015725863,0.7999866,0.004979629,0.000049378697,0.0000835729,0.0000028590653,0.00008889999,0.00007410094],"genre_scores_gemma":[0.977597,0.00008997161,0.021693159,0.00037155245,0.000045238656,0.000009540263,0.000018525774,0.000009393843,0.00016561437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705344,0.0002410239,0.0004378155,0.00082761835,0.000994705,0.00044538695],"domain_scores_gemma":[0.9972625,0.0011671152,0.0001049736,0.0010050472,0.00011797133,0.00034243453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012884219,0.00018063332,0.0003692851,0.0007076164,0.00014089103,0.00022841801,0.001488274,0.00013397729,0.00019023952],"category_scores_gemma":[0.0041248747,0.00011815647,0.000103582235,0.0018959299,0.00021513281,0.0008499605,0.00072133495,0.00026675448,0.00005475915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042293763,0.00015115603,0.11096695,0.000007405479,0.00011917446,0.00046064268,0.00026387148,0.00087583455,0.00086858263,0.00015337722,0.00048663554,0.8856041],"study_design_scores_gemma":[0.0004919068,0.000057221427,0.07074289,0.000098057724,0.00009184899,0.000003952148,0.00006343342,0.9250309,0.0022916093,0.00041277788,0.00050823943,0.00020716117],"about_ca_topic_score_codex":0.0008935195,"about_ca_topic_score_gemma":0.017435288,"teacher_disagreement_score":0.92415506,"about_ca_system_score_codex":0.00007380889,"about_ca_system_score_gemma":0.00013107977,"threshold_uncertainty_score":0.97293},"labels":[],"label_agreement":null},{"id":"W2559780085","doi":"","title":"Proceedings of the 3rd International Workshop on Evaluation Methods for Machine Learning","year":2008,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.14147653804815027,"score_gpt":0.41304350251220384,"score_spread":0.2715669644640536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559780085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10273777,0.00013752237,0.7568947,0.024003768,0.0038054192,0.0014737828,0.00001787248,0.00040258255,0.1105266],"genre_scores_gemma":[0.9642351,0.00007072191,0.030863928,0.00035441638,0.00018384604,0.00011096578,0.000027645636,0.000025374253,0.0041279728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972736,0.00022169405,0.00053162937,0.00059736444,0.0010772805,0.00029843382],"domain_scores_gemma":[0.9969671,0.00067193975,0.0005564182,0.00023216137,0.0015005813,0.000071830385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019573637,0.00025733165,0.00023888283,0.00033853765,0.00044241894,0.0002052828,0.0020086009,0.00010161634,0.00031783717],"category_scores_gemma":[0.0038693277,0.00020870667,0.00018898532,0.00038946344,0.00011395973,0.0005664131,0.00036849326,0.00082177756,0.00004148905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026706283,0.00024743777,0.0105567565,0.000017334218,0.0001499766,0.0000029899218,0.0033519776,0.04081494,0.019976169,0.67654705,0.00020881118,0.24785948],"study_design_scores_gemma":[0.00038099717,0.00021102624,0.0013626548,0.0001366114,0.000010888449,0.000019456158,0.00019334898,0.9548531,0.018577846,0.01161255,0.012424967,0.00021653004],"about_ca_topic_score_codex":0.00008332481,"about_ca_topic_score_gemma":0.000012780162,"teacher_disagreement_score":0.9140382,"about_ca_system_score_codex":0.00021559946,"about_ca_system_score_gemma":0.00013740333,"threshold_uncertainty_score":0.8510811},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06341091681322418,"score_gpt":0.28276736659888757,"score_spread":0.21935644978566338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561412020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9119898,0.0011046507,0.060578533,0.005050291,0.00036784817,0.0008753035,0.0000023633831,0.00042886357,0.019602332],"genre_scores_gemma":[0.96613413,0.0003391149,0.02907059,0.00032914255,0.00005817412,0.00005265707,0.0000034256707,0.000021796866,0.003990995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790317,0.0001326474,0.00033116087,0.00066151185,0.0004538044,0.00051771704],"domain_scores_gemma":[0.99796927,0.000062346844,0.00019880969,0.0015337674,0.00009083211,0.00014497322],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007403527,0.0001898291,0.00030062633,0.00015965397,0.000464346,0.0019831895,0.0021471488,0.000081880455,0.000098987395],"category_scores_gemma":[0.00024226167,0.00018719565,0.000047793685,0.00018540285,0.000092688664,0.0054531596,0.0007609823,0.00043238807,0.00036729197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004168024,0.020414606,0.1123071,0.0010042326,0.00081314245,0.000652649,0.166329,0.0040453654,0.15248749,0.16098158,0.00049119175,0.38005686],"study_design_scores_gemma":[0.00023540788,0.00032088114,0.0006678928,0.00039324837,0.000017962755,0.00000614257,0.00062839984,0.8883874,0.097441174,0.010877989,0.00059456885,0.00042896156],"about_ca_topic_score_codex":0.001118442,"about_ca_topic_score_gemma":0.0002150719,"teacher_disagreement_score":0.884342,"about_ca_system_score_codex":0.00009770435,"about_ca_system_score_gemma":0.000046589885,"threshold_uncertainty_score":0.9990528},"labels":[],"label_agreement":null},{"id":"W2613094910","doi":"10.1109/cvprw.2017.215","title":"Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Canadian Institute for Advanced Research; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ambiguity; Computer science; Visualization; Deep neural networks; Class (philosophy); Process (computing); Artificial intelligence; Machine learning; Decision-making; Artificial neural network","score_opus":0.09244963275525038,"score_gpt":0.30320837872067985,"score_spread":0.21075874596542948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613094910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029923987,0.000025235435,0.9319558,0.009113453,0.00067064684,0.0005713232,5.7228146e-7,0.00027734725,0.027461635],"genre_scores_gemma":[0.9837938,0.0000042546762,0.013216436,0.0018586451,0.00016928189,0.00009436217,0.0000010417344,0.00003187528,0.0008303267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667954,0.0004391425,0.00043817793,0.00091034954,0.0005375959,0.0009951674],"domain_scores_gemma":[0.99616927,0.0008518563,0.00026915764,0.0023069542,0.00012464414,0.0002781383],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021659352,0.00033286618,0.0003018285,0.00017409159,0.0030180975,0.0023523592,0.0038294608,0.00012487292,0.000019036292],"category_scores_gemma":[0.00077322294,0.00024656256,0.00015034998,0.0005217031,0.00026539405,0.0016900614,0.001420895,0.00044720675,0.00012920625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010825729,0.0001342446,0.00019697944,0.000009257372,0.00007677132,0.00008924549,0.01786988,0.11982004,0.0023035232,0.8443146,0.0011394251,0.012963456],"study_design_scores_gemma":[0.0001915381,0.00022164077,0.00057290064,0.000021490958,0.000008403007,0.000017700931,0.014041247,0.9779249,0.0023866794,0.0038408954,0.00037843882,0.00039418717],"about_ca_topic_score_codex":0.00012725928,"about_ca_topic_score_gemma":0.00016504563,"teacher_disagreement_score":0.9538698,"about_ca_system_score_codex":0.00030524403,"about_ca_system_score_gemma":0.000052657942,"threshold_uncertainty_score":0.9999987},"labels":[],"label_agreement":null},{"id":"W2616591008","doi":"10.48550/arxiv.1705.05278","title":"Unimodal probability distributions for deep ordinal classification","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Ordinal data; Probability distribution; Binomial (polynomial); Poisson distribution; Binomial distribution; Mathematics; Ordinal regression; Entropy (arrow of time); Context (archaeology); Poisson binomial distribution; Statistics; Ordinal optimization; Principle of maximum entropy; Negative binomial distribution; Artificial intelligence; Computer science; Pattern recognition (psychology); Beta-binomial distribution; Geography","score_opus":0.20686150628964825,"score_gpt":0.2480125443743021,"score_spread":0.04115103808465384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616591008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06863578,0.000019906867,0.9269184,0.0006693299,0.00065580517,0.00087922736,0.00007437142,0.00025752003,0.0018896515],"genre_scores_gemma":[0.990601,0.00002952376,0.008306989,0.000020379279,0.000110848734,0.000016315318,0.00009039856,0.000013886292,0.00081064407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756366,0.00013317227,0.00027988752,0.0014189899,0.000104786704,0.00049949955],"domain_scores_gemma":[0.99588835,0.0001889146,0.00044589757,0.002620844,0.0006547947,0.00020122551],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055660674,0.00030603184,0.0003135783,0.00014782112,0.0008597284,0.00039897693,0.0033121994,0.00034478962,0.000016240501],"category_scores_gemma":[0.0003775954,0.00036513022,0.00028900628,0.00030950303,0.00031371365,0.00078591926,0.0015496803,0.00046133331,0.000092834154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003409169,0.00016199937,0.0015447523,0.00007953408,0.000039747596,0.000023969842,0.00011961231,0.023676839,0.00007050118,0.9715165,0.00021129195,0.0025211466],"study_design_scores_gemma":[0.000101316655,0.000046492794,0.0018082455,0.00002951985,0.00003839889,0.0000015319722,0.00005012007,0.54869884,0.00051236356,0.4470163,0.0014009877,0.00029584952],"about_ca_topic_score_codex":0.00026760862,"about_ca_topic_score_gemma":0.0003403885,"teacher_disagreement_score":0.92196524,"about_ca_system_score_codex":0.00061659416,"about_ca_system_score_gemma":0.0004717863,"threshold_uncertainty_score":0.9998801},"labels":[],"label_agreement":null},{"id":"W2753913847","doi":"10.15353/vsnl.v3i1.166","title":"Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction","year":2017,"lang":"en","type":"preprint","venue":"Journal of Computational Vision and Imaging Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute; Canadian Institute for Advanced Research; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Interpretability; Deep learning; Artificial intelligence; Machine learning; Computer science; Financial market; Stock market; Stock (firearms); Finance; Economics; Engineering","score_opus":0.02321433490793953,"score_gpt":0.3150460745439577,"score_spread":0.2918317396360182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753913847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1264432,0.00048563778,0.87119806,0.0007441298,0.00039930004,0.0005977635,0.000007260065,0.00002138542,0.000103257335],"genre_scores_gemma":[0.9699335,0.000033389286,0.02966738,0.000061329,0.00019973709,0.000021778547,0.000006197312,0.000023692637,0.000052972573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969697,0.00070772297,0.0009291649,0.000413813,0.0007244539,0.00025516003],"domain_scores_gemma":[0.9955679,0.0010340109,0.0021407788,0.00025811192,0.000887465,0.000111726724],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003306304,0.00026840682,0.00058383273,0.00031700943,0.0006687753,0.0011424811,0.00066827046,0.00010839948,8.6404236e-7],"category_scores_gemma":[0.0005620039,0.00020085226,0.00013185159,0.00013245053,0.00026293483,0.0009805249,0.00044620514,0.0007433552,2.6453182e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026481422,0.000103617065,0.002149235,0.0005855329,0.00017156122,0.000025822857,0.015640413,0.95602757,0.0009555322,0.0023153329,0.0008316235,0.018545602],"study_design_scores_gemma":[0.0006032902,0.0006355915,0.014298724,0.0015203806,0.000048011658,0.00027000924,0.0022905408,0.97893655,0.000114151335,0.0007745121,0.00030670236,0.00020155072],"about_ca_topic_score_codex":0.000015081018,"about_ca_topic_score_gemma":7.5196414e-7,"teacher_disagreement_score":0.8434903,"about_ca_system_score_codex":0.00009387277,"about_ca_system_score_gemma":0.00034710413,"threshold_uncertainty_score":0.99989444},"labels":[],"label_agreement":null},{"id":"W2773154100","doi":"","title":"LibGuides: UofM Dataverse General Terms of Use: General Rules of Conduct and Conduct Requirements","year":2017,"lang":"en","type":"libguides","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.18158639198957371,"score_gpt":0.3621473063768665,"score_spread":0.18056091438729277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773154100","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75667924,0.0033617332,0.066089906,0.0025454962,0.020530397,0.0059169563,0.004910158,0.0011290816,0.13883702],"genre_scores_gemma":[0.06474589,0.00661462,0.6415166,0.0023037952,0.0025679993,0.00012409351,0.0017389931,0.00036958623,0.2800184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955233,0.00020739093,0.0014549398,0.0012347962,0.00087110535,0.00070850656],"domain_scores_gemma":[0.9943548,0.00023173787,0.0014524694,0.003233737,0.00049116847,0.000236128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084017473,0.0006440403,0.00123518,0.0004511973,0.00025576926,0.0005813177,0.0038654075,0.00044751156,0.0002955275],"category_scores_gemma":[0.00059124856,0.0005545066,0.00022372545,0.00016898355,0.0009202589,0.003315893,0.002171628,0.00035757787,0.0000644117],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006851286,0.00033967057,0.0025666007,0.0011756703,0.0007123933,0.00023665602,0.0012038067,0.00012433004,0.058276646,0.2692491,0.6420233,0.024023298],"study_design_scores_gemma":[0.0009198985,0.0009648175,0.0007699432,0.0011369524,0.00022381185,0.00010221672,0.00021794834,0.020342233,0.38605237,0.02135861,0.56572974,0.0021814737],"about_ca_topic_score_codex":0.005043629,"about_ca_topic_score_gemma":0.000224149,"teacher_disagreement_score":0.69193333,"about_ca_system_score_codex":0.00007609479,"about_ca_system_score_gemma":0.00040190684,"threshold_uncertainty_score":0.99969065},"labels":[],"label_agreement":null},{"id":"W2806372986","doi":"10.1609/aaai.v32i1.11353","title":"Building More Explainable Artificial Intelligence With Argumentation","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Research Foundation","keywords":"Argumentation theory; Artificial intelligence; Black box; Computer science; Order (exchange); Data science; Management science; Epistemology; Engineering; Philosophy","score_opus":0.07023473309506409,"score_gpt":0.31771451339344026,"score_spread":0.24747978029837617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806372986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27637854,0.000048537484,0.6973296,0.008403928,0.0013456981,0.0016619249,0.000010167522,0.00051734643,0.014304261],"genre_scores_gemma":[0.9632074,0.000025469275,0.035521537,0.0005305604,0.00027896932,0.00011819181,0.0000010773199,0.000049739763,0.00026701443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99455065,0.00006187656,0.0013654185,0.0014170457,0.0014330058,0.0011720115],"domain_scores_gemma":[0.995389,0.00024379039,0.00094096735,0.0009781204,0.0022116557,0.00023650563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012581706,0.000648593,0.00056954223,0.00047935714,0.0009819557,0.0009464029,0.004399784,0.00021980485,0.0002304902],"category_scores_gemma":[0.0006545499,0.00049697876,0.00020948287,0.002852066,0.0015396987,0.0019592482,0.0008136844,0.0006265243,0.0004472836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019497676,0.0002554425,0.00006705917,0.000048580216,0.000031724776,0.0000033393937,0.0031921885,0.00024691375,0.07466657,0.8231274,0.00007474635,0.09809104],"study_design_scores_gemma":[0.000014591117,0.0006523155,0.00003748903,0.00031852335,0.00002066317,0.000017029026,0.0028473963,0.05874887,0.64226043,0.29449618,0.00016556308,0.00042093624],"about_ca_topic_score_codex":0.00020957823,"about_ca_topic_score_gemma":0.000072326126,"teacher_disagreement_score":0.6868289,"about_ca_system_score_codex":0.00022755092,"about_ca_system_score_gemma":0.00030447822,"threshold_uncertainty_score":0.9997482},"labels":[],"label_agreement":null},{"id":"W2887879157","doi":"10.18653/v1/w18-5434","title":"Learning Explanations from Language Data","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Linguistics; Psychology; Natural language processing; Cognitive psychology; Data science; Cognitive science; Philosophy","score_opus":0.09718035733699655,"score_gpt":0.34636045480738575,"score_spread":0.24918009747038922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887879157","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0142537635,0.00020203991,0.9500796,0.0011870926,0.0012198952,0.00018910342,0.000066278364,0.0007276362,0.03207455],"genre_scores_gemma":[0.6552707,0.000089528636,0.3333425,0.00068908936,0.0012627927,0.000042218533,0.0016249836,0.000041594027,0.007636646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782515,0.00012810188,0.0003076341,0.0010860546,0.00035065506,0.0003024331],"domain_scores_gemma":[0.9958355,0.000242363,0.0001569429,0.003533577,0.00013200774,0.0000996466],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004612451,0.0002057354,0.00020639187,0.00013901305,0.00018513396,0.00064586045,0.005819956,0.00018402499,0.000709374],"category_scores_gemma":[0.00039339912,0.0002011277,0.000047612328,0.00020736111,0.000057804205,0.0006697556,0.0100629525,0.00058077986,0.0021975127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020489488,0.0005709307,0.0032191102,0.00014790599,0.0006226657,0.0006140906,0.074048094,0.013235678,0.004288596,0.21342413,0.27726138,0.41254693],"study_design_scores_gemma":[0.000051074425,0.000043054064,0.00023030497,0.00009295748,0.000019916804,0.0000030045353,0.0019531406,0.92045826,0.013265141,0.0344864,0.028777856,0.00061889406],"about_ca_topic_score_codex":0.004903203,"about_ca_topic_score_gemma":0.0010563304,"teacher_disagreement_score":0.90722257,"about_ca_system_score_codex":0.00005407848,"about_ca_system_score_gemma":0.00017573495,"threshold_uncertainty_score":0.99955904},"labels":[],"label_agreement":null},{"id":"W2888392564","doi":"10.1007/978-3-319-99740-7_24","title":"Measures of Model Interpretability for Model Selection","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Selection (genetic algorithm); Simplicity; Machine learning; Artificial intelligence; Measure (data warehouse); Model selection; Data mining","score_opus":0.06628423837819125,"score_gpt":0.29725731790965637,"score_spread":0.23097307953146512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888392564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030641985,0.00010202011,0.99633545,0.00021518038,0.0006836644,0.0007139129,0.000010932385,0.00013923444,0.0014932017],"genre_scores_gemma":[0.36727402,0.000010189354,0.63185483,0.00034469104,0.00016165992,0.00002489904,0.0000016168394,0.000028726025,0.00029936028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959723,0.000031428648,0.00078469695,0.0016237883,0.0009163798,0.0006714248],"domain_scores_gemma":[0.99642867,0.00041901506,0.00039897606,0.0013554094,0.001255698,0.00014221786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017482521,0.0004769348,0.00060271396,0.0007000294,0.00024056964,0.00025435706,0.0033675802,0.0003619636,0.000011133978],"category_scores_gemma":[0.00036017766,0.0004547677,0.0002268046,0.0005431675,0.0010216063,0.0008894176,0.00090219686,0.00046187127,0.00001326302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023885652,0.000039969284,0.000011923896,0.00006235235,0.00001027385,9.793279e-7,0.0018535752,0.78395826,0.0017539983,0.044481926,0.000028678136,0.16777417],"study_design_scores_gemma":[0.000043314012,0.00014505259,0.0000010506433,0.000101821126,0.000005423171,0.0000041303497,1.658284e-7,0.56793624,0.02717021,0.404305,0.000039842125,0.0002477726],"about_ca_topic_score_codex":0.00002708828,"about_ca_topic_score_gemma":0.00026593683,"teacher_disagreement_score":0.3669676,"about_ca_system_score_codex":0.0004190705,"about_ca_system_score_gemma":0.0010679795,"threshold_uncertainty_score":0.99979043},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02554129803942862,"score_gpt":0.267225479299438,"score_spread":0.2416841812600094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888580379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003260356,0.00054870895,0.9770159,0.00771268,0.003011493,0.00053735165,0.0000016291574,0.00024884078,0.010890751],"genre_scores_gemma":[0.109875314,0.00024624055,0.80510134,0.037732646,0.008588174,0.00006585538,0.00000927458,0.00024457643,0.03813656],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946242,0.000061134466,0.00068069174,0.0019617453,0.0014153194,0.0012569363],"domain_scores_gemma":[0.9950741,0.00071225845,0.00031817443,0.0030878182,0.00048627745,0.0003213561],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015691848,0.0006780875,0.0005313509,0.0006840983,0.0007837857,0.0016000217,0.008783604,0.00037469075,0.00026257796],"category_scores_gemma":[0.00025424824,0.0005054731,0.00018969104,0.001228884,0.0015007353,0.0013719775,0.0026994685,0.0011510503,0.0010617666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011849952,0.000038460767,0.000018406075,0.000030679934,0.000021172433,0.00020963453,0.0056634457,0.017913913,0.00023522897,0.21191797,0.004547774,0.7593915],"study_design_scores_gemma":[0.00009368134,0.00024339613,0.000011380153,0.0002278317,0.000007644244,0.00009093472,0.0000013608013,0.22928266,0.010916398,0.6983115,0.060084525,0.00072867697],"about_ca_topic_score_codex":0.00020050403,"about_ca_topic_score_gemma":0.00045620668,"teacher_disagreement_score":0.75866276,"about_ca_system_score_codex":0.00043207285,"about_ca_system_score_gemma":0.001554366,"threshold_uncertainty_score":0.9997397},"labels":[],"label_agreement":null},{"id":"W2903079774","doi":"10.23919/eusipco.2018.8553178","title":"“What are You Listening to?” Explaining Predictions of Deep Machine Listening Systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Active listening; Benchmark (surveying); Trustworthiness; Artificial intelligence; Feature (linguistics); Deep neural networks; Representation (politics); Inversion (geology); Face (sociological concept); Quality (philosophy); Machine learning; Speech recognition; Artificial neural network; Pattern recognition (psychology); Linguistics","score_opus":0.02990730751658645,"score_gpt":0.2827500205386372,"score_spread":0.25284271302205075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903079774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025489198,0.0003820606,0.9587562,0.0007042805,0.0029928435,0.00033601013,0.0000030260865,0.00045277094,0.01088358],"genre_scores_gemma":[0.9659289,0.000015416656,0.03140469,0.00028885933,0.0003618422,0.000046966918,0.0000023904468,0.000023783177,0.0019271392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975606,0.000111091045,0.0006644316,0.00061570515,0.000488458,0.0005596657],"domain_scores_gemma":[0.9977657,0.00021670868,0.00026826985,0.000941988,0.0005538087,0.00025348403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072368083,0.00022679684,0.00033357117,0.00034399747,0.00045256215,0.0006506785,0.0012040959,0.00009542832,0.00006451877],"category_scores_gemma":[0.00028887665,0.00021289228,0.000095755284,0.0011247367,0.00011549649,0.0020692397,0.00056745554,0.0001709097,0.00022349962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018723797,0.0007260447,0.029230392,0.0005175543,0.00044536495,0.00028177624,0.17776531,0.11276427,0.03430035,0.5075285,0.005598947,0.13065428],"study_design_scores_gemma":[0.00011951554,0.00046831052,0.00037076374,0.0004608279,0.000013462239,0.00006620387,0.017422982,0.94775856,0.027274478,0.00041318787,0.005241269,0.000390464],"about_ca_topic_score_codex":0.0004990028,"about_ca_topic_score_gemma":0.000527308,"teacher_disagreement_score":0.9404397,"about_ca_system_score_codex":0.000095210075,"about_ca_system_score_gemma":0.00004684793,"threshold_uncertainty_score":0.8681495},"labels":[],"label_agreement":null},{"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.06201937909602152,"score_gpt":0.3515502138729238,"score_spread":0.2895308347769023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910705748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90711695,0.0015193985,0.010767443,0.0071131596,0.000061034123,0.0011521506,0.00000866264,0.00009087585,0.07217034],"genre_scores_gemma":[0.9475317,0.000078253426,0.052154258,0.00012188591,0.000008551966,0.000017505812,4.955887e-8,0.0000018746783,0.00008592032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989209,0.000016920068,0.00026528444,0.00024988523,0.00041694415,0.00013002423],"domain_scores_gemma":[0.99926424,0.00033537758,0.0002282459,0.000011824143,0.00013773948,0.000022597518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019979542,0.000063749656,0.00011579797,0.00021751538,0.00013818104,0.000051470848,0.0010127056,0.00004146984,0.000007825643],"category_scores_gemma":[0.00040866554,0.000046350164,0.000029852044,0.0011896398,0.00027316596,0.00086047576,0.00032716396,0.00017984792,0.0000037931995],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013405515,0.000021407744,0.021469573,0.000026653968,0.0000024687185,1.1669323e-9,0.00033259054,0.00037122905,0.07048021,0.90537316,0.000011544877,0.0019097886],"study_design_scores_gemma":[0.000058879064,0.000039821844,0.014248158,0.00007660213,0.0000027075125,0.000005422404,0.00046917255,0.09281341,0.2711298,0.6203507,0.00070835487,0.00009696729],"about_ca_topic_score_codex":0.000023408855,"about_ca_topic_score_gemma":2.4860708e-7,"teacher_disagreement_score":0.28502247,"about_ca_system_score_codex":0.000023093555,"about_ca_system_score_gemma":0.000022669083,"threshold_uncertainty_score":0.18901049},"labels":[],"label_agreement":null},{"id":"W2911045808","doi":"10.5539/ijsp.v8n2p11","title":"Boosted Convolutional Decision Trees for Translationally Invariant Pattern Recognition and Transfer Learning","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Brain Tumor Society","keywords":"Convolutional neural network; Computer science; Pattern recognition (psychology); Artificial intelligence; Decision tree; Transfer of learning; Machine learning; Categorical variable; Hyperparameter; Invariant (physics); Tree (set theory); Mathematics","score_opus":0.03956154923011547,"score_gpt":0.27986037659620866,"score_spread":0.2402988273660932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911045808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26930636,0.00006465574,0.7293663,0.00067855994,0.00027226217,0.00016454248,0.000110021334,0.0000058909045,0.000031392225],"genre_scores_gemma":[0.88825655,0.00007490513,0.11145242,0.000108904,0.00006190665,0.000004893477,0.000023889734,0.000004830969,0.000011667858],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875987,0.00006681025,0.00047846208,0.0001950145,0.0003791279,0.00012069004],"domain_scores_gemma":[0.99760544,0.0009722186,0.00013502178,0.00006488633,0.0011510283,0.00007140726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000886586,0.000090798974,0.00014746097,0.000102200254,0.0000791832,0.0001645053,0.00023160451,0.00004653273,0.00005710119],"category_scores_gemma":[0.00031174882,0.000081643986,0.00004340125,0.00005272608,0.000055132365,0.00048576298,0.000036058293,0.00013992292,0.000004911463],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050400116,0.00018458451,0.02005603,0.00006436552,0.00013585767,0.000018652758,0.0022089975,0.0021371124,0.002181987,0.09087204,0.00010326593,0.8815331],"study_design_scores_gemma":[0.0014567929,0.00080486457,0.048611324,0.0001560623,0.00002581789,0.00016438613,0.00011872688,0.19280578,0.00092775916,0.7528573,0.0018309026,0.00024023728],"about_ca_topic_score_codex":0.000030709976,"about_ca_topic_score_gemma":0.00009433834,"teacher_disagreement_score":0.8812929,"about_ca_system_score_codex":0.00004969657,"about_ca_system_score_gemma":0.000109924236,"threshold_uncertainty_score":0.3329345},"labels":[],"label_agreement":null},{"id":"W2916951218","doi":"10.1016/j.dib.2019.103704","title":"Corrigendum to: “FreeSurfer subcortical normative data” [Data in Brief 9 (2016) 732–736]","year":2019,"lang":"en","type":"erratum","venue":"Data in Brief","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Normative; Psychology; Data science; Cognitive science; Computer science; Psychoanalysis; Epistemology; Philosophy","score_opus":0.12274566137513704,"score_gpt":0.33931176809049296,"score_spread":0.21656610671535592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916951218","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061720907,0.005919149,0.50756025,0.013887618,0.24463934,0.0090630865,0.12129091,0.0012971059,0.095725305],"genre_scores_gemma":[0.010132823,0.0051707113,0.08833334,0.025684528,0.01055694,0.00036120444,0.6210226,0.00093202206,0.23780583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891855,0.00059306156,0.0019363833,0.0047214082,0.0016665311,0.0018971005],"domain_scores_gemma":[0.9672784,0.0005371781,0.0005081708,0.030931091,0.00026466115,0.0004804946],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0040273485,0.0009175606,0.0013600711,0.0008056324,0.00016762635,0.0011480951,0.04441346,0.0007556436,0.0003349491],"category_scores_gemma":[0.0038396295,0.00096577225,0.0000651603,0.0023648164,0.00030454647,0.008438162,0.043249533,0.002795966,0.00493543],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038692804,0.00028831133,0.00058178423,0.00012066154,0.000039377977,0.0005653065,0.0005943016,0.00002106693,0.000011561431,0.003950476,0.9840095,0.009778929],"study_design_scores_gemma":[0.00025301334,0.00011562347,0.002117047,0.00054612505,0.00002530268,0.000038044087,0.00015889475,0.13492559,0.00004076356,0.0006139441,0.8600687,0.0010969988],"about_ca_topic_score_codex":0.019453363,"about_ca_topic_score_gemma":0.028713493,"teacher_disagreement_score":0.4997317,"about_ca_system_score_codex":0.00040486763,"about_ca_system_score_gemma":0.002151479,"threshold_uncertainty_score":0.99988884},"labels":[],"label_agreement":null},{"id":"W2919557871","doi":"10.1109/tmm.2019.2902099","title":"Multi-Scale Interpretation Model for Convolutional Neural Networks: Building Trust Based on Hierarchical Interpretation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Interpretability; Computer science; Discriminative model; Artificial intelligence; Convolutional neural network; Machine learning; Interpretation (philosophy); Deep learning; Artificial neural network; Feature (linguistics); Scale (ratio)","score_opus":0.024416744323347336,"score_gpt":0.2849254407007991,"score_spread":0.2605086963774518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919557871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017493159,0.000008947598,0.978833,0.00047748486,0.0019017983,0.00093149993,0.000035049106,0.00026677846,0.000052266038],"genre_scores_gemma":[0.75932753,0.000001993075,0.23955083,0.00063644716,0.000049851256,0.00020529405,0.000011286707,0.000027082699,0.00018970358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997785,0.00012713812,0.00047804453,0.0007288643,0.00039483485,0.00048612434],"domain_scores_gemma":[0.99799967,0.00096717465,0.00012833321,0.0005258612,0.0002010914,0.00017786576],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035379443,0.00028888317,0.0002597366,0.0003642843,0.00025386692,0.00015276727,0.00060786115,0.00017717933,0.000045155815],"category_scores_gemma":[0.000041170777,0.0002967906,0.0002517694,0.00036469309,0.00009980941,0.0007693412,0.0000049828095,0.00046869522,0.000110930996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036823243,0.0002780987,0.000024479754,0.00001575385,0.000015640733,0.0000010449802,0.0010360777,0.93367535,0.0038085976,0.00022798912,0.000026762486,0.060521986],"study_design_scores_gemma":[0.00077881134,0.00032733893,0.00008725024,0.00007213997,0.000017352693,0.000002164966,0.000050655875,0.9894702,0.008605626,0.00027428256,0.000013305123,0.00030091315],"about_ca_topic_score_codex":0.000023001583,"about_ca_topic_score_gemma":0.00005705921,"teacher_disagreement_score":0.74183434,"about_ca_system_score_codex":0.0002322164,"about_ca_system_score_gemma":0.00010012563,"threshold_uncertainty_score":0.99994844},"labels":[],"label_agreement":null},{"id":"W2922750115","doi":"10.1007/s10459-019-09884-7","title":"Correction to: Debiasing versus knowledge retrieval checklists to reduce diagnostic error in ECG interpretation","year":2019,"lang":"en","type":"erratum","venue":"Advances in Health Sciences Education","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Debiasing; Interpretation (philosophy); Computer science; MEDLINE; Information retrieval; Medical physics; Natural language processing; Psychology; Medicine; Social psychology; Programming language","score_opus":0.036095205801475225,"score_gpt":0.4161651358454293,"score_spread":0.38006993004395406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922750115","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011539932,0.025185248,0.10085664,0.010727403,0.8004026,0.0053431694,0.0000072238768,0.00028292259,0.045654852],"genre_scores_gemma":[0.8779709,0.00780259,0.06396043,0.0047661928,0.0036706754,0.0010102374,0.0001477805,0.00012493819,0.040546305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950301,0.00045994678,0.001197609,0.0016123739,0.00071222096,0.0009877625],"domain_scores_gemma":[0.9957228,0.0021995632,0.00061329,0.0007575644,0.00036810164,0.00033869225],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00280801,0.0003855636,0.000515376,0.0018404999,0.0003402838,0.00036917,0.0019134992,0.0002013816,0.000015084834],"category_scores_gemma":[0.009971761,0.00043003194,0.00006252005,0.0064366935,0.00013519828,0.002726525,0.00029582673,0.00082717073,0.00036381537],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021109922,0.00048687618,0.0011756554,0.000694877,0.0000033368756,0.0000030455715,0.026437763,0.04161271,0.000036964335,0.0027200754,0.13796179,0.7886558],"study_design_scores_gemma":[0.0005284612,0.0043843836,0.014263423,0.020336784,0.000012567927,0.00002688491,0.011153752,0.5178206,0.0015213203,0.0051982966,0.42233345,0.0024200755],"about_ca_topic_score_codex":0.0021867359,"about_ca_topic_score_gemma":0.014487496,"teacher_disagreement_score":0.86643094,"about_ca_system_score_codex":0.0031135834,"about_ca_system_score_gemma":0.00694128,"threshold_uncertainty_score":0.99981517},"labels":[],"label_agreement":null},{"id":"W2943040636","doi":"10.4018/978-1-5225-9069-9.ch006","title":"Explanations in Artificial Intelligence Decision Making","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in computational intelligence and robotics book series","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Management science; Computer science; Artificial intelligence; Engineering","score_opus":0.039497682339424044,"score_gpt":0.3160569381488064,"score_spread":0.2765592558093824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943040636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008849488,0.010272052,0.9477847,0.00083452056,0.0009818937,0.00056629727,0.000013713617,0.00009123651,0.039446693],"genre_scores_gemma":[0.121431984,0.054876707,0.7892539,0.0018572076,0.00046008936,0.00010132807,0.00012047463,0.00021603747,0.03168228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596786,0.000053822623,0.0014989303,0.0011736716,0.00073972327,0.00056599895],"domain_scores_gemma":[0.9967457,0.001783436,0.00043459327,0.000589053,0.000342143,0.00010507703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004917713,0.00059443864,0.00066748745,0.0010296243,0.0002196784,0.00033560087,0.0011812384,0.0003537372,0.00010759109],"category_scores_gemma":[0.0001816263,0.0006436921,0.00012005882,0.00040703916,0.00041824233,0.0037944093,0.0005753056,0.0007740726,0.00031639752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021361942,0.000023411534,0.000023224438,0.00003407562,0.0000058029937,0.000052254116,0.00031250942,0.4373765,4.7122427e-7,0.4735269,0.000009118182,0.088614404],"study_design_scores_gemma":[0.000017717935,0.00013186355,0.000017466198,0.0009063164,0.0000064196684,0.000044393644,0.00022225495,0.22876172,0.00009311103,0.7625689,0.0066758487,0.00055398804],"about_ca_topic_score_codex":0.000012156159,"about_ca_topic_score_gemma":0.0008603153,"teacher_disagreement_score":0.28904203,"about_ca_system_score_codex":0.0002726644,"about_ca_system_score_gemma":0.0003537654,"threshold_uncertainty_score":0.9996014},"labels":[],"label_agreement":null},{"id":"W2962737936","doi":"","title":"Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction.","year":2018,"lang":"en","type":"article","venue":"British Machine Vision Conference","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Semantics (computer science); Task (project management); Dual (grammatical number); Domain (mathematical analysis); Natural language processing; Artificial intelligence; Programming language; Mathematics; Engineering; Systems engineering","score_opus":0.06426731988318665,"score_gpt":0.2848324016629119,"score_spread":0.22056508177972525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962737936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08917577,0.00025145878,0.90609264,0.0010395402,0.0006866393,0.0004494704,0.000086954235,0.00033741715,0.0018801384],"genre_scores_gemma":[0.93242127,0.00039961145,0.066482104,0.00022557074,0.00020578098,0.000099668854,0.000010214097,0.000022024098,0.00013377926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768347,0.00009902456,0.00047148697,0.0008293691,0.00039885184,0.000517829],"domain_scores_gemma":[0.9983237,0.00021308154,0.00013344985,0.00058580114,0.00051921926,0.00022477758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007328165,0.00022423414,0.00028074242,0.00013540093,0.0006307718,0.00089534855,0.00068725424,0.00009817574,0.000035416346],"category_scores_gemma":[0.00022736265,0.0002651284,0.00006535131,0.0003844848,0.00023860355,0.0021122245,0.0005759512,0.00014723578,0.000025519626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050660023,0.0002824942,0.00036672977,0.0001036563,0.00003357183,0.000078837445,0.003542571,0.0004196739,0.0053327912,0.7083652,0.005357641,0.27606618],"study_design_scores_gemma":[0.00034961483,0.0005601769,0.0006439978,0.00021380447,0.000010330816,0.00013535596,0.0001756029,0.75354266,0.0051147765,0.23333704,0.005538087,0.00037855815],"about_ca_topic_score_codex":0.0005267178,"about_ca_topic_score_gemma":0.0009840835,"teacher_disagreement_score":0.8432455,"about_ca_system_score_codex":0.000035976376,"about_ca_system_score_gemma":0.000117152675,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W2963041618","doi":"10.1109/ijcnn.2018.8489172","title":"Interpretable Deep Convolutional Neural Networks via Meta-learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Machine learning","score_opus":0.030447145000053015,"score_gpt":0.26506993539975743,"score_spread":0.2346227903997044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963041618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001584909,0.00023780888,0.97692907,0.0005859,0.00071091397,0.00010454681,1.2860676e-7,0.00036035496,0.019486342],"genre_scores_gemma":[0.96923983,0.000003922519,0.026682729,0.0011870285,0.0002676866,0.000020901967,0.0000015912401,0.000011163319,0.0025851347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828124,0.00013130972,0.00030393954,0.000468386,0.00026828435,0.0005468379],"domain_scores_gemma":[0.99886626,0.00018336158,0.00008716583,0.00045371684,0.00026857402,0.00014092981],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048515663,0.00017798213,0.00023926255,0.00009236823,0.0003606767,0.0002605046,0.0009769575,0.00007435124,0.0018238914],"category_scores_gemma":[0.00009495415,0.00014818262,0.00014865515,0.0005091844,0.00017877673,0.0010353434,0.00046286057,0.00025328554,0.0006301193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055948494,0.00020915392,0.0018306258,0.0000109733155,0.00090485933,0.00006381657,0.003180304,0.17103878,0.0023213467,0.697519,0.006421163,0.11644403],"study_design_scores_gemma":[0.000035558354,0.00014756013,0.00006881226,0.0000019786517,0.0000338321,0.000024808342,0.00005821575,0.9859801,0.003227926,0.0055995854,0.0046390872,0.00018256181],"about_ca_topic_score_codex":0.00020336859,"about_ca_topic_score_gemma":0.000121480516,"teacher_disagreement_score":0.96765494,"about_ca_system_score_codex":0.00004970016,"about_ca_system_score_gemma":0.000028059627,"threshold_uncertainty_score":0.9990886},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02019924449996864,"score_gpt":0.26750177237627765,"score_spread":0.24730252787630902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964306570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0401568,0.00019641856,0.95400125,0.00018509806,0.00090460235,0.00048372996,9.638262e-7,0.00014385577,0.0039272713],"genre_scores_gemma":[0.9867202,0.0000028295187,0.012938404,0.000041985048,0.00019181099,0.000033048374,0.0000029554994,0.000013568222,0.000055199318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808085,0.00020943819,0.00048089286,0.00068074575,0.00022824187,0.0003198162],"domain_scores_gemma":[0.99696505,0.0003486748,0.00036214042,0.0017402474,0.00051773747,0.00006617857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007978382,0.00025315685,0.00028471765,0.00006381463,0.00014124483,0.00025167767,0.0019399263,0.0001596926,0.00004000107],"category_scores_gemma":[0.00015903465,0.00015151298,0.000113680515,0.00031905205,0.0003553745,0.00029106805,0.0025563692,0.00046136038,0.000013491177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011304628,0.00024779866,0.011131238,0.00036582,0.00011866018,0.0000055630067,0.010988803,0.26707253,0.00015658667,0.041546803,0.00016484164,0.6680883],"study_design_scores_gemma":[0.000022744862,0.0001039698,0.0012351791,0.000036324524,0.0000139604035,0.0000030700546,0.00010502019,0.9930344,0.0019994753,0.0032358177,0.000024895631,0.00018513862],"about_ca_topic_score_codex":0.0005314626,"about_ca_topic_score_gemma":0.0013067791,"teacher_disagreement_score":0.9465634,"about_ca_system_score_codex":0.00009325355,"about_ca_system_score_gemma":0.00008900699,"threshold_uncertainty_score":0.617852},"labels":[],"label_agreement":null},{"id":"W2966010467","doi":"10.1609/aaai.v33i01.33019890","title":"Learning Generalized Temporal Abstractions across Both Action and Perception","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Perception; Task (project management); Action (physics); Artificial intelligence; Key (lock); Human–computer interaction; Cognitive science; Psychology","score_opus":0.08339651864273415,"score_gpt":0.3342602207353737,"score_spread":0.25086370209263953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966010467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818029,0.000018399982,0.011687379,0.0019582366,0.00060126145,0.00051664055,0.0000027888598,0.00017667319,0.0032357238],"genre_scores_gemma":[0.99553704,0.00014091238,0.0029382033,0.00013960866,0.00008580242,0.000029412015,0.0000014353725,0.00001913093,0.0011084524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975901,0.00004092258,0.00062114355,0.0007024945,0.00053836504,0.000506965],"domain_scores_gemma":[0.99840206,0.00010552032,0.0004883971,0.00034251207,0.00054110686,0.00012043434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007831174,0.0002786658,0.0003025479,0.0001383841,0.0005048313,0.000566551,0.0011654432,0.00015442696,0.00025510314],"category_scores_gemma":[0.00022832645,0.00023152637,0.00013066002,0.0005921879,0.0002646615,0.0013261356,0.0003948942,0.0005691891,0.0007409099],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009915438,0.00016099594,0.0039530885,0.000070599825,0.000022162876,6.7433666e-7,0.0056265667,0.00079590356,0.38342085,0.4265767,0.00009409468,0.1791792],"study_design_scores_gemma":[0.00007210971,0.0006687409,0.0043333652,0.00023188266,0.000018560173,0.00002869029,0.01406656,0.23235717,0.6539393,0.092583105,0.0010668713,0.0006336279],"about_ca_topic_score_codex":0.000327845,"about_ca_topic_score_gemma":0.00006795768,"teacher_disagreement_score":0.3339936,"about_ca_system_score_codex":0.00009714271,"about_ca_system_score_gemma":0.0000792706,"threshold_uncertainty_score":0.9523145},"labels":[],"label_agreement":null},{"id":"W2966262171","doi":"","title":"Reproducibility in Machine Learning for Health","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Field (mathematics); Reproducibility; Machine learning; Scale (ratio); Artificial intelligence; Data science; Human health; Medicine","score_opus":0.088447391195338,"score_gpt":0.3988270749660196,"score_spread":0.3103796837706816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966262171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38155305,0.00009703071,0.45417625,0.078633755,0.0027608394,0.0024555332,0.00001680848,0.00078833476,0.0795184],"genre_scores_gemma":[0.9870693,0.00003059558,0.0045011225,0.00036534754,0.000057158803,0.00009942318,0.000051910753,0.000012784505,0.007812345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972726,0.00025974785,0.00046835106,0.0012992498,0.00038580192,0.00031422588],"domain_scores_gemma":[0.9979575,0.0004835168,0.00023998128,0.000899038,0.00034214085,0.00007777596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017864986,0.00013877949,0.00019594116,0.00031091445,0.00018008657,0.000244988,0.00082232896,0.000047068173,0.0002963558],"category_scores_gemma":[0.0024901992,0.00014901417,0.00008144734,0.00036983343,0.00003674125,0.00057624717,0.00017669739,0.00047456525,0.00033236024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008671122,0.00026222624,0.20282486,0.0000282133,0.00003372753,0.0000067473306,0.005980202,0.111216746,0.0022683276,0.6442588,0.00027128402,0.03276218],"study_design_scores_gemma":[0.00038114388,0.00035946927,0.022180138,0.000081827995,0.0000013525436,0.00000574378,0.0008062394,0.9491829,0.0017577036,0.016752565,0.008263385,0.0002275199],"about_ca_topic_score_codex":0.00071900175,"about_ca_topic_score_gemma":0.00021089899,"teacher_disagreement_score":0.83796614,"about_ca_system_score_codex":0.00019392755,"about_ca_system_score_gemma":0.00019914865,"threshold_uncertainty_score":0.6076622},"labels":[],"label_agreement":null},{"id":"W2966373041","doi":"10.1609/aaai.v33i01.33019751","title":"Model AI Assignments 2019","year":2019,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Variety (cybernetics); Dissemination; Computer science; Artificial intelligence; Core (optical fiber); Multimedia; World Wide Web; Telecommunications","score_opus":0.025657955760233785,"score_gpt":0.27708588290213276,"score_spread":0.251427927141899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966373041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017319262,0.00001589975,0.89980763,0.00148844,0.0003315455,0.00016262937,5.388313e-7,0.00018684495,0.08068718],"genre_scores_gemma":[0.9130118,0.0000045374554,0.034940768,0.0029265413,0.000019792373,0.000006644789,7.815868e-7,0.000008179993,0.049080987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884814,0.000021991562,0.00016751594,0.0003531018,0.0002893166,0.00031991286],"domain_scores_gemma":[0.9990644,0.0000349149,0.00003499404,0.00071421586,0.00006598558,0.00008549593],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019364628,0.000101103346,0.00010405738,0.000066509085,0.00005324363,0.00015959365,0.0009408122,0.000048668488,0.00028124172],"category_scores_gemma":[0.000012162192,0.00008852407,0.000044955304,0.00021997635,0.000015288108,0.0010224022,0.00028167357,0.00009731609,0.008074986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033440704,0.00008314811,0.0011438864,0.000005447706,0.000010088188,0.0000054988263,0.00037009938,0.036608733,0.015655737,0.908315,0.026905559,0.0108934585],"study_design_scores_gemma":[0.000048078215,0.000038087484,0.000056171513,0.0000042843103,8.4443707e-7,0.0000016308836,0.000022563388,0.9177208,0.045715775,0.033893637,0.0023630052,0.0001351515],"about_ca_topic_score_codex":0.00006181394,"about_ca_topic_score_gemma":0.0000058639366,"teacher_disagreement_score":0.8956925,"about_ca_system_score_codex":0.000047636873,"about_ca_system_score_gemma":0.00006737517,"threshold_uncertainty_score":0.99269736},"labels":[],"label_agreement":null},{"id":"W2967394917","doi":"10.1145/3341216.3342210","title":"Cracking Open the Black Box","year":2019,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Interpretability; Black box; Computer science; Adaptation (eye); Path (computing); Artificial intelligence; Machine learning; Data science; Computer network","score_opus":0.03780025358261297,"score_gpt":0.30071388582548625,"score_spread":0.2629136322428733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967394917","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037343252,0.000025219655,0.42073074,0.011067142,0.0005851696,0.00063953997,2.128396e-7,0.00016933793,0.5294394],"genre_scores_gemma":[0.9651674,0.000004542276,0.00930351,0.003275,0.000043433018,0.000008964169,2.1952205e-7,0.0000068843606,0.022190047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990118,0.00005558231,0.00015792785,0.00030384221,0.00019517269,0.00027568298],"domain_scores_gemma":[0.9986704,0.0001610398,0.00004773165,0.0010039308,0.000070746115,0.000046173034],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055683666,0.00008298932,0.00009273057,0.00002894506,0.00013409264,0.00091684744,0.0036517151,0.000028828303,0.0006137587],"category_scores_gemma":[0.000042740874,0.000051860665,0.000035896508,0.00034796286,0.000043467484,0.0011490154,0.0013895738,0.00010510296,0.00939661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002440277,0.000027027454,0.001061172,0.00000344101,0.0000073385463,0.0000054700727,0.0014878872,0.00080236915,0.0012169256,0.9708531,0.008329641,0.016203186],"study_design_scores_gemma":[0.00020995049,0.00020413061,0.002235008,0.000042957075,0.0000055162936,0.000018806591,0.0026613942,0.3769224,0.17366762,0.15066676,0.29274085,0.0006246294],"about_ca_topic_score_codex":0.00038463488,"about_ca_topic_score_gemma":0.00009239407,"teacher_disagreement_score":0.92782414,"about_ca_system_score_codex":0.000025788497,"about_ca_system_score_gemma":0.000053757427,"threshold_uncertainty_score":0.9913747},"labels":[],"label_agreement":null},{"id":"W2987883180","doi":"","title":"What Does It Mean for Machine Learning to Be Trustworthy","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Trustworthiness; Artificial intelligence; Computer science; Machine learning; Data science; Computer security","score_opus":0.05817481502801922,"score_gpt":0.29600115757438034,"score_spread":0.23782634254636112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987883180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010312947,0.00006637879,0.8407401,0.14570722,0.0005519399,0.00039357832,0.0000013654644,0.0003745535,0.0018518995],"genre_scores_gemma":[0.8337099,0.000065513465,0.10334864,0.05527556,0.00032762552,0.00008123957,0.0000059869003,0.00003184636,0.007153673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857986,0.00004581805,0.00024326249,0.00051437295,0.00023096759,0.00038569918],"domain_scores_gemma":[0.9990514,0.00020091976,0.000047667516,0.0003122055,0.00011167196,0.00027613092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003081039,0.00014347975,0.00017039002,0.000060905273,0.00020343177,0.0006151591,0.00089745544,0.00004109296,0.00019331557],"category_scores_gemma":[0.00027490675,0.00010798749,0.00008328113,0.0004685565,0.000019320772,0.0012832149,0.000342647,0.00012920712,0.00027590626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012991074,0.00012809942,0.00067544373,0.000096456904,0.00007268417,0.00005742454,0.1466105,0.019258201,0.009748155,0.45232075,0.018498482,0.35240388],"study_design_scores_gemma":[0.000096553245,0.00039337852,0.000005946049,0.000014696297,0.000005084056,0.0000020410614,0.007613631,0.48915848,0.08408045,0.0033105277,0.41502374,0.0002954694],"about_ca_topic_score_codex":0.00008491221,"about_ca_topic_score_gemma":0.0011041935,"teacher_disagreement_score":0.823397,"about_ca_system_score_codex":0.000025867965,"about_ca_system_score_gemma":0.000032599964,"threshold_uncertainty_score":0.5931994},"labels":[],"label_agreement":null},{"id":"W2991989919","doi":"10.1109/tnnls.2019.2952322","title":"CHIP: Channel-Wise Disentangled Interpretation of Deep Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Computer science; Discriminative model; Artificial intelligence; Convolutional neural network; Interpretation (philosophy); Machine learning; Pattern recognition (psychology); Class (philosophy); Regularization (linguistics); Channel (broadcasting); Deep learning","score_opus":0.01118582938150223,"score_gpt":0.22867731617651488,"score_spread":0.21749148679501265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991989919","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1263591,0.0005688046,0.8694546,0.0000961569,0.002871156,0.00040792022,0.0000014121472,0.0001486893,0.000092110015],"genre_scores_gemma":[0.99923515,0.000045804456,0.000072860246,0.00008443138,0.00015390894,0.000040645333,0.0000047327185,0.000023773104,0.00033870593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783677,0.00042285564,0.0005158635,0.0004996375,0.00029556794,0.0004293137],"domain_scores_gemma":[0.99871475,0.00043495424,0.00025550852,0.00032607425,0.00012771609,0.00014099877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003689165,0.0002495284,0.00035664046,0.00016517943,0.00033102455,0.00019440074,0.00035498274,0.00014196684,0.00002053836],"category_scores_gemma":[0.000008935248,0.00023527634,0.0001446002,0.00047760407,0.00008772934,0.000579873,0.000008705458,0.0006868598,0.000014084725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007991949,0.00004992641,0.000303232,0.000032294734,0.000032665608,0.000005288804,0.00050450553,0.9817476,0.00009225316,0.00047152388,0.0000115813655,0.016669169],"study_design_scores_gemma":[0.00022805776,0.00037965708,0.0002923603,0.000091763766,0.000017801238,0.00003994263,0.0003173255,0.9982568,0.00008923703,0.00002013182,0.00003958706,0.00022733644],"about_ca_topic_score_codex":0.00016095956,"about_ca_topic_score_gemma":0.000038461876,"teacher_disagreement_score":0.87287605,"about_ca_system_score_codex":0.00005048138,"about_ca_system_score_gemma":0.000012480739,"threshold_uncertainty_score":0.9594291},"labels":[],"label_agreement":null},{"id":"W2997236691","doi":"","title":"Why Do I Trust Your Model? Building and Explaining Predictive Models for Peritoneal Dialysis Eligibility","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Accountability; Peritoneal dialysis; Health care; Transparency (behavior); Computer science; Realm; Medicine; Artificial intelligence; Machine learning; Political science; Law; Computer security; Internal medicine","score_opus":0.025356208312936335,"score_gpt":0.3226810353900463,"score_spread":0.29732482707710994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997236691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24323018,0.0007252551,0.75476074,0.0005957295,0.0003647151,0.00020835082,0.000005060371,0.000020309002,0.00008963691],"genre_scores_gemma":[0.94668716,0.000023569217,0.052938294,0.00019488377,0.00012067974,0.000005759666,0.00000120244,0.0000112067655,0.000017217588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981454,0.00010569822,0.00069347816,0.00031025845,0.0005219101,0.00022326449],"domain_scores_gemma":[0.9980005,0.0004689407,0.00045870256,0.00016248104,0.0007559132,0.00015346799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013709138,0.00016405394,0.00038200352,0.00028772,0.00022461581,0.00068557897,0.0003074105,0.00004115906,0.0000013259179],"category_scores_gemma":[0.00008965122,0.00013821587,0.000108190005,0.00018961419,0.000055079712,0.0021293696,0.00012791564,0.00015450855,9.54447e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058479898,0.000035586356,0.0012010175,0.00006047076,0.000033189364,0.0000035456492,0.0028009608,0.9663303,0.0006292322,0.023405198,0.00032191625,0.005120107],"study_design_scores_gemma":[0.00035658473,0.00015683555,0.00023367812,0.00019096422,0.000015582213,0.00012999929,0.0013133722,0.95214516,0.00009776488,0.04504649,0.00017530621,0.00013827352],"about_ca_topic_score_codex":0.000024298886,"about_ca_topic_score_gemma":3.0529006e-7,"teacher_disagreement_score":0.703457,"about_ca_system_score_codex":0.00008037779,"about_ca_system_score_gemma":0.0001093781,"threshold_uncertainty_score":0.66110533},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12844193667783704,"score_gpt":0.31858244567677824,"score_spread":0.1901405089989412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997520586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3202744,0.00017854033,0.64290315,0.028623026,0.0005717995,0.002220978,0.000032906915,0.00017124912,0.005023919],"genre_scores_gemma":[0.9985968,0.000009927445,0.000757017,0.00048902404,0.000075708434,0.00004855534,0.0000022171687,0.000011347968,0.0000094121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677557,0.00016518775,0.0012305406,0.00058663276,0.0006880831,0.000554015],"domain_scores_gemma":[0.9957877,0.00080142013,0.0010070694,0.00031484253,0.001963934,0.00012502556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013711016,0.00031023973,0.00048739277,0.00013071374,0.00039564373,0.0002830683,0.003249119,0.00013198965,0.00002691109],"category_scores_gemma":[0.0029638666,0.00021832553,0.00012794702,0.0032113947,0.000712688,0.00092542253,0.000971822,0.00093428243,0.00002026337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010834236,0.000097815006,0.00069595175,0.000025030888,0.00003470471,0.0000012322286,0.026032664,0.013353751,0.006190253,0.9390389,0.000043888667,0.014377521],"study_design_scores_gemma":[0.00003013324,0.0002450914,0.00019062785,0.00018384683,0.0000150412225,0.0000026139767,0.0063023083,0.6871855,0.2809607,0.024695951,0.000012723262,0.00017540196],"about_ca_topic_score_codex":0.00006045923,"about_ca_topic_score_gemma":0.000043824195,"teacher_disagreement_score":0.9143429,"about_ca_system_score_codex":0.000087690016,"about_ca_system_score_gemma":0.00014694556,"threshold_uncertainty_score":0.89030564},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16656570928716258,"score_gpt":0.32200664110880406,"score_spread":0.15544093182164148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000965188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19441977,0.000883113,0.7683439,0.022811007,0.00081418635,0.0013575973,0.0000221003,0.00060690864,0.01074141],"genre_scores_gemma":[0.996641,0.000035532674,0.0020052814,0.0009480364,0.00019383596,0.000087299886,0.000001917706,0.000019288282,0.0000678265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959581,0.0008141426,0.001147464,0.0006586618,0.0009327299,0.00048890075],"domain_scores_gemma":[0.99571013,0.0014489287,0.00040610498,0.0017292687,0.00052278617,0.00018278575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003230297,0.00027353424,0.00039754252,0.000061361025,0.00055894186,0.000246363,0.0033360317,0.00011170217,0.000042514817],"category_scores_gemma":[0.0013274595,0.00016971407,0.00024968607,0.0012952241,0.00037450052,0.00061405456,0.00061398844,0.00044358088,0.0003926704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008677775,0.00029046452,0.008520423,0.0005902613,0.0002216484,0.00001840057,0.050161704,0.008339814,0.015910225,0.8729082,0.0026681705,0.04028395],"study_design_scores_gemma":[0.00018226697,0.00022024623,0.004096488,0.00016667182,0.00006212161,0.00004021449,0.028909573,0.15855365,0.7814516,0.008146344,0.017310897,0.0008599282],"about_ca_topic_score_codex":0.0011448527,"about_ca_topic_score_gemma":0.0005459733,"teacher_disagreement_score":0.8647618,"about_ca_system_score_codex":0.00017106206,"about_ca_system_score_gemma":0.00017202522,"threshold_uncertainty_score":0.6920739},"labels":[],"label_agreement":null},{"id":"W3001759017","doi":"10.1037/cep0000199","title":"Performance monitoring during categorization with and without prior knowledge: A comparison of confidence calibration indices with the certainty criterion.","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Certainty; Categorization; Psychology; Calibration; Cognitive psychology; Social psychology; Statistics; Artificial intelligence; Computer science; Mathematics","score_opus":0.05784011160937338,"score_gpt":0.3243635665656008,"score_spread":0.2665234549562274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001759017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868727,0.0017146236,0.008795313,0.0015990173,0.00037812337,0.00031587662,0.000004061184,0.000021222744,0.00029909992],"genre_scores_gemma":[0.9959138,0.000024015615,0.003481378,0.00037771522,0.00013787602,0.000023925055,0.0000016464822,0.000023908571,0.000015705402],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981011,0.00015182151,0.0005338443,0.00046822717,0.000119719545,0.0006252866],"domain_scores_gemma":[0.99806136,0.000062263876,0.0005404695,0.00038986222,0.00018122535,0.0007648412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034496302,0.00025950486,0.00037504846,0.00023314689,0.00038481693,0.00013785555,0.0010264744,0.0001029271,0.000021173175],"category_scores_gemma":[0.000042102132,0.00020273413,0.000045521178,0.0005529985,0.0005085913,0.00083816,0.000050542443,0.00035856385,0.0000027744848],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006798771,0.0002242405,0.5594379,0.000117446216,0.00017131065,0.00022164734,0.14614125,0.0011553577,0.28679878,0.0013292917,0.00040741925,0.0033155002],"study_design_scores_gemma":[0.0027191732,0.0066406783,0.12403257,0.00058832037,0.00006852408,0.002028781,0.06794272,0.008910632,0.78562874,0.000105046514,0.00046444673,0.00087038917],"about_ca_topic_score_codex":0.0015012433,"about_ca_topic_score_gemma":0.008254763,"teacher_disagreement_score":0.49882993,"about_ca_system_score_codex":0.0003124147,"about_ca_system_score_gemma":0.0004312427,"threshold_uncertainty_score":0.8267258},"labels":[],"label_agreement":null},{"id":"W3004896569","doi":"10.48550/arxiv.2002.01660","title":"CHAIN: Concept-harmonized Hierarchical Inference Interpretation of Deep Convolutional Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interpretation (philosophy); Inference; Convolutional neural network; Computer science; Artificial intelligence; Machine learning","score_opus":0.07841569637209679,"score_gpt":0.22129229386010327,"score_spread":0.14287659748800646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004896569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04155156,0.00012082129,0.9559903,0.00047252118,0.0007322733,0.000360633,0.000012422438,0.00020970861,0.00054975937],"genre_scores_gemma":[0.9970567,0.00005857184,0.0023671784,0.00027187282,0.000112058355,0.000002531098,0.000041383882,0.000016599937,0.00007305903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742144,0.00036211722,0.0004605838,0.001141264,0.00017605507,0.00043856297],"domain_scores_gemma":[0.99754596,0.00049525575,0.00045741964,0.0008308994,0.0004088993,0.0002615908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022960624,0.00035099956,0.0005058087,0.00021437711,0.00013901119,0.00011292122,0.0023244075,0.00032047616,0.00007005987],"category_scores_gemma":[0.00023968473,0.00042278715,0.0002769407,0.0008060526,0.00045615342,0.0005252622,0.0023218633,0.0010131614,0.000037430622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009051619,0.00005030745,0.0004776113,0.000031124404,0.000053038144,0.000108145076,0.0008490151,0.6778023,0.000054152923,0.3176865,0.000029451481,0.0027678206],"study_design_scores_gemma":[0.00021662566,0.00010719529,0.00037023216,0.000055973378,0.000032422275,0.0000028385928,0.000109837456,0.93323374,0.00039885362,0.06510692,0.000020561449,0.0003448255],"about_ca_topic_score_codex":0.00014728661,"about_ca_topic_score_gemma":0.000040928717,"teacher_disagreement_score":0.9555052,"about_ca_system_score_codex":0.00019055286,"about_ca_system_score_gemma":0.00023659942,"threshold_uncertainty_score":0.9998224},"labels":[],"label_agreement":null},{"id":"W3010142250","doi":"10.1109/tmm.2020.2976985","title":"Feature-Flow Interpretation of Deep Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Interpretability; Computer science; Feature (linguistics); Convolutional neural network; Artificial intelligence; Interpretation (philosophy); Visualization; Representation (politics); Pattern recognition (psychology); Feature extraction; Deep learning; Machine learning; Data mining","score_opus":0.020010300986707825,"score_gpt":0.25059093384670444,"score_spread":0.2305806328599966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010142250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015918128,0.00006697641,0.99454814,0.0022785233,0.0010215605,0.00020405234,0.0000097291295,0.00016656758,0.00011265613],"genre_scores_gemma":[0.9492998,0.0000113857295,0.049795188,0.0007268764,0.00008627854,0.000024728604,0.000004060059,0.000012322736,0.000039334518],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987278,0.000089219335,0.00025776983,0.00036240206,0.00030077237,0.00026203017],"domain_scores_gemma":[0.9990062,0.0002850021,0.000098223856,0.0002753869,0.00015755082,0.00017764325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010748557,0.00016114955,0.00018840551,0.00010168214,0.000116889205,0.000049175203,0.00052072975,0.00010695349,0.00007904692],"category_scores_gemma":[0.000028819046,0.0001645196,0.00013886915,0.0005352691,0.0001079442,0.0005089553,0.000004180806,0.00034698672,0.00009850819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005342352,0.000074883625,0.000013716548,0.000008920719,0.000024110017,0.000006433646,0.0019970885,0.7858123,0.0012977152,0.00017004897,0.000184294,0.21035706],"study_design_scores_gemma":[0.00017015042,0.00016900485,0.00007328562,0.0000109001685,0.00001235161,0.0000042817105,0.000082770006,0.97687715,0.022316573,0.000071623654,0.00008902389,0.00012286617],"about_ca_topic_score_codex":0.000020120802,"about_ca_topic_score_gemma":0.00003874593,"teacher_disagreement_score":0.947708,"about_ca_system_score_codex":0.000046584846,"about_ca_system_score_gemma":0.00003657976,"threshold_uncertainty_score":0.67089146},"labels":[],"label_agreement":null},{"id":"W3012029260","doi":"10.1145/3399579.3399865","title":"Causality-based Explanation of Classification Outcomes","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Causality (physics); Classifier (UML); Outcome (game theory); Computer science; Simple (philosophy); Artificial intelligence; Machine learning; Econometrics; Mathematics; Epistemology; Mathematical economics; Philosophy","score_opus":0.15773891655686023,"score_gpt":0.3484741825097441,"score_spread":0.19073526595288387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012029260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054361406,0.00001540474,0.9742426,0.013572731,0.00056650746,0.0003581846,0.000010008178,0.00031101608,0.0054874043],"genre_scores_gemma":[0.9325115,0.0000062447025,0.06643649,0.00074950134,0.00003690603,0.000053974076,0.000047369922,0.000011397196,0.00014661762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793667,0.0001392892,0.00060784613,0.0006325906,0.0004941844,0.00018944625],"domain_scores_gemma":[0.9978569,0.0002117955,0.0004144407,0.0011147239,0.000311599,0.00009054928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042016842,0.00020835269,0.00034354362,0.00018896532,0.00005030648,0.00014124143,0.0014351053,0.00019497499,0.000045410143],"category_scores_gemma":[0.00025168966,0.00019591607,0.00014560754,0.00030868378,0.000051288018,0.0002415774,0.00056240935,0.0002874236,0.00012410627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012816732,0.00016801716,0.0076452657,0.0002927914,0.00005203203,0.000008592794,0.0009968373,0.0055805724,0.0037736478,0.97041893,0.0017240187,0.009326505],"study_design_scores_gemma":[0.000096904805,0.00006906313,0.01498616,0.000058755766,0.000019419202,4.0073604e-7,0.00018987937,0.78028506,0.11527843,0.0877329,0.0008647275,0.00041828214],"about_ca_topic_score_codex":0.00042710145,"about_ca_topic_score_gemma":0.000096549426,"teacher_disagreement_score":0.9270754,"about_ca_system_score_codex":0.00009990336,"about_ca_system_score_gemma":0.0003293897,"threshold_uncertainty_score":0.7989226},"labels":[],"label_agreement":null},{"id":"W3022244144","doi":"10.48550/arxiv.2004.14841","title":"Interpretable Random Forests via Rule Extraction","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Random forest; Extraction (chemistry); Computer science; Artificial intelligence; Mathematics; Chromatography; Chemistry","score_opus":0.08040118876147091,"score_gpt":0.21672737909158676,"score_spread":0.13632619033011584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022244144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06658792,0.00005644023,0.924917,0.000341485,0.0012187533,0.00040447045,0.0000054865136,0.00048545445,0.0059830397],"genre_scores_gemma":[0.9953733,0.00008470982,0.0025568318,0.00017579093,0.00013532207,0.0000030811746,0.000012903688,0.000025226384,0.001632848],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748003,0.00018007394,0.00031469797,0.0013901008,0.00014311331,0.00049198203],"domain_scores_gemma":[0.9977098,0.00019535197,0.00031727977,0.0012990675,0.00020500757,0.0002734736],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000309524,0.00037215633,0.0004297993,0.0002537037,0.0002192528,0.00029156683,0.0024036227,0.0003166913,0.00012222363],"category_scores_gemma":[0.00010847299,0.00044838793,0.00030254526,0.00072967366,0.000103302686,0.0011448821,0.002257126,0.0008258058,0.0007862221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005587825,0.00038878748,0.0039327745,0.00026057527,0.00034799232,0.0025717772,0.002180066,0.7141507,0.003351494,0.25669533,0.0032638882,0.01229779],"study_design_scores_gemma":[0.0002639341,0.00005200763,0.00028188407,0.00006865261,0.000043667067,0.000008703223,0.000073589574,0.7925879,0.0043843286,0.2006531,0.0011561657,0.0004260782],"about_ca_topic_score_codex":0.00057985494,"about_ca_topic_score_gemma":0.000249416,"teacher_disagreement_score":0.9287854,"about_ca_system_score_codex":0.00030925157,"about_ca_system_score_gemma":0.0002075773,"threshold_uncertainty_score":0.9999918},"labels":[],"label_agreement":null},{"id":"W3022420189","doi":"","title":"Futility of a Right to Explanation.","year":2020,"lang":"en","type":"article","venue":"EDBT/ICDT Workshops","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science","score_opus":0.03723338439552299,"score_gpt":0.27156466150983616,"score_spread":0.23433127711431317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022420189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038410973,0.00017219303,0.9254579,0.025198683,0.0006343527,0.00040691224,0.0000064301476,0.0003139409,0.009398611],"genre_scores_gemma":[0.9703579,0.000007751099,0.026595628,0.002525741,0.00020811014,0.00002561231,0.0000026651603,0.000011585496,0.00026498703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99813634,0.00008393333,0.0004360614,0.0005396068,0.0004305484,0.0003735367],"domain_scores_gemma":[0.9985028,0.00018981096,0.00010918985,0.0006767019,0.00020204688,0.00031944778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000347593,0.00016587194,0.00024889418,0.00010326589,0.00011692921,0.0001060168,0.0013251876,0.00008041525,0.00028923104],"category_scores_gemma":[0.00039609268,0.00016127384,0.00009134024,0.0014690055,0.00005458571,0.00055105553,0.00038803837,0.00018155159,0.00069587294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022029248,0.000656994,0.003553182,0.00017341076,0.00013307462,0.00023067655,0.04380928,0.01181082,0.020777848,0.45889688,0.1594144,0.30032313],"study_design_scores_gemma":[0.00050474465,0.0006602746,0.005880136,0.00018478784,0.000030028721,0.000016072621,0.002260063,0.1483106,0.59335506,0.030197768,0.21718244,0.001418038],"about_ca_topic_score_codex":0.000045347017,"about_ca_topic_score_gemma":0.00004197689,"teacher_disagreement_score":0.93194693,"about_ca_system_score_codex":0.00004828139,"about_ca_system_score_gemma":0.0000858577,"threshold_uncertainty_score":0.89442706},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03673167126332117,"score_gpt":0.3144207998614237,"score_spread":0.2776891285981025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023454035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02003059,0.000064138454,0.97867274,0.00021232234,0.00023230736,0.0005843855,0.000021465443,0.0001652518,0.000016785258],"genre_scores_gemma":[0.99618214,0.00014997927,0.0030555027,0.0004951199,0.000031656014,0.00005407043,0.000012571793,0.000013579333,0.000005365034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836785,0.00015309821,0.00050776725,0.0005226258,0.00023921259,0.00020946356],"domain_scores_gemma":[0.99888086,0.00022384693,0.00017055548,0.00024014311,0.00032888094,0.00015573516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002865717,0.0002015482,0.0002761623,0.00013851005,0.00026787326,0.00016722789,0.00024463268,0.00012741314,0.000003382819],"category_scores_gemma":[0.000020143394,0.0002082618,0.00009422078,0.0008139728,0.00018183263,0.0005953182,0.000010476186,0.000079201665,0.0000012770589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020694155,0.00018602409,0.00041313944,0.00021189584,0.000035251636,7.0371664e-7,0.0018894912,0.0046219295,0.00011036952,0.97755814,0.00005448568,0.014711615],"study_design_scores_gemma":[0.00064963894,0.00052613,0.00026381767,0.00003928711,0.000028501205,0.0000051168854,0.00026518258,0.984157,0.006865528,0.006715753,0.0002924437,0.0001915508],"about_ca_topic_score_codex":0.000029058354,"about_ca_topic_score_gemma":0.00004937401,"teacher_disagreement_score":0.9795351,"about_ca_system_score_codex":0.000035309335,"about_ca_system_score_gemma":0.00005474618,"threshold_uncertainty_score":0.849267},"labels":[],"label_agreement":null},{"id":"W3027176385","doi":"10.1002/pst.2029","title":"Investigating the appropriateness of different concordance measures in a time‐to‐event setting","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Censoring (clinical trials); Concordance; Statistic; Statistics; Comparability; Parametric statistics; Event (particle physics); Mathematics; Econometrics; Computer science; Medicine; Internal medicine","score_opus":0.08646133817187293,"score_gpt":0.3480782208862438,"score_spread":0.2616168827143709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027176385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04491257,0.00006723049,0.94778866,0.0064898725,0.000090479596,0.0004123222,0.000024689014,0.00005855154,0.00015562469],"genre_scores_gemma":[0.9504816,0.000009044712,0.046228394,0.0031604853,0.00005865377,0.00003343026,0.0000020559257,0.0000128322445,0.000013494338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978687,0.000281722,0.00053703506,0.0003489674,0.0005660398,0.00039754336],"domain_scores_gemma":[0.9983719,0.00084634696,0.00012349905,0.00023859079,0.00013173286,0.0002879201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006136419,0.00016134317,0.00024559727,0.000034776152,0.000096640724,0.00010221441,0.001088143,0.000031760464,0.000043272248],"category_scores_gemma":[0.0015981948,0.00012068419,0.000032738863,0.00055935263,0.00014066107,0.00011116886,0.00048303968,0.00030124665,0.00013962253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090104906,0.0004776324,0.020204015,0.0005105974,0.00008887471,0.00011370108,0.018359175,0.024857571,0.11024034,0.3406437,0.0032119753,0.48120233],"study_design_scores_gemma":[0.00017777186,0.00008765964,0.0017866857,0.000058151483,0.000012019714,0.000002174344,0.00009568452,0.8794835,0.104704276,0.011839337,0.0015546646,0.00019805014],"about_ca_topic_score_codex":0.00003591736,"about_ca_topic_score_gemma":0.000010080243,"teacher_disagreement_score":0.905569,"about_ca_system_score_codex":0.000057503108,"about_ca_system_score_gemma":0.000073555224,"threshold_uncertainty_score":0.49213585},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031822364545461786,"score_gpt":0.27488611181836614,"score_spread":0.24306374727290436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029534136","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027761818,0.0003730256,0.03024898,0.022316562,0.0004937121,0.0015957177,0.000056454086,0.00016055444,0.9444774],"genre_scores_gemma":[0.14257367,0.00031998532,0.008673001,0.0036053136,0.00044944815,0.00009386156,0.0007869535,0.00016773533,0.84333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997797,0.000078155805,0.00038839906,0.00078625436,0.0006014897,0.00034865914],"domain_scores_gemma":[0.99870414,0.00011116403,0.00034667616,0.00063343055,0.00009734283,0.000107243446],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005004283,0.0003614643,0.00036140528,0.00009951311,0.00020977583,0.0011067543,0.0028546152,0.00024988726,0.00023393173],"category_scores_gemma":[0.00008446374,0.0003081524,0.00010530411,0.00013600623,0.00010480217,0.00085033505,0.00072624796,0.0010728248,0.0011057875],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028745419,0.00004497775,0.00004948404,0.000033970322,0.000043465363,0.0025897108,0.004450928,0.0003526831,0.0005297341,0.63583696,0.35272765,0.0033116522],"study_design_scores_gemma":[0.00028721074,0.00033143957,0.00012194845,0.0002720075,0.000043204713,0.00012440981,0.0009716694,0.0075978586,0.0019639502,0.03655129,0.95045996,0.0012750694],"about_ca_topic_score_codex":0.00027867348,"about_ca_topic_score_gemma":0.00039530252,"teacher_disagreement_score":0.5992857,"about_ca_system_score_codex":0.000100583966,"about_ca_system_score_gemma":0.00013369901,"threshold_uncertainty_score":0.99993706},"labels":[],"label_agreement":null},{"id":"W3031116957","doi":"10.3390/jimaging6060052","title":"Explainable Deep Learning Models in Medical Image Analysis","year":2020,"lang":"en","type":"preprint","venue":"Journal of Imaging","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Nvidia","keywords":"Deep learning; Software deployment; Black box; Variety (cybernetics); Computer science; Taxonomy (biology); Data science; Artificial intelligence; Clinical Practice; Medical imaging; Medicine; Software engineering; Biology","score_opus":0.03677458504116512,"score_gpt":0.3054511353584473,"score_spread":0.2686765503172822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031116957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074140183,0.0014239389,0.97921795,0.008984708,0.0004639241,0.00009595099,4.4440992e-7,0.0000621744,0.0023368688],"genre_scores_gemma":[0.9142097,0.00040254646,0.08448773,0.00053994026,0.0002911247,0.0000057866996,0.0000020311397,0.000026183332,0.0000349305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955354,0.00040999198,0.0014486754,0.0005802848,0.001450432,0.00057526433],"domain_scores_gemma":[0.99706393,0.00029946343,0.0011124637,0.00053181587,0.0005774641,0.0004148864],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029538858,0.00031648515,0.00094820606,0.0014630961,0.00012093025,0.000720034,0.00294319,0.00015831461,0.000094348965],"category_scores_gemma":[0.0011746505,0.0003092953,0.0005748627,0.0017493918,0.00008390537,0.0018651249,0.0020905037,0.0029775098,0.000026292588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037087346,0.00017462202,0.0049030297,0.000162646,0.0005487262,0.011560544,0.010777244,0.88816386,0.00064301863,0.007450794,0.00039841307,0.075179994],"study_design_scores_gemma":[0.00012452142,0.000026485934,0.00017846187,0.00022874355,0.00010705225,0.00011444886,0.0009797992,0.95320344,0.0009607088,0.04356788,0.00023539859,0.0002730704],"about_ca_topic_score_codex":0.00025768497,"about_ca_topic_score_gemma":0.000055944514,"teacher_disagreement_score":0.90679574,"about_ca_system_score_codex":0.0003507994,"about_ca_system_score_gemma":0.00061057886,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W3035856201","doi":"10.1109/icpr48806.2021.9412303","title":"A generalizable saliency map-based interpretation of model outcome","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Artificial intelligence; Computer science; Salient; Outcome (game theory); Class (philosophy); Machine learning; Pixel; Property (philosophy); Artificial neural network; Perspective (graphical); Sensitivity (control systems); Exploit; Pattern recognition (psychology); Mathematics","score_opus":0.06865303010564977,"score_gpt":0.3259663453591399,"score_spread":0.2573133152534901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035856201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010372922,0.00017793333,0.98297983,0.0007758265,0.0008351041,0.0002983492,0.0000062401177,0.00020928474,0.0043445],"genre_scores_gemma":[0.63019335,0.0000077769855,0.3680427,0.00057419116,0.000020347063,0.000049117716,0.000023526005,0.000015696683,0.0010733028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972808,0.00012645379,0.00089014764,0.00083987584,0.0005032107,0.00035950873],"domain_scores_gemma":[0.9973072,0.00008455767,0.00036262398,0.0016280154,0.0005149181,0.0001026743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048390112,0.00029673357,0.00049212377,0.00026711027,0.000060137718,0.00032138254,0.0018508467,0.00024381827,0.00010626373],"category_scores_gemma":[0.000115808805,0.000295225,0.00028196097,0.00034233258,0.000061427294,0.0004438401,0.0015140459,0.00033469943,0.000045495657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000533506,0.000116812356,0.00028593317,0.00023849608,0.000018670322,0.000011756582,0.001133641,0.93899655,0.0011218339,0.05564784,0.00031139902,0.0021117073],"study_design_scores_gemma":[0.000045676,0.000028194903,0.000011967777,0.00010915199,0.000011806664,8.3457206e-7,0.000086320215,0.92964,0.049668882,0.020088665,0.000030088828,0.0002784237],"about_ca_topic_score_codex":0.00079262,"about_ca_topic_score_gemma":0.00019735274,"teacher_disagreement_score":0.6198204,"about_ca_system_score_codex":0.00013605057,"about_ca_system_score_gemma":0.0006154009,"threshold_uncertainty_score":0.99995},"labels":[],"label_agreement":null},{"id":"W3037129427","doi":"10.1609/aaai.v34i09.7072","title":"Model AI Assignments 2020","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Variety (cybernetics); Dissemination; Computer science; Artificial intelligence; Core (optical fiber); Multimedia; World Wide Web; Telecommunications","score_opus":0.06656900982648457,"score_gpt":0.28836224536035865,"score_spread":0.2217932355338741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037129427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013534697,0.000015509055,0.9454004,0.02727828,0.000087170236,0.000092444294,6.036225e-7,0.00028087816,0.025491245],"genre_scores_gemma":[0.9114105,0.0000056602694,0.06430666,0.02283945,0.00006302969,0.000008722655,5.7532594e-7,0.00000765807,0.0013577029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988952,0.000023677292,0.00017711653,0.00036830397,0.00026938177,0.00026630904],"domain_scores_gemma":[0.9993547,0.000024537374,0.000030256982,0.000327535,0.00005422429,0.0002087042],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009227155,0.00009965081,0.000100033656,0.00001935133,0.000080710255,0.00016782696,0.0009500681,0.000037294005,0.00014551668],"category_scores_gemma":[0.00005236423,0.00009081956,0.00004409351,0.00035336553,0.000021208296,0.0007503602,0.0003361964,0.00011090128,0.0018025958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010394461,0.00010192124,0.00051120104,0.000014475171,0.000021877348,0.000078034005,0.0030592948,0.052823227,0.019811073,0.77364314,0.12055344,0.02937192],"study_design_scores_gemma":[0.000035482146,0.00004448794,0.000015058592,0.0000017747234,0.0000012177128,0.0000011092286,0.00004138356,0.9431054,0.0378408,0.01580609,0.002990836,0.000116343304],"about_ca_topic_score_codex":0.000017252109,"about_ca_topic_score_gemma":0.00000459708,"teacher_disagreement_score":0.91005707,"about_ca_system_score_codex":0.000025313173,"about_ca_system_score_gemma":0.000062953804,"threshold_uncertainty_score":0.9989746},"labels":[],"label_agreement":null},{"id":"W3037201993","doi":"","title":"Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Identifiability; Interpretability; Representation (politics); Piecewise; Equivalence (formal languages); Computer science; Decomposition; Algorithm; Additive model; Mathematics; Generalized additive model; Function (biology); Variance (accounting); Artificial intelligence; Machine learning; Discrete mathematics","score_opus":0.14353834344966945,"score_gpt":0.3268560395712488,"score_spread":0.18331769612157936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037201993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018939285,0.000015394753,0.9919799,0.0034539413,0.00088219513,0.0005424264,0.00017168903,0.00010211761,0.00095842744],"genre_scores_gemma":[0.8687044,0.000052060343,0.12915331,0.0013109569,0.0003754653,0.00018126336,0.00009276494,0.000026624388,0.00010316404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777514,0.00011467401,0.00043398104,0.0007323374,0.00057914545,0.00036471433],"domain_scores_gemma":[0.99751097,0.00096277037,0.00022600325,0.00026870013,0.000844119,0.00018745183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040284978,0.00027505882,0.00021914665,0.0001275944,0.00047072192,0.0009824126,0.00072513206,0.00007283016,0.00007987482],"category_scores_gemma":[0.00028070653,0.00021920429,0.000051002637,0.00028764055,0.00018460865,0.0009374534,0.00014596073,0.00030524938,0.00006740236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015485966,0.00008677662,0.0000013021264,0.00001142232,0.000040455787,0.00001612679,0.0014913463,0.0411347,0.00070810557,0.6192497,0.00024160853,0.3368636],"study_design_scores_gemma":[0.000052746847,0.00063490955,0.000012094106,0.000055101285,0.0000154907,0.0000130291255,0.0020727057,0.8983718,0.01758007,0.08050831,0.0004300656,0.0002536547],"about_ca_topic_score_codex":0.000073030096,"about_ca_topic_score_gemma":0.000096516815,"teacher_disagreement_score":0.86681044,"about_ca_system_score_codex":0.0000922828,"about_ca_system_score_gemma":0.00013526884,"threshold_uncertainty_score":0.94734275},"labels":[],"label_agreement":null},{"id":"W3037211332","doi":"10.1609/aaai.v34i09.7116","title":"Explaining Image Classifiers Generating Exemplars and Counter-Exemplars from Latent Representations","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":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Horizon 2020 Framework Programme","keywords":"Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology); Machine learning; Set (abstract data type); Class (philosophy); Counterfactual thinking; Decision tree; Autoencoder; Feature (linguistics); Coherence (philosophical gambling strategy); Fidelity; Probabilistic latent semantic analysis; Mathematics; Artificial neural network; Linguistics; Psychology","score_opus":0.10787770024118251,"score_gpt":0.3035250152619264,"score_spread":0.19564731502074387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037211332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7214613,0.00007680805,0.23647545,0.03707185,0.00062750495,0.000833151,0.000035169684,0.00031008842,0.0031087014],"genre_scores_gemma":[0.97147214,0.0000896541,0.027060946,0.0010988805,0.00015141649,0.000049914554,0.0000026580537,0.000028561348,0.000045810986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99657243,0.000046918638,0.00097342394,0.0010905489,0.00073351973,0.0005831444],"domain_scores_gemma":[0.9976664,0.0002881578,0.000585449,0.00044998812,0.0007104042,0.000299601],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005135915,0.00038622308,0.00043025787,0.00013393469,0.0007476867,0.00091195863,0.0021732822,0.00014022358,0.00009698142],"category_scores_gemma":[0.0010588598,0.00033366607,0.00014908993,0.0009103239,0.00048240137,0.001334387,0.0008710848,0.00053610955,0.00012801902],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008925709,0.000100184516,0.0007236928,0.00004170634,0.000047533817,0.000008176293,0.016405918,0.00034522332,0.44985667,0.5029858,0.00087783515,0.028518014],"study_design_scores_gemma":[0.000038598562,0.00018670877,0.00012506185,0.00015826395,0.000022034317,0.0000053805393,0.0046794326,0.32036433,0.610562,0.063403614,0.000097344106,0.00035722458],"about_ca_topic_score_codex":0.00030845724,"about_ca_topic_score_gemma":0.00004998404,"teacher_disagreement_score":0.43958217,"about_ca_system_score_codex":0.00009786113,"about_ca_system_score_gemma":0.0001272032,"threshold_uncertainty_score":0.99991155},"labels":[],"label_agreement":null},{"id":"W3037467471","doi":"","title":"Optimization Methods for Interpretable Differentiable Decision Trees Applied to Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Differentiable function; Artificial intelligence; Computer science; Decision tree; Machine learning; Mathematical optimization; Mathematics","score_opus":0.11948672140957296,"score_gpt":0.38912509464424233,"score_spread":0.2696383732346694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037467471","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001309084,0.000010593565,0.99269545,0.0024769048,0.00046052405,0.00056027033,0.000022376213,0.00012461872,0.0035183402],"genre_scores_gemma":[0.4270589,0.000063121886,0.57148075,0.0010144113,0.00008501841,0.0000863987,0.000034362725,0.00001539456,0.00016164467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976686,0.00009265255,0.00071377214,0.00073002087,0.00040018396,0.00039475813],"domain_scores_gemma":[0.9976984,0.0009778774,0.00019080908,0.00025889723,0.00057329866,0.00030069178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053331954,0.00027774094,0.0003048142,0.00021073427,0.00028281022,0.00080019183,0.00094803976,0.000088485176,0.00035564604],"category_scores_gemma":[0.0016692198,0.0002769208,0.000056171237,0.0003408766,0.00007679058,0.00036105773,0.00033200142,0.00022143069,0.0001444947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018941938,0.000030766198,0.0000034804982,0.0000068972313,0.000017290413,0.0000014476235,0.0009758162,0.23897114,0.0024299077,0.505233,0.00018459959,0.25195622],"study_design_scores_gemma":[0.00004207273,0.00053563964,0.000004470387,0.000042625685,0.000009797623,0.0000013492912,0.0006850243,0.8677044,0.024634844,0.10415313,0.0019160123,0.00027067712],"about_ca_topic_score_codex":0.000028522612,"about_ca_topic_score_gemma":0.00002941455,"teacher_disagreement_score":0.6287332,"about_ca_system_score_codex":0.00007642848,"about_ca_system_score_gemma":0.00008293344,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"W3040426486","doi":"10.1007/s43154-020-00013-6","title":"From Humans and Back: a Survey on Using Machine Learning to both Socially Perceive Humans and Explain to Them Robot Behaviours","year":2020,"lang":"en","type":"article","venue":"Current Robotics Reports","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut interdisciplinaire d'innovation technologique; Université de Sherbrooke","funders":"","keywords":"Perception; Robot; Artificial intelligence; Social robot; Computer science; Human–robot interaction; Human–computer interaction; Psychology; Mobile robot; Robot control","score_opus":0.14616403047979462,"score_gpt":0.33764906646268544,"score_spread":0.19148503598289082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040426486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6589366,0.0001686388,0.33835635,0.0011640853,0.00065842614,0.00049390056,0.000016813197,0.00012517812,0.00007999281],"genre_scores_gemma":[0.96790737,0.000034305343,0.031203544,0.00044242895,0.00023457721,0.000009057262,0.00004566905,0.00004670841,0.000076331686],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970087,0.00024297826,0.00060739776,0.0011185476,0.000496493,0.0005259133],"domain_scores_gemma":[0.998327,0.00018819739,0.00025335787,0.0004925161,0.00016459671,0.00057431654],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006547653,0.00034772637,0.00043416876,0.00011993513,0.00047896453,0.00052196934,0.00039682497,0.00008767547,0.000042839943],"category_scores_gemma":[0.0004432561,0.00036283632,0.00006912669,0.00044112367,0.00007107432,0.00031069625,0.00065878575,0.0004268617,0.00005104243],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009350787,0.0005425153,0.45527425,0.00007614296,0.00009867497,0.0011530572,0.11553939,0.38108963,0.010207802,0.003579745,0.0018395826,0.030505698],"study_design_scores_gemma":[0.0009149398,0.0026775878,0.45722714,0.0014320948,0.0002888766,0.00018460075,0.0049531506,0.50494576,0.011182281,0.0071697384,0.0036354582,0.005388388],"about_ca_topic_score_codex":0.0021591336,"about_ca_topic_score_gemma":0.0012508339,"teacher_disagreement_score":0.30897078,"about_ca_system_score_codex":0.0001202143,"about_ca_system_score_gemma":0.00013485519,"threshold_uncertainty_score":0.99988234},"labels":[],"label_agreement":null},{"id":"W3041420828","doi":"10.1007/978-3-030-50788-6_14","title":"Knowledge-to-Information Translation Training (KITT): An Adaptive Approach to Explainable Artificial Intelligence","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Training (meteorology); Translation (biology)","score_opus":0.10456046355613227,"score_gpt":0.2954454831840099,"score_spread":0.19088501962787766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041420828","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042900283,0.00007715257,0.98026556,0.0011020605,0.001252049,0.0014353622,0.000009574156,0.00036892167,0.015446413],"genre_scores_gemma":[0.28785512,0.000004692277,0.70943564,0.0019473992,0.00057857396,0.00007082823,0.000017401442,0.000043573844,0.000046780337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994292,0.000098600736,0.0011787801,0.0020442696,0.0012553801,0.0011309567],"domain_scores_gemma":[0.9964801,0.00040684,0.0003064053,0.0013840371,0.0006473903,0.0007752245],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016693645,0.0007735711,0.00072191615,0.0017594713,0.00057700824,0.0014216481,0.00454777,0.00038774445,0.000015073029],"category_scores_gemma":[0.00025708994,0.0008144176,0.0001558523,0.002640794,0.00035447185,0.0040247366,0.00092217134,0.00096824166,0.0006262786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027895232,0.00003676357,2.8738407e-7,0.00002558214,0.0000051070683,0.000009867719,0.027075566,0.19987051,0.00013177273,0.14791359,0.0000053977133,0.62489766],"study_design_scores_gemma":[0.000034371453,0.0007406061,0.000003183489,0.00020647288,0.000007142876,0.000020271844,0.00005251123,0.81222355,0.007975871,0.17663679,0.0012564535,0.0008427913],"about_ca_topic_score_codex":0.000057676454,"about_ca_topic_score_gemma":0.00016999016,"teacher_disagreement_score":0.62405485,"about_ca_system_score_codex":0.00059241813,"about_ca_system_score_gemma":0.0010070289,"threshold_uncertainty_score":0.99961495},"labels":[],"label_agreement":null},{"id":"W3041899234","doi":"10.1109/itsc45102.2020.9294213","title":"Explainability of Intelligent Transportation Systems using Knowledge Compilation: a Traffic Light Controller Case","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Air Force Office of Scientific Research; Office of Naval Research; Division of Electrical, Communications and Cyber Systems; Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"Controller (irrigation); Computer science; State (computer science); Black box; Representation (politics); Control (management); Traffic signal; Intelligent transportation system; Action (physics); Real-time computing; Control engineering; Artificial intelligence; Transport engineering; Engineering; Programming language","score_opus":0.10116194188333054,"score_gpt":0.3258268616807003,"score_spread":0.22466491979736974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041899234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13899305,0.000998291,0.8551108,0.0005033057,0.0014683445,0.0017829661,0.00004812621,0.00033964482,0.00075545016],"genre_scores_gemma":[0.98894227,0.000020710404,0.010585789,0.00003592658,0.00017632532,0.00010319857,0.000029312301,0.000030424995,0.00007602823],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957435,0.0004092595,0.0017308982,0.0012114783,0.00047177452,0.00043306997],"domain_scores_gemma":[0.9966881,0.00030603935,0.0006985666,0.0010713236,0.0009739923,0.0002619549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008711906,0.00050390407,0.0010205383,0.00028904734,0.00019227824,0.00028409,0.0011585056,0.00037468804,0.000038577324],"category_scores_gemma":[0.00010410181,0.0004904964,0.0003861187,0.00071120186,0.00011302711,0.00044735134,0.00028990296,0.00056131056,0.000046175464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010387148,0.00068511016,0.00017158431,0.0022378115,0.00023010108,0.0008853805,0.03519128,0.8376321,0.0014516963,0.11187469,0.00034860187,0.009187759],"study_design_scores_gemma":[0.0001716104,0.00009435979,0.000031267627,0.00023125991,0.000070725706,0.00009990989,0.0019341839,0.98538995,0.008608337,0.0021156957,0.00076564524,0.00048703895],"about_ca_topic_score_codex":0.00073332945,"about_ca_topic_score_gemma":0.00045696466,"teacher_disagreement_score":0.84994924,"about_ca_system_score_codex":0.00036355125,"about_ca_system_score_gemma":0.0005181269,"threshold_uncertainty_score":0.99975467},"labels":[],"label_agreement":null},{"id":"W3042234123","doi":"10.48550/arxiv.2007.09028","title":"Sequential Explanations with Mental Model-Based Policies","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Computer science; Reinforcement learning; Proxy (statistics); Representation (politics); Selection (genetic algorithm); Mental representation; Baseline (sea); Machine learning; Artificial intelligence; Mental model; Cognitive psychology; Data science; Psychology; Cognitive science; Cognition","score_opus":0.14897382185708133,"score_gpt":0.2217217124871226,"score_spread":0.07274789063004128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042234123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08714627,0.00001134926,0.907462,0.0014441366,0.00023750814,0.00032409516,0.000041200532,0.00038524068,0.0029482034],"genre_scores_gemma":[0.99244076,0.000018139885,0.0064218906,0.00046548666,0.00006035351,0.0000029457467,0.000041481453,0.000022136159,0.0005268203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981014,0.00009269375,0.000193091,0.0010378683,0.00017050828,0.0004044296],"domain_scores_gemma":[0.9983643,0.000054427062,0.00019313555,0.0009671346,0.00018406523,0.00023688971],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010867125,0.00032567358,0.00027154054,0.00028479367,0.0002899538,0.00024045505,0.0019678306,0.0001705166,0.000029203713],"category_scores_gemma":[0.000018271818,0.0003607061,0.00015294488,0.0007337222,0.0001807666,0.00053733174,0.0011707572,0.00045725686,0.00013423905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028466091,0.0000613558,0.00019044931,0.000024323135,0.000045081393,0.00018049705,0.0010502625,0.7275623,0.0001707579,0.270207,0.00040911775,0.00007038725],"study_design_scores_gemma":[0.00016967188,0.00007127098,0.000024621997,0.00004362644,0.000039038867,0.0000025194079,0.00021080447,0.95984703,0.004613407,0.034332253,0.00024196254,0.0004037821],"about_ca_topic_score_codex":0.0004903715,"about_ca_topic_score_gemma":0.00029516252,"teacher_disagreement_score":0.9052945,"about_ca_system_score_codex":0.00032434217,"about_ca_system_score_gemma":0.00062785763,"threshold_uncertainty_score":0.9998845},"labels":[],"label_agreement":null},{"id":"W3042974867","doi":"10.1016/j.artint.2021.103503","title":"Toward personalized XAI: A case study in intelligent tutoring systems","year":2021,"lang":"en","type":"preprint","venue":"Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Personalization; Computer science; Context (archaeology); Constraint (computer-aided design); Perception; Intelligent tutoring system; Value (mathematics); Cognition; Human–computer interaction; World Wide Web; Psychology; Machine learning","score_opus":0.19535364336425445,"score_gpt":0.36216192382724816,"score_spread":0.1668082804629937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042974867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42960706,0.0022389435,0.55810726,0.00037356428,0.006158232,0.002550744,0.000009436049,0.0004914535,0.00046330367],"genre_scores_gemma":[0.9920617,0.0002528371,0.005732002,0.00013140136,0.000568956,0.000866484,0.000014754235,0.00010448253,0.00026740492],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9888144,0.0013281876,0.0031417836,0.0034205208,0.0015549883,0.0017401183],"domain_scores_gemma":[0.99344754,0.0008187037,0.00077600783,0.0034081442,0.0010087336,0.0005408448],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032231489,0.0012417786,0.0016534234,0.0011215202,0.0004407057,0.0035812834,0.0041319295,0.0006912538,0.0001414938],"category_scores_gemma":[0.00090835115,0.0013753561,0.0005466761,0.0024897668,0.0003286798,0.001136629,0.0050131506,0.0024780836,0.0004394885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014757206,0.005953325,0.0032715988,0.0009929003,0.00053417264,0.17554851,0.25619686,0.2035496,0.0010126597,0.1947969,0.00009730096,0.1578986],"study_design_scores_gemma":[0.000111378475,0.00064260955,0.000054296277,0.0013308111,0.00012905318,0.0035849812,0.2576248,0.6766872,0.03476988,0.021364238,0.0005548911,0.0031458642],"about_ca_topic_score_codex":0.030589614,"about_ca_topic_score_gemma":0.0075322995,"teacher_disagreement_score":0.56245464,"about_ca_system_score_codex":0.0011668409,"about_ca_system_score_gemma":0.0011579603,"threshold_uncertainty_score":0.9998232},"labels":[],"label_agreement":null},{"id":"W3045760512","doi":"10.2196/19428","title":"Retracted: An Artificial Intelligence Fusion Model for Cardiac Emergency Decision Making: Application and Robustness Analysis","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":true,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Hebei North University","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Machine learning; Data mining","score_opus":0.05238497331964575,"score_gpt":0.3476675299301252,"score_spread":0.2952825566104794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045760512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081166156,0.000028285973,0.91689676,0.0008346445,0.0001622518,0.0006144465,0.000010632428,0.00018019385,0.000106599786],"genre_scores_gemma":[0.82108843,0.000087610155,0.17797357,0.00049410394,0.00016536097,0.00013963762,0.0000334851,0.000012403498,0.0000054108987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969149,0.000049417868,0.0012102203,0.00037657752,0.0010421838,0.00040666485],"domain_scores_gemma":[0.99797785,0.00020917624,0.0003173129,0.0006128994,0.00033663795,0.0005461497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010041501,0.00022292568,0.0003946528,0.00023040755,0.00026649772,0.00018858816,0.0011323008,0.0003244927,0.00004245684],"category_scores_gemma":[0.00051383494,0.00020443207,0.0001605668,0.001778325,0.00008861102,0.0014457579,0.00038124085,0.00035659104,0.000029668248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072067196,0.00013995665,0.00017834926,0.00013949566,0.000072905845,0.0000024628366,0.016948245,0.08503493,0.00015433556,0.06757904,0.0005092354,0.829169],"study_design_scores_gemma":[0.000027651327,0.000112345886,0.00005897046,0.000019945688,0.000054642795,0.0000013323705,0.0012750544,0.9856116,0.00049719197,0.01183495,0.00026144035,0.00024486947],"about_ca_topic_score_codex":0.0000065562504,"about_ca_topic_score_gemma":0.000028808752,"teacher_disagreement_score":0.90057665,"about_ca_system_score_codex":0.000045718298,"about_ca_system_score_gemma":0.0001279025,"threshold_uncertainty_score":0.83364975},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.17972663068993538,"score_gpt":0.3685186475705217,"score_spread":0.18879201688058633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046399757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015696835,0.0003138099,0.97761583,0.003193222,0.00026016336,0.001549843,0.00001220279,0.00032380546,0.0010342689],"genre_scores_gemma":[0.7376114,0.000045831377,0.26041466,0.0008906846,0.00047143738,0.0002582273,0.000009080054,0.00006227568,0.00023637751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99468845,0.0006508476,0.0008682264,0.0016734458,0.0008148083,0.0013042397],"domain_scores_gemma":[0.9951158,0.0019147267,0.00022867462,0.0008131237,0.0014675999,0.0004600619],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024005906,0.00048065974,0.00055026845,0.00057694386,0.0014503134,0.0012410644,0.001857038,0.00013305274,0.000056605473],"category_scores_gemma":[0.0004816451,0.00044998855,0.000108132735,0.0030571083,0.0006165734,0.0012560362,0.0013371188,0.00076047814,0.00014265269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010282915,0.00030734885,0.000058139325,0.00023560975,0.00015213051,0.00038397915,0.016501652,0.0071888994,0.004254138,0.722998,0.008020342,0.23887144],"study_design_scores_gemma":[0.00014338878,0.0043829805,0.000026847514,0.0002504231,0.000018959128,0.000047891575,0.0045846943,0.69666195,0.2171628,0.06611322,0.009756108,0.0008507131],"about_ca_topic_score_codex":0.0000543879,"about_ca_topic_score_gemma":0.0000652866,"teacher_disagreement_score":0.7219146,"about_ca_system_score_codex":0.00015648257,"about_ca_system_score_gemma":0.0005217457,"threshold_uncertainty_score":0.9998497},"labels":[],"label_agreement":null},{"id":"W3046415660","doi":"10.1007/978-3-030-49100-0_25","title":"Explainable AI for the Operating Theater","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; St. Michael's Hospital; Public Safety Canada","funders":"","keywords":"Workflow; Computer science; Software deployment; Representation (politics); Data science; Artificial intelligence; Management science; Software engineering; Engineering; Database","score_opus":0.05611421029647499,"score_gpt":0.2754389539326332,"score_spread":0.2193247436361582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046415660","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.7158023e-7,0.00020986912,0.5571682,0.01378326,0.0003804378,0.0006321566,0.0000037436407,0.00017889575,0.42764318],"genre_scores_gemma":[0.0031968297,0.000064754684,0.025327343,0.014955008,0.0007155205,0.00019329198,0.0000077725235,0.00008282795,0.9554567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814194,0.000016666505,0.00040927524,0.00069949316,0.00031453092,0.0004180804],"domain_scores_gemma":[0.99808294,0.0004724241,0.00010777705,0.0009885165,0.00024149453,0.00010687853],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037908636,0.0003496376,0.00030925986,0.000064252934,0.00055973,0.00073494023,0.002029629,0.00018117344,0.0004268864],"category_scores_gemma":[0.00007260462,0.00022372007,0.00021708835,0.00006119207,0.00007752407,0.00050217385,0.0006073669,0.0003736459,0.0009488568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003092416,0.0000038817225,3.3547352e-7,0.000020691095,0.00003384209,0.000014596547,0.0004528424,0.0001956357,0.00006388687,0.9625542,0.022622598,0.014034412],"study_design_scores_gemma":[0.00005121526,0.000127136,1.7118487e-7,0.00004265935,0.00001827679,0.000008941635,0.00010997069,0.098796286,0.005967209,0.15970768,0.73480076,0.00036968093],"about_ca_topic_score_codex":0.00005997799,"about_ca_topic_score_gemma":0.00004027351,"teacher_disagreement_score":0.8028465,"about_ca_system_score_codex":0.000066776905,"about_ca_system_score_gemma":0.00014882277,"threshold_uncertainty_score":0.999829},"labels":[],"label_agreement":null},{"id":"W3049119636","doi":"10.7202/1070751ar","title":"Mesure d’impact d’une variable binaire sur une réponse quantitative dans un cadre non paramétrique","year":2020,"lang":"fr","type":"article","venue":"Assurances et gestion des risques","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Mathematics; Philosophy; Physics","score_opus":0.07028396679511847,"score_gpt":0.3247555292614408,"score_spread":0.2544715624663223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049119636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19335757,0.007991394,0.6413846,0.14632393,0.0012857243,0.0009143351,0.00019671416,0.00062161963,0.007924124],"genre_scores_gemma":[0.95980376,0.0029326463,0.034040313,0.0012118473,0.00022790578,0.00007551605,0.000037526253,0.00007593861,0.0015945381],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936353,0.002022705,0.001021199,0.0013373476,0.0007938876,0.0011895575],"domain_scores_gemma":[0.9948678,0.0019880994,0.00054729934,0.0007975411,0.0011806921,0.00061858125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018994549,0.0007853725,0.0008969934,0.00018973865,0.0007306898,0.0009376855,0.0013358633,0.0005242997,0.00019111788],"category_scores_gemma":[0.0024085743,0.0007778024,0.00033598355,0.0044351188,0.0008915409,0.0046840254,0.00026171163,0.0010054022,0.0005858855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006567793,0.000822116,0.010678679,0.0007725987,0.0005820659,0.0009760751,0.11118083,0.65308505,0.011202839,0.11720793,0.029947445,0.06288758],"study_design_scores_gemma":[0.00055264385,0.0025672605,0.05074609,0.00137002,0.0001584715,0.00013550493,0.0040811147,0.83385015,0.06224722,0.033625137,0.009288779,0.0013776217],"about_ca_topic_score_codex":0.040393375,"about_ca_topic_score_gemma":0.0048099984,"teacher_disagreement_score":0.7664462,"about_ca_system_score_codex":0.0003995979,"about_ca_system_score_gemma":0.0007662312,"threshold_uncertainty_score":0.9994673},"labels":[],"label_agreement":null},{"id":"W3049425455","doi":"10.1111/exsy.12621","title":"Visual interpretation of regression error","year":2020,"lang":"en","type":"article","venue":"Expert Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia; Canada Research Chairs","keywords":"Computer science; Machine learning; Black box; Context (archaeology); Artificial intelligence; Visualization; Reliability (semiconductor); Regression; Interpretation (philosophy); Regression analysis; Point (geometry); Data mining; Data science; Statistics","score_opus":0.048962434098616815,"score_gpt":0.33237532759424937,"score_spread":0.28341289349563253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049425455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029710222,0.001061128,0.9638608,0.0015743314,0.0011144788,0.00026111328,7.7922397e-7,0.00020041039,0.0022167463],"genre_scores_gemma":[0.99746335,0.000007614658,0.0018899911,0.000345947,0.00015725875,0.000022422497,0.0000012766021,0.000008745771,0.00010341065],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876726,0.00011882685,0.00036384302,0.00028912732,0.00029389883,0.00016705717],"domain_scores_gemma":[0.99928194,0.00007058769,0.00016034587,0.00027013966,0.000113399255,0.000103563274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016709523,0.00010503621,0.00019700605,0.00005580638,0.00005572195,0.000075587785,0.0005581649,0.000053993826,0.000013222212],"category_scores_gemma":[0.00012928326,0.00008616186,0.000056063433,0.00032598633,0.000029617773,0.00049148896,0.00014311718,0.00006685252,0.00016370749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022158201,0.00033639354,0.0009920897,0.00044396368,0.000090160975,0.00012226353,0.2069019,0.006402556,0.51978517,0.13849235,0.03772769,0.08848387],"study_design_scores_gemma":[0.000057227062,0.00018520343,0.000020152072,0.0001331999,0.0000010032402,0.000004801072,0.0021256101,0.88486814,0.10799422,0.000084714135,0.0044068205,0.00011890816],"about_ca_topic_score_codex":0.000200048,"about_ca_topic_score_gemma":0.000002800058,"teacher_disagreement_score":0.9677531,"about_ca_system_score_codex":0.00003124338,"about_ca_system_score_gemma":0.000036126872,"threshold_uncertainty_score":0.35135788},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Transparency (behavior); Acknowledgement; Vision; Artificial intelligence; European union; Data science; Computer security","score_opus":0.1208874855785112,"score_gpt":0.36651958890720737,"score_spread":0.24563210332869617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081090156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010802377,0.008046805,0.9749053,0.006341897,0.00047560144,0.0011008881,0.000004522512,0.00023149422,0.008882677],"genre_scores_gemma":[0.41001683,0.009434678,0.57449925,0.002256391,0.0025327539,0.00041389145,0.000015039381,0.0001665583,0.00066459004],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99342364,0.00013075057,0.00084899686,0.0027247807,0.0017138727,0.0011579689],"domain_scores_gemma":[0.9950729,0.0015767631,0.00023773314,0.001854556,0.00078285503,0.000475172],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002812716,0.00058190105,0.00063719094,0.0012191959,0.00093026244,0.0010006401,0.004545227,0.0004506537,0.000036430814],"category_scores_gemma":[0.0003671487,0.0005774387,0.000106733336,0.0013503213,0.0023326527,0.0009737153,0.0032522709,0.0017831371,0.00037418774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037769976,0.000022818365,7.4235174e-7,0.00004324704,0.000004360481,0.000048424852,0.002053023,0.0012347754,0.00009102057,0.47923562,0.000008761949,0.51725346],"study_design_scores_gemma":[0.000026096153,0.0002681743,0.0000050297963,0.00025785825,0.000004227491,0.000035496985,0.00003089611,0.15261942,0.005756201,0.8322422,0.008196787,0.00055759575],"about_ca_topic_score_codex":0.000027885117,"about_ca_topic_score_gemma":0.00010556876,"teacher_disagreement_score":0.51669586,"about_ca_system_score_codex":0.00036442874,"about_ca_system_score_gemma":0.0008136214,"threshold_uncertainty_score":0.9996677},"labels":[],"label_agreement":null},{"id":"W3090729135","doi":"10.1109/ijcnn48605.2020.9207648","title":"Improved Policy Extraction via Online Q-Value Distillation","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Distillation; Artificial neural network; Decision tree; Function (biology); Artificial intelligence; Monte Carlo tree search; Machine learning; Value (mathematics); Monte Carlo method; Algorithm; Mathematics","score_opus":0.03551764141124086,"score_gpt":0.3154533688888263,"score_spread":0.27993572747758544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090729135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010126417,0.000014614843,0.9660599,0.020205116,0.00016638929,0.00015038463,0.000001633695,0.00038133236,0.0028942132],"genre_scores_gemma":[0.94845176,0.00000836716,0.048019055,0.0027508887,0.00045452637,0.0000045449437,0.0000065475297,0.000009000972,0.000295338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894047,0.00004015702,0.0002435478,0.00035662673,0.00017894914,0.00024027847],"domain_scores_gemma":[0.9993094,0.000059570084,0.00007853638,0.00030194543,0.00009079315,0.00015970928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009771966,0.000110585825,0.00010293496,0.00007187396,0.00010501668,0.00012675852,0.000427796,0.000052046184,0.000050829498],"category_scores_gemma":[0.00021205968,0.0001032813,0.00005095169,0.0006937854,0.000023837838,0.0008544032,0.00013461718,0.000113712056,0.00024832136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022644826,0.00014811775,0.00023169174,0.000023715062,0.000016100483,0.0000141509245,0.001750133,0.0038110653,0.21435867,0.41929698,0.00074861065,0.35957813],"study_design_scores_gemma":[0.00004979276,0.00009990095,0.00066806085,0.00000235147,0.0000021600886,0.0000053701647,0.000071305985,0.92954946,0.059133396,0.005803814,0.004479447,0.00013494254],"about_ca_topic_score_codex":0.000822856,"about_ca_topic_score_gemma":0.000086070846,"teacher_disagreement_score":0.9383253,"about_ca_system_score_codex":0.000071665534,"about_ca_system_score_gemma":0.00008070082,"threshold_uncertainty_score":0.42116892},"labels":[],"label_agreement":null},{"id":"W3091240018","doi":"10.1109/ijcnn48605.2020.9207559","title":"Locality Guided Neural Networks for Explainable Artificial Intelligence","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Locality; Computer science; Artificial intelligence; Deep learning; Artificial neural network; Convolutional neural network; Layer (electronics); Network topology; Topology (electrical circuits); Pattern recognition (psychology); Computer network; Mathematics","score_opus":0.12413100787788897,"score_gpt":0.31864002262455227,"score_spread":0.1945090147466633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091240018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011802226,0.00007703022,0.9809128,0.014088111,0.000566756,0.00069131935,0.0000023661419,0.00061300665,0.0018683706],"genre_scores_gemma":[0.92977744,0.000008449354,0.062376387,0.0069925245,0.0005173294,0.0001148032,0.000006038081,0.000025655669,0.0001813494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697673,0.00010558247,0.0007626233,0.0009234191,0.0003408409,0.0008907965],"domain_scores_gemma":[0.99800104,0.00036480193,0.00014231792,0.0007320097,0.00034406057,0.00041578093],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006511872,0.00029216916,0.00033281735,0.00006905054,0.00037432616,0.00048387065,0.0018708938,0.00013286373,0.0001326037],"category_scores_gemma":[0.0005508328,0.00027946732,0.000191802,0.0010171038,0.000121250945,0.001076927,0.0004935528,0.00023537628,0.00019623818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005034978,0.00008032468,0.000045304994,0.000036866273,0.000015617334,0.000026990367,0.00079182937,0.13131505,0.0004424693,0.7607816,0.0058584395,0.100555144],"study_design_scores_gemma":[0.000033220105,0.0002278517,0.000005081051,0.000005950949,0.0000058091186,0.000005801235,0.0004411777,0.9061742,0.042511027,0.046733093,0.0035337291,0.0003230965],"about_ca_topic_score_codex":0.00013055836,"about_ca_topic_score_gemma":0.000045194898,"teacher_disagreement_score":0.9285973,"about_ca_system_score_codex":0.000070173126,"about_ca_system_score_gemma":0.000083763385,"threshold_uncertainty_score":0.9999657},"labels":[],"label_agreement":null},{"id":"W3091797093","doi":"10.2196/18752","title":"Explainable Artificial Intelligence Recommendation System by Leveraging the Semantics of Adverse Childhood Experiences: Proof-of-Concept Prototype Development","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Semantics (computer science); Recommender system; Expert system; Applications of artificial intelligence; Chatbot","score_opus":0.03754824203812151,"score_gpt":0.2783566048046656,"score_spread":0.2408083627665441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091797093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047219314,0.000022103746,0.9486075,0.0016490268,0.00023541698,0.0014517857,0.0000029526527,0.00011057989,0.0007012911],"genre_scores_gemma":[0.97464997,0.0000035020344,0.024308464,0.0006140923,0.000054751858,0.00033695775,0.000014164459,0.000011034486,0.0000070840956],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996534,0.000106757565,0.0016707613,0.00022129236,0.001057019,0.0004101748],"domain_scores_gemma":[0.99824846,0.00018835532,0.000677201,0.00040796152,0.0002224079,0.00025559033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089736294,0.00022154172,0.0003479453,0.000069823844,0.00022904399,0.000054468783,0.0015788322,0.00013746628,0.00019177231],"category_scores_gemma":[0.000359742,0.00016460584,0.00007453609,0.0009238973,0.0002593896,0.00093822693,0.0005387488,0.00033876894,0.00004642208],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003366709,0.00029382895,0.00004392835,0.00081483176,0.00004722425,0.000006668304,0.6654268,0.0009968553,0.000048654627,0.01739908,0.0012026067,0.3136859],"study_design_scores_gemma":[0.00008641379,0.00033023334,0.0000051317215,0.0003723338,0.000007677524,0.000012577033,0.16439041,0.47444084,0.3546147,0.0003197487,0.005130832,0.00028908413],"about_ca_topic_score_codex":0.000016263673,"about_ca_topic_score_gemma":0.0000028319703,"teacher_disagreement_score":0.9274306,"about_ca_system_score_codex":0.00009041,"about_ca_system_score_gemma":0.00045424234,"threshold_uncertainty_score":0.67124313},"labels":[],"label_agreement":null},{"id":"W3094897300","doi":"10.2478/jdis-2020-0027","title":"Global Collaboration in Artificial Intelligence: Bibliometrics and Network Analysis from 1985 to 2019","year":2020,"lang":"en","type":"article","venue":"Journal of Data and Information Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Social network analysis; Bibliometrics; China; Institution; Field (mathematics); Political science; Regional science; Library science; Social science; Public relations; Sociology; Computer science; Social capital","score_opus":0.0638513092071118,"score_gpt":0.359537235449634,"score_spread":0.2956859262425222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094897300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12745713,0.0001403457,0.8671218,0.0048215548,0.00019309949,0.000087121116,0.000056890753,0.000008413225,0.000113628346],"genre_scores_gemma":[0.9330258,0.00032400026,0.06490885,0.0016384571,0.00008966189,5.127801e-7,0.000011379783,9.4333456e-7,4.1321323e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803686,0.00003674669,0.00077626784,0.00020937994,0.00073434797,0.00020637139],"domain_scores_gemma":[0.9983485,0.00011576,0.00037953825,0.00031876468,0.0005530319,0.00028441157],"candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0021538269,0.000081096456,0.00019979858,0.0024670092,0.00014646571,0.0015414857,0.0015241356,0.000035075143,0.000007127929],"category_scores_gemma":[0.0012705111,0.00007106471,0.00001695486,0.05542158,0.00010304632,0.026851393,0.00071386766,0.00009697939,0.00001860981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117078474,0.000052227027,0.032779675,0.000014651378,0.000058487247,0.000014073517,0.011609702,0.10400442,0.00044219123,0.086832754,0.0043468513,0.7597279],"study_design_scores_gemma":[0.000050195584,0.00019595928,0.021539774,0.000015068641,0.000024389117,0.000006368989,0.0017988636,0.96521527,0.000576231,0.0047458964,0.0056877215,0.0001442432],"about_ca_topic_score_codex":0.00008557155,"about_ca_topic_score_gemma":0.00007757976,"teacher_disagreement_score":0.8612109,"about_ca_system_score_codex":0.000055740507,"about_ca_system_score_gemma":0.00029250508,"threshold_uncertainty_score":0.999495},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.14686940195410675,"score_gpt":0.37902970762359456,"score_spread":0.2321603056694878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095556657","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1496728e-7,0.9336433,0.033257294,0.02318684,0.0035927652,0.0035139453,0.00006088417,0.0004673574,0.002277298],"genre_scores_gemma":[0.000022203503,0.97933406,0.00888743,0.0068480587,0.0020067587,0.002146295,0.00018757295,0.00020277109,0.0003648719],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98946977,0.0014670987,0.0031992763,0.0035005736,0.00067219784,0.0016911031],"domain_scores_gemma":[0.99397266,0.00039701143,0.001751882,0.0028252173,0.0002764417,0.00077678316],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0016203009,0.0017703307,0.004476831,0.0004351908,0.00059561373,0.0009656321,0.0048597977,0.00066629285,0.0021332458],"category_scores_gemma":[0.00032297158,0.001737555,0.0015959541,0.0018698754,0.00040116988,0.00034239737,0.0008769582,0.001515654,0.015785873],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012058584,0.00027718302,2.558168e-8,0.009701151,0.00014719015,0.00020404365,0.00010868867,0.0000017644425,0.000017448145,0.019780561,0.04698987,0.92276],"study_design_scores_gemma":[0.00003568893,0.00028292244,1.6760024e-8,0.020533256,0.0003923595,0.00036306056,0.000076389966,0.000099120116,0.0005335456,0.003046277,0.97303855,0.0015987962],"about_ca_topic_score_codex":0.000036094698,"about_ca_topic_score_gemma":0.000016307442,"teacher_disagreement_score":0.9260487,"about_ca_system_score_codex":0.00050395826,"about_ca_system_score_gemma":0.0006173485,"threshold_uncertainty_score":0.9995042},"labels":[],"label_agreement":null},{"id":"W3100210912","doi":"","title":"What went wrong and when? Instance-wise feature importance for time-series black-box models","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Black box; Computer science; Series (stratigraphy); Feature (linguistics); Time series; Artificial intelligence; Machine learning","score_opus":0.03220889811413114,"score_gpt":0.24985837122618623,"score_spread":0.2176494731120551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100210912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018856855,0.0027121913,0.95820004,0.015883926,0.00097368174,0.0015416689,0.000014819298,0.00066060456,0.0011562282],"genre_scores_gemma":[0.98394245,0.00012449372,0.011567601,0.0031667382,0.00023635931,0.00017889537,0.000033531556,0.000023063047,0.0007268808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983821,0.000032721335,0.000584995,0.00029453565,0.0003604891,0.0003451909],"domain_scores_gemma":[0.9987018,0.00003998518,0.00043698447,0.00026013778,0.0003952058,0.00016587238],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0002508543,0.00022140772,0.000262987,0.000082524675,0.00032802098,0.0030073675,0.00050812965,0.000105429586,0.0000022597483],"category_scores_gemma":[0.00007487495,0.00019961127,0.000046516096,0.00034478362,0.00007844336,0.031017758,0.000119366465,0.00015591989,0.0000368999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045934916,0.000087272056,0.0004893107,0.008891777,0.00007911778,0.000025366846,0.24079253,0.24743673,0.0027608217,0.1369243,0.048941772,0.31311163],"study_design_scores_gemma":[0.00015452299,0.00010900242,0.0000074318073,0.00019345152,0.000005529763,0.000018117113,0.0034040597,0.97880137,0.0018268607,0.0016793271,0.01355661,0.0002437403],"about_ca_topic_score_codex":0.000007217142,"about_ca_topic_score_gemma":0.000004711445,"teacher_disagreement_score":0.96508557,"about_ca_system_score_codex":0.00006173403,"about_ca_system_score_gemma":0.00009636896,"threshold_uncertainty_score":0.9980276},"labels":[],"label_agreement":null},{"id":"W3103399673","doi":"10.22215/etd/2016-11247","title":"Complex Fan Analysis : an Extension of ACT-R Fan Effect Model","year":2016,"lang":"fy","type":"dissertation","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inference; Task (project management); Computer science; Process (computing); Artificial intelligence; Extension (predicate logic); Cognition; Natural language processing; Psychology; Engineering","score_opus":0.056398373074924686,"score_gpt":0.35231872620233473,"score_spread":0.29592035312741005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103399673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33501473,0.000056708737,0.65601146,0.00012967193,0.00039889407,0.0005979712,0.000029422043,0.00015228566,0.007608853],"genre_scores_gemma":[0.9781434,0.00006325438,0.013399937,0.00013009598,0.00009152521,0.000035969304,0.00056832633,0.000056529603,0.0075109764],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937778,0.0006524359,0.0014528789,0.0019165071,0.0012525698,0.0009477996],"domain_scores_gemma":[0.99387425,0.0005469617,0.0010029324,0.0028200909,0.0013063555,0.0004494367],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014404152,0.0008429146,0.0016393784,0.0014815558,0.00047456217,0.00032216648,0.0025421658,0.0005899308,0.0005973432],"category_scores_gemma":[0.00023336319,0.0006586968,0.0009171407,0.002659904,0.00019485573,0.0014216823,0.0002978209,0.00037347357,0.0006880383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062685594,0.0010076229,0.00290422,0.0005864862,0.0019117816,0.000066276676,0.013280553,0.04809204,0.62763953,0.05788504,0.0004900869,0.24550949],"study_design_scores_gemma":[0.00013842364,0.000659753,0.0034623954,0.00014205558,0.00070406136,0.0000018495834,0.0005162901,0.7837498,0.20730941,0.002597821,0.000038539507,0.0006795841],"about_ca_topic_score_codex":0.0022021958,"about_ca_topic_score_gemma":0.0039559663,"teacher_disagreement_score":0.7356578,"about_ca_system_score_codex":0.00016058498,"about_ca_system_score_gemma":0.0003217347,"threshold_uncertainty_score":0.9995864},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3509394530848094,"score_gpt":0.43152788481715193,"score_spread":0.08058843173234254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103420222","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11822044,0.012081351,0.042680487,0.8228038,0.00015721888,0.0012337936,0.00000509302,0.00053235074,0.0022854533],"genre_scores_gemma":[0.89518946,0.0009203814,0.095837794,0.000552265,0.000104742125,0.0003308315,0.00005189404,0.000017015393,0.0069955983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987392,0.000041228694,0.00018613928,0.0004180533,0.000241518,0.00037388876],"domain_scores_gemma":[0.9990303,0.00021559744,0.000033593853,0.00015482277,0.0003717381,0.00019397879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053019694,0.00009857199,0.00012039796,0.00031899317,0.0009578986,0.00011963498,0.00038032833,0.00008509934,0.000034167926],"category_scores_gemma":[0.0004993132,0.000094261755,0.000008049541,0.00044671216,0.00031013187,0.00017893635,0.00048005246,0.0003396172,0.000031116044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009978734,0.000087648994,0.0055728485,0.00003422893,0.000024371517,0.00000845718,0.0026531054,0.000004536254,0.0012037194,0.90027124,0.0038269837,0.08630287],"study_design_scores_gemma":[0.00028849518,0.0007722107,0.001572295,0.000054718952,0.0000024166543,0.000050194445,0.008369099,0.0034386732,0.013515779,0.47534448,0.49620992,0.0003817085],"about_ca_topic_score_codex":0.000029391847,"about_ca_topic_score_gemma":0.00002312815,"teacher_disagreement_score":0.82225156,"about_ca_system_score_codex":0.00004732027,"about_ca_system_score_gemma":0.0005928637,"threshold_uncertainty_score":0.73674786},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.038588597743119256,"score_gpt":0.2735726670442438,"score_spread":0.23498406930112456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103654318","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012833545,0.0017252753,0.30228418,0.6731539,0.0008941618,0.0003806759,0.0000024531923,0.002305985,0.0064198505],"genre_scores_gemma":[0.9806342,0.000113269896,0.006776264,0.012273799,0.00012620885,0.000038082737,6.0241854e-7,0.000015376749,0.00002216596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981984,0.000038255686,0.0003416703,0.00078848604,0.00021122597,0.0004219618],"domain_scores_gemma":[0.9984968,0.000059611033,0.00009240818,0.0010837928,0.0001300337,0.00013738521],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012603667,0.00020128349,0.00026439887,0.0002148892,0.000111129804,0.00019506134,0.0023544445,0.00020495465,0.00009495865],"category_scores_gemma":[0.00016718535,0.00020464316,0.00010391641,0.00140765,0.0002723244,0.001511453,0.0010052898,0.00038051596,0.001666988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010771493,0.00007200827,0.00048943015,0.000025569796,0.000026025496,0.000052076168,0.0026489443,0.000014497229,0.003699548,0.9151726,0.0006869787,0.0771016],"study_design_scores_gemma":[0.00006876555,0.00028563046,0.000008839144,0.000027690028,0.0000052504706,0.000015696978,0.00022386765,0.014575411,0.11798881,0.8490345,0.017510919,0.0002546534],"about_ca_topic_score_codex":0.000009126576,"about_ca_topic_score_gemma":0.0000024865942,"teacher_disagreement_score":0.9678007,"about_ca_system_score_codex":0.000052970645,"about_ca_system_score_gemma":0.00004523287,"threshold_uncertainty_score":0.99911034},"labels":[],"label_agreement":null},{"id":"W3103683805","doi":"","title":"Algorithmic recourse under imperfect causal knowledge: a probabilistic approach","year":2020,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Counterfactual thinking; Probabilistic logic; Imperfect; Computer science; Causal model; Causal structure; Bayesian network; Bayesian probability; Probability distribution; Mathematical optimization; Theoretical computer science; Artificial intelligence; Machine learning; Mathematics","score_opus":0.03002586498763677,"score_gpt":0.2315503291181706,"score_spread":0.20152446413053385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103683805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061873193,0.00011104126,0.98690814,0.0026833315,0.00016738217,0.00058570644,0.00021134203,0.00091663277,0.0022291262],"genre_scores_gemma":[0.7932457,0.000106329455,0.2007292,0.0005263682,0.0003986892,0.00009151619,0.002011167,0.0000777729,0.0028132568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827486,0.00007392912,0.00021861936,0.0007463979,0.00021999402,0.00046619985],"domain_scores_gemma":[0.9981075,0.00012441375,0.00007404396,0.000981534,0.00023342669,0.0004790623],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024666192,0.0002434705,0.00019606568,0.00028691973,0.0002517841,0.00020510236,0.0013057176,0.00006488327,0.0000128036645],"category_scores_gemma":[0.0002447996,0.00029103344,0.00008670498,0.0017368611,0.00006224902,0.0016243431,0.0005833399,0.0002567148,0.0002641634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012843597,0.0005693667,0.0000762087,0.00013031575,0.00011490857,0.000050471906,0.0004071466,0.029439908,0.0019932205,0.9114485,0.05430385,0.0014532558],"study_design_scores_gemma":[0.0002469655,0.00006990555,0.0002798049,0.000012938235,0.000041610056,0.000024919338,0.00017283297,0.88086337,0.0011444811,0.0000076106703,0.1167205,0.0004150631],"about_ca_topic_score_codex":0.000029136505,"about_ca_topic_score_gemma":0.000004050286,"teacher_disagreement_score":0.9114409,"about_ca_system_score_codex":0.0003813116,"about_ca_system_score_gemma":0.00029793844,"threshold_uncertainty_score":0.99995416},"labels":[],"label_agreement":null},{"id":"W3105320009","doi":"","title":"Causal Discovery in Physical Systems from Videos","year":2020,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Computer science; Causal structure; Inference; Graph; Causal model; Causal inference; Perception; Representation (politics); Artificial intelligence; Machine learning; Ground truth; Theoretical computer science; Mathematics; Psychology","score_opus":0.027142591720973906,"score_gpt":0.25797024902581395,"score_spread":0.23082765730484003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105320009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5141511,0.00027541205,0.4767111,0.0066745845,0.00069013523,0.00045646177,0.0000955314,0.0006799194,0.0002657527],"genre_scores_gemma":[0.98732126,0.000026305388,0.012153196,0.00020717712,0.00015269953,0.00008410987,0.000012176197,0.000024075685,0.00001900763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728936,0.000050054026,0.0007458291,0.0009021821,0.00041585512,0.00059669133],"domain_scores_gemma":[0.99837255,0.000067214096,0.00026346807,0.0009924491,0.000116646646,0.0001876934],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023228851,0.00033594336,0.0006791278,0.0004975013,0.00010467238,0.00012442739,0.0022359341,0.00038574962,0.0000046454375],"category_scores_gemma":[0.00050355244,0.00032157515,0.00013351381,0.0024681329,0.0004962017,0.0011396414,0.00088202034,0.0007001066,0.00032629305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065379136,0.00040161243,0.0033371798,0.00014799381,0.00008706468,0.00054661225,0.0009598242,0.008277838,0.08505912,0.87858593,0.00065628457,0.02187515],"study_design_scores_gemma":[0.0006405006,0.00051340024,0.00019352941,0.00037452273,0.000044014378,0.000022387892,0.0007425329,0.4471961,0.42635947,0.07464517,0.048237238,0.001031139],"about_ca_topic_score_codex":0.00053993287,"about_ca_topic_score_gemma":0.000059420032,"teacher_disagreement_score":0.8039408,"about_ca_system_score_codex":0.00013285906,"about_ca_system_score_gemma":0.00018536192,"threshold_uncertainty_score":0.99992365},"labels":[],"label_agreement":null},{"id":"W3112004508","doi":"10.20381/ruor-25786","title":"Interpretability for Deep Learning Text Classifiers","year":2020,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Ottawa","keywords":"Interpretability; Artificial intelligence; Deep learning; Machine learning; Natural language processing; Computer science; Data science","score_opus":0.07087409241126696,"score_gpt":0.33986685176276665,"score_spread":0.2689927593514997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112004508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039123334,0.000208622,0.73892003,0.004332943,0.0009817472,0.0023887965,0.00002529994,0.00042060707,0.21359862],"genre_scores_gemma":[0.9331817,0.00016324334,0.029767584,0.000032792268,0.00009851289,0.000008917285,0.0002186997,0.00004890085,0.03647965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969556,0.00042553514,0.00024135956,0.00085310685,0.00089581317,0.0006285996],"domain_scores_gemma":[0.99687356,0.0008707056,0.00021720945,0.00062369934,0.0011463426,0.00026849148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015109328,0.00020092659,0.00039839593,0.00056305894,0.0007274192,0.00013218627,0.0028259386,0.00030918987,0.00019100806],"category_scores_gemma":[0.0013713489,0.000261882,0.00027717685,0.0011070481,0.00027344938,0.0006913707,0.00040683895,0.0011362885,0.00020458238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019031062,0.00031711868,0.0029386436,0.001884816,0.00027955117,0.00014956314,0.0479405,0.00035796684,0.006897547,0.52589697,0.008317089,0.40482992],"study_design_scores_gemma":[0.0006022426,0.001912231,0.005007789,0.00034443446,0.0000590183,0.0000029990642,0.104422174,0.4224989,0.01776282,0.021584677,0.42474607,0.0010566416],"about_ca_topic_score_codex":0.00019228164,"about_ca_topic_score_gemma":0.002306132,"teacher_disagreement_score":0.89405835,"about_ca_system_score_codex":0.00028470033,"about_ca_system_score_gemma":0.000430068,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W3112198773","doi":"10.1016/j.eswa.2022.117230","title":"When stakes are high: Balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates","year":2022,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"Categorical variable; Computer science; Feature selection; Black box; Surrogate model; Feature engineering; Generalized linear model; Transparency (behavior); Decision tree; Machine learning; Segmentation; Gradient boosting; Artificial intelligence; Data mining; Boosting (machine learning); Variable (mathematics); Random forest; Mathematics; Deep learning","score_opus":0.040064940698052554,"score_gpt":0.26870500282512394,"score_spread":0.2286400621270714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112198773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007116789,0.0012916967,0.9882406,0.0011671464,0.00007849275,0.0012890045,0.00014447393,0.00030450086,0.00036727855],"genre_scores_gemma":[0.97000194,0.000040097206,0.026214853,0.00013219808,0.000053446856,0.0032529184,0.00008110264,0.000030916322,0.00019253117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774116,0.00011026393,0.0003848296,0.00090184633,0.0004611769,0.0004006972],"domain_scores_gemma":[0.99727607,0.0003591878,0.0002564984,0.0018036044,0.000147131,0.00015751128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027500614,0.00023945108,0.0003073811,0.00012133989,0.00081227586,0.0003351327,0.001832061,0.000034126788,0.000020288186],"category_scores_gemma":[0.000028903476,0.00019804717,0.000018446968,0.00049689796,0.000089497546,0.001172013,0.0004308057,0.00020404135,0.000016395647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092281065,0.0005487482,0.0066353977,0.00025523614,0.00021758219,0.000053864864,0.034350008,0.8197378,0.0026179235,0.1252365,0.0062653203,0.003989368],"study_design_scores_gemma":[0.00020967973,0.00015751435,0.00009975537,0.00012555209,0.000021428154,0.0000896441,0.005087747,0.98233426,0.0004883041,0.0008090085,0.010154775,0.00042235275],"about_ca_topic_score_codex":0.0017797991,"about_ca_topic_score_gemma":0.00055251736,"teacher_disagreement_score":0.96288514,"about_ca_system_score_codex":0.00011948115,"about_ca_system_score_gemma":0.0001758978,"threshold_uncertainty_score":0.8076129},"labels":[],"label_agreement":null},{"id":"W3114997257","doi":"10.1007/978-3-030-65847-2_3","title":"Superimposition: Augmenting Machine Learning Outputs with Conceptual Models for Explainable AI","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; HEC Montréal","funders":"","keywords":"Superimposition; Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Mathematics","score_opus":0.034230608920964446,"score_gpt":0.25495340429432556,"score_spread":0.22072279537336112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114997257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005703608,0.0005541271,0.9929135,0.00247265,0.0006284315,0.00087838876,0.0000091630845,0.00034262484,0.0021441078],"genre_scores_gemma":[0.4678721,0.000029191602,0.5267231,0.0037979498,0.0006236732,0.00007836779,0.000030550975,0.000096387805,0.0007486834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99510306,0.000054213582,0.0006712917,0.0020655363,0.0010603378,0.0010455456],"domain_scores_gemma":[0.9973368,0.0005732714,0.00033627893,0.0009067508,0.00055409246,0.00029279597],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008460571,0.00068997,0.0007147325,0.00052529445,0.0008334944,0.0010722919,0.0026184036,0.00027707705,0.000020910917],"category_scores_gemma":[0.00011463641,0.00063419744,0.00016404584,0.00071382255,0.00084724004,0.0020131385,0.0011801698,0.0011258563,0.00003592864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043186305,0.000031673153,0.000024674697,0.0000878091,0.000024887844,0.000177476,0.0045264154,0.5484955,0.0005061543,0.36838502,0.00001802898,0.077679224],"study_design_scores_gemma":[0.00024431877,0.0007331063,9.353836e-7,0.0002975629,0.0000122668325,0.000058699745,0.0000050668605,0.86901855,0.010512154,0.11628764,0.002115586,0.0007141034],"about_ca_topic_score_codex":0.00006196155,"about_ca_topic_score_gemma":0.00006739993,"teacher_disagreement_score":0.46781507,"about_ca_system_score_codex":0.00037761152,"about_ca_system_score_gemma":0.00067505596,"threshold_uncertainty_score":0.9999647},"labels":[],"label_agreement":null},{"id":"W3117721506","doi":"10.18653/v1/2020.coling-main.286","title":"RANCC: Rationalizing Neural Networks via Concept Clustering","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Alberta Machine Intelligence Institute","keywords":"Computer science; Cluster analysis; Artificial intelligence; Artificial neural network; Feature (linguistics); Feature extraction; Machine learning; Natural language processing","score_opus":0.04073720661813371,"score_gpt":0.2615254019216346,"score_spread":0.22078819530350088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117721506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063515565,0.0001277121,0.98610425,0.009891534,0.00038487354,0.00013367186,2.0060436e-7,0.000335636,0.0023869413],"genre_scores_gemma":[0.9643653,0.000003309315,0.022148505,0.013012959,0.00032884927,0.000008868058,0.0000019692036,0.000009525582,0.000120724224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880797,0.00005742555,0.00025827944,0.00036034785,0.0002029551,0.00031303472],"domain_scores_gemma":[0.99935436,0.00010349183,0.00005591584,0.00025052254,0.000075322256,0.00016038233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011943544,0.00012098992,0.00013034792,0.000026239986,0.00016321574,0.0002351378,0.0006954366,0.00004372329,0.00016646522],"category_scores_gemma":[0.00004940312,0.00011674672,0.00005759727,0.0004076717,0.000040071754,0.0011079558,0.0003181784,0.00013890851,0.00012340503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013789797,0.000020450425,0.00020905663,0.000009346716,0.000014985008,0.00005430244,0.0026416,0.8105965,0.0024913931,0.107570715,0.0042416914,0.07213612],"study_design_scores_gemma":[0.0000677059,0.000045477685,0.00003328229,0.0000033710526,0.0000014428316,0.000006973718,0.000078356294,0.99117315,0.0054398207,0.0005946244,0.0024092488,0.00014657198],"about_ca_topic_score_codex":0.000052053445,"about_ca_topic_score_gemma":0.000020873418,"teacher_disagreement_score":0.96395576,"about_ca_system_score_codex":0.000022905504,"about_ca_system_score_gemma":0.00002057612,"threshold_uncertainty_score":0.47607931},"labels":[],"label_agreement":null},{"id":"W3121407777","doi":"10.1117/12.2581362","title":"Uncertainty aware and explainable diagnosis of retinal disease","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Nvidia","keywords":"Computer science; Artificial intelligence; Posterior probability; Bayesian probability; Dropout (neural networks); Machine learning; Deep learning; Segmentation; Macular degeneration; Bayes' theorem; Medicine; Ophthalmology","score_opus":0.03147320254809458,"score_gpt":0.27700022505941774,"score_spread":0.24552702251132316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121407777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39508566,0.0035205807,0.5889518,0.0057421685,0.0014653348,0.00097373826,0.00003516328,0.00039919207,0.003826321],"genre_scores_gemma":[0.9833028,0.0008610372,0.01442259,0.00027186092,0.000073535215,0.00023157123,0.000026524356,0.000019036366,0.00079108117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973264,0.00017226319,0.0005244636,0.0010635407,0.00047360163,0.00043973964],"domain_scores_gemma":[0.9971095,0.00031309802,0.00023877912,0.0015195255,0.00048082456,0.00033827184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004455814,0.000324094,0.00046856987,0.00016388294,0.00014118783,0.0004251935,0.0012920841,0.00017321257,0.0002241661],"category_scores_gemma":[0.0003813644,0.00031655477,0.0001731389,0.0003571316,0.00015976554,0.0004217842,0.0038702972,0.0003866579,0.000012692479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002236033,0.0023174703,0.16741116,0.0076297806,0.0005045071,0.003537567,0.016141845,0.094258405,0.00029949535,0.55904454,0.021131774,0.12749983],"study_design_scores_gemma":[0.00047982731,0.00041925942,0.016937036,0.0033004265,0.00023438084,0.000037765076,0.0088849915,0.72442555,0.07021156,0.16263497,0.009011251,0.0034230135],"about_ca_topic_score_codex":0.0017875955,"about_ca_topic_score_gemma":0.00021002706,"teacher_disagreement_score":0.6301671,"about_ca_system_score_codex":0.00009805055,"about_ca_system_score_gemma":0.00053159945,"threshold_uncertainty_score":0.99992865},"labels":[],"label_agreement":null},{"id":"W3124177705","doi":"10.1609/aimag.v41i4.7383","title":"Place Your Bets: Will Machine Learning Outgrow Human Labeling?","year":2020,"lang":"en","type":"article","venue":"AI Magazine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Craft; Artificial intelligence; Computer science; Machine learning; Data science; Art; Visual arts","score_opus":0.038125017079584385,"score_gpt":0.28694597779414976,"score_spread":0.2488209607145654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124177705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107512414,0.0017797563,0.7387246,0.12679446,0.0009070657,0.000789066,0.000017035713,0.0031040784,0.020371562],"genre_scores_gemma":[0.97654444,0.000029736551,0.01012011,0.009234263,0.00035554825,0.000013941416,0.000018602525,0.000043632186,0.003639711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790215,0.000116414325,0.00039848947,0.000648508,0.00039333355,0.00054108165],"domain_scores_gemma":[0.99885213,0.00008523812,0.00013172858,0.00049451814,0.00016112311,0.00027528714],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035223408,0.0002515379,0.00027525602,0.000095795076,0.00033967628,0.00028004844,0.0012235596,0.00008378115,0.00022582832],"category_scores_gemma":[0.0003376565,0.00025247654,0.000087380715,0.00073045696,0.00006392371,0.0010269188,0.0005693266,0.00055498345,0.0024056174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015221017,0.0007318189,0.03191009,0.00035308837,0.0002683368,0.0015007599,0.03039495,0.038899895,0.3117096,0.40802786,0.08552895,0.09052242],"study_design_scores_gemma":[0.0006095684,0.0009852392,0.00054211967,0.00006319125,0.000027996633,0.000031809377,0.00019689287,0.56220984,0.033846743,0.007488006,0.3930196,0.0009789952],"about_ca_topic_score_codex":0.000079998186,"about_ca_topic_score_gemma":0.00007180841,"teacher_disagreement_score":0.869032,"about_ca_system_score_codex":0.000050544877,"about_ca_system_score_gemma":0.00005021371,"threshold_uncertainty_score":0.9999927},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.44533367302389276,"score_gpt":0.44675477312989736,"score_spread":0.0014211001060046025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125340956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4258285,0.001148443,0.563968,0.00058387534,0.0007030542,0.0004989257,0.0000015609627,0.00012279603,0.0071448334],"genre_scores_gemma":[0.91180634,0.00009697664,0.087799795,0.000057121717,0.000058547506,0.000012242137,0.0000012108455,0.000011050228,0.00015672018],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99524826,0.00029845786,0.00058886973,0.0009880553,0.0017398477,0.0011365362],"domain_scores_gemma":[0.9971406,0.0010221417,0.000073650735,0.0005012864,0.0008709335,0.0003914236],"candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0063352813,0.0001665677,0.00022302454,0.0041238577,0.00045484508,0.0018655912,0.0011044566,0.0001061077,0.000026675922],"category_scores_gemma":[0.0036927965,0.00018558354,0.000033994926,0.036449064,0.00027891767,0.0011991512,0.0011087817,0.0006624271,0.00009653334],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002841876,0.000053122632,0.003937588,0.000019187277,0.0000050750505,0.00017466037,0.0037697495,0.0006089016,0.0037508337,0.15712315,0.000013396907,0.8305415],"study_design_scores_gemma":[0.00020089508,0.00018124617,0.0062795705,0.00030863628,0.0000050740746,0.0002667342,0.049925268,0.11072734,0.6967097,0.13247816,0.001856644,0.001060734],"about_ca_topic_score_codex":0.00023027649,"about_ca_topic_score_gemma":0.00027157794,"teacher_disagreement_score":0.82948077,"about_ca_system_score_codex":0.00029225147,"about_ca_system_score_gemma":0.0014052644,"threshold_uncertainty_score":0.99917054},"labels":[],"label_agreement":null},{"id":"W3130627855","doi":"10.1177/1071181320641073","title":"Abstraction Hierarchy Based Explainable Artificial Intelligence","year":2020,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Loan; Hierarchy; Abstraction; Context (archaeology); Computer science; Quality (philosophy); Set (abstract data type); Domain (mathematical analysis); Process (computing); Artificial intelligence; Cognition; Test (biology); Perception; Psychology; Knowledge management; Finance; Business; Epistemology; Political science","score_opus":0.04355932228892601,"score_gpt":0.2529781301734863,"score_spread":0.2094188078845603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130627855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98857385,0.00004202549,0.008759645,0.0015303609,0.00015812134,0.00022398063,0.0000070105975,0.000117683514,0.0005873421],"genre_scores_gemma":[0.99166024,0.000017034326,0.0077590146,0.00037533283,0.00014050795,0.000008275692,0.0000010224086,0.000017425828,0.000021141128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835217,0.000012213128,0.0005118084,0.00049023126,0.00024010101,0.0003934842],"domain_scores_gemma":[0.998914,0.00012751238,0.0003999057,0.00013973365,0.00026517583,0.0001536691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005233025,0.00022823113,0.0002520336,0.000036453603,0.0007846836,0.0002995776,0.0009710842,0.000115771814,0.000007186935],"category_scores_gemma":[0.00021894074,0.00018916535,0.0002230311,0.00038399117,0.00020888673,0.0010834889,0.00047739022,0.00034297456,0.000004355552],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016505294,0.00040483256,0.02430808,0.0011447114,0.00018037825,0.0000015189646,0.15221639,0.008224,0.2689812,0.52743524,0.0030004287,0.01393819],"study_design_scores_gemma":[0.00008061578,0.00025262736,0.0023079487,0.00015040873,0.000028719907,0.0000018579757,0.036191043,0.12677157,0.8104422,0.02216744,0.0010419643,0.0005635828],"about_ca_topic_score_codex":0.00012009681,"about_ca_topic_score_gemma":0.000005031221,"teacher_disagreement_score":0.54146105,"about_ca_system_score_codex":0.000080242484,"about_ca_system_score_gemma":0.000050779498,"threshold_uncertainty_score":0.7713939},"labels":[],"label_agreement":null},{"id":"W3132215508","doi":"10.48550/arxiv.2102.07799","title":"Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Convolutional neural network; Machine learning; Artificial neural network; Interpretation (philosophy); Backpropagation","score_opus":0.1338579434810109,"score_gpt":0.22655431502542606,"score_spread":0.09269637154441515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132215508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19177692,0.0001704982,0.8064954,0.00006458156,0.0008256167,0.00044341254,0.000016739921,0.00008862832,0.0001182007],"genre_scores_gemma":[0.99280435,0.00003909446,0.006808428,0.000056909776,0.00010405242,0.000005242987,0.000057951842,0.000017099459,0.00010687415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978,0.00014984397,0.00038601324,0.001063895,0.00016053722,0.00043972261],"domain_scores_gemma":[0.9973711,0.00047538395,0.0004512479,0.0007865603,0.0007866275,0.00012908001],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040510585,0.0002927929,0.0004053107,0.00029119535,0.00021998108,0.00011337622,0.0012334316,0.0002652967,0.000017124987],"category_scores_gemma":[0.00011388674,0.0003673653,0.00029735776,0.00071781955,0.00014085793,0.00031882513,0.0012175965,0.00039879116,0.0000054909888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044842003,0.00009105813,0.00019310962,0.000056131976,0.00007138218,0.00003708641,0.00029688797,0.8434791,0.000068578396,0.1551596,0.00003056709,0.00047168374],"study_design_scores_gemma":[0.00018658268,0.00007514727,0.00030955064,0.00013739555,0.00006783421,0.0000037072157,0.00045460105,0.99080765,0.0010083704,0.0065977694,0.000018964169,0.00033242907],"about_ca_topic_score_codex":0.00021621183,"about_ca_topic_score_gemma":0.00011815177,"teacher_disagreement_score":0.8010274,"about_ca_system_score_codex":0.00029900865,"about_ca_system_score_gemma":0.0002974297,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W3133174645","doi":"","title":"Neural Disjunctive Normal Form: Vertically Integrating Logic With Deep Learning For Classification","year":2021,"lang":"en","type":"article","venue":"Summit (Simon Fraser University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Interpretability; Disjunctive normal form; Artificial intelligence; Artificial neural network; Computer science; Deep learning; Conjunctive normal form; Inductive logic programming; Classifier (UML); Representation (politics); Deep neural networks; Machine learning; Theoretical computer science; Algorithm","score_opus":0.02546261787081183,"score_gpt":0.23309179048196207,"score_spread":0.20762917261115024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133174645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0892267,0.000024074081,0.9032725,0.0007480203,0.00013915011,0.00020412475,0.0000015604629,0.00017510656,0.0062087243],"genre_scores_gemma":[0.9794568,0.000009780833,0.019016197,0.0001921493,0.000040740324,0.000003916659,0.00002194879,0.000013321857,0.0012451601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849296,0.00012158173,0.00017245475,0.000546425,0.00022755795,0.0004390388],"domain_scores_gemma":[0.9986094,0.00026109582,0.00010756954,0.00036054145,0.00052074593,0.00014060015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014885493,0.00018155141,0.00017733681,0.00017265171,0.00048392068,0.00018343922,0.0006228713,0.00009169572,0.00002395015],"category_scores_gemma":[0.00020999959,0.00017573006,0.000096170785,0.0011021057,0.0000977008,0.0014222538,0.00021137662,0.000293892,0.00003284423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040239154,0.0003111606,0.19198999,0.00006489941,0.00012305357,0.000643751,0.0007953936,0.009837795,0.0010392824,0.7057168,0.00044166695,0.08863382],"study_design_scores_gemma":[0.0007567268,0.00076904194,0.002535614,0.00005741099,0.000070521906,2.2078144e-7,0.06380618,0.8798648,0.024188284,0.0036193095,0.023689017,0.00064285344],"about_ca_topic_score_codex":0.000046928806,"about_ca_topic_score_gemma":0.012641149,"teacher_disagreement_score":0.89023006,"about_ca_system_score_codex":0.00019012806,"about_ca_system_score_gemma":0.0001373001,"threshold_uncertainty_score":0.7166064},"labels":[],"label_agreement":null},{"id":"W3135579708","doi":"10.1109/access.2021.3064838","title":"These <i>do not</i> Look Like Those: An Interpretable Deep Learning Model for Image Recognition","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Artificial intelligence; Computer science; Interpretation (philosophy); Image (mathematics); Process (computing); Machine learning; Deep belief network; Pattern recognition (psychology)","score_opus":0.08591313571085571,"score_gpt":0.3504382333529624,"score_spread":0.26452509764210674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135579708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056044236,0.00013369448,0.94058186,0.00031448688,0.00060101884,0.0002685795,0.000007245341,0.00025388238,0.0017950026],"genre_scores_gemma":[0.93137324,0.000105945786,0.06509548,0.0016678717,0.00018140463,0.00016932694,0.000020796087,0.000042154927,0.0013437688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979178,0.00015093392,0.0003504412,0.0007637871,0.00028165153,0.00053542585],"domain_scores_gemma":[0.99810547,0.00025658752,0.00014572007,0.00074169034,0.00059953565,0.00015102244],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058881135,0.00020791873,0.00023792747,0.000101310456,0.0002754521,0.0015571032,0.0015292959,0.00010333231,0.000055442873],"category_scores_gemma":[0.0002486783,0.00021717047,0.00011660218,0.00048398806,0.000055002514,0.005324264,0.00036551064,0.00027070602,0.0001459604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015442415,0.00060609577,0.00029175117,0.00020027137,0.00007754993,0.00020652833,0.01546588,0.09748,0.14431584,0.0058828294,0.0019686313,0.7333502],"study_design_scores_gemma":[0.00009064866,0.000052956122,0.000006866181,0.000045177654,0.000010658198,0.000012543334,0.00021578357,0.7092887,0.26724163,0.022180814,0.0006205405,0.00023363686],"about_ca_topic_score_codex":0.000059315556,"about_ca_topic_score_gemma":0.00015812529,"teacher_disagreement_score":0.8754864,"about_ca_system_score_codex":0.00006923918,"about_ca_system_score_gemma":0.00014338763,"threshold_uncertainty_score":0.99947935},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5508278289633713,"score_gpt":0.532768470116231,"score_spread":0.018059358847140383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138114698","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018704353,0.7220171,0.25997815,0.015275196,0.00046541475,0.0017995659,0.000010948073,0.00006015976,0.0003915733],"genre_scores_gemma":[0.00041877062,0.9434252,0.054087177,0.00064158504,0.00047691667,0.0004882917,0.00007730649,0.000037333266,0.0003474414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908908,0.00062567374,0.0013911208,0.0036212546,0.0022724462,0.0011987007],"domain_scores_gemma":[0.9935359,0.0025138275,0.00023737385,0.0022170476,0.00097486866,0.0005209937],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049026236,0.00033000752,0.0013946937,0.0016912833,0.00060148793,0.00014100134,0.0025534427,0.000092440605,0.000052758187],"category_scores_gemma":[0.01597384,0.0002644586,0.00016253171,0.010095955,0.0008563627,0.0005983405,0.00027969212,0.0010094198,0.00006892021],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045555416,0.000059523936,0.000009893853,0.0014603469,0.0000049394894,0.000009797032,0.002907041,0.00037705206,0.000008468051,0.072062284,0.00028934935,0.92280674],"study_design_scores_gemma":[0.00011853452,0.00039459358,0.00002391082,0.008518963,0.000009345213,0.000020795285,0.0000682988,0.008790153,0.00001718879,0.010865294,0.97090393,0.00026900912],"about_ca_topic_score_codex":0.00037483952,"about_ca_topic_score_gemma":0.0006504644,"teacher_disagreement_score":0.97061455,"about_ca_system_score_codex":0.0005772401,"about_ca_system_score_gemma":0.004956218,"threshold_uncertainty_score":0.99998075},"labels":[],"label_agreement":null},{"id":"W3140202004","doi":"10.1007/s00146-021-01200-5","title":"Algorithmic and human decision making: for a double standard of transparency","year":2021,"lang":"en","type":"article","venue":"AI & Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Transparency (behavior); Computer science; Management science; Data science; Economics; Computer security","score_opus":0.03689015840083826,"score_gpt":0.343253311839331,"score_spread":0.30636315343849274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140202004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06226076,0.0004360095,0.9360235,0.0006981205,0.00013036109,0.00019548234,0.000010533229,0.000048336766,0.0001969446],"genre_scores_gemma":[0.81514144,0.00006432771,0.18437085,0.0002870908,0.000034856163,0.000020892641,0.000002118588,0.000008289487,0.00007014555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988643,0.000017186761,0.0002772156,0.00036133028,0.00023871547,0.00024128154],"domain_scores_gemma":[0.99908745,0.00013298528,0.00006857253,0.00037240295,0.00028827178,0.00005033621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003371105,0.00010116043,0.00019558838,0.000016758517,0.00021662877,0.000104198414,0.00033495823,0.00007149285,0.000020233256],"category_scores_gemma":[0.000020277072,0.000101452926,0.00015949288,0.0002985688,0.000071818584,0.0003284289,0.00011291861,0.00009008882,0.0000021912622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011493677,0.0003155385,0.0017106615,0.0003372323,0.00014471218,0.000029395651,0.035243116,0.00030459554,0.03624299,0.6133796,0.014698797,0.29747844],"study_design_scores_gemma":[0.0022995207,0.0011075733,0.0014476139,0.00041747076,0.00006898338,0.000035171244,0.004132046,0.07224341,0.46883035,0.4176971,0.030881973,0.000838769],"about_ca_topic_score_codex":0.000026111788,"about_ca_topic_score_gemma":0.000058054113,"teacher_disagreement_score":0.7528807,"about_ca_system_score_codex":0.000044187153,"about_ca_system_score_gemma":0.00011806933,"threshold_uncertainty_score":0.413713},"labels":[],"label_agreement":null},{"id":"W3153936456","doi":"10.33423/jabe.v22i11","title":"Towards a New Approach for Building Trust and Confidence in Machine Learning Data and Models: Based on an Integration of Artificial Intelligence and Blockchain (Part 3)","year":2020,"lang":"en","type":"paratext","venue":"Journal of Applied Business and Economics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.11792081120769504,"score_gpt":0.2925109011080428,"score_spread":0.17459008990034774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153936456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029193403,0.00057690457,0.9688826,0.00046569138,0.00018087708,0.00033132962,0.000040738232,0.000005606686,0.000322821],"genre_scores_gemma":[0.7849788,0.005038873,0.20901081,0.00026067672,0.000518259,0.000014568072,0.00008031485,0.000046678277,0.000051024046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981356,0.000035832963,0.0008908442,0.0006214643,0.00010847483,0.00020776893],"domain_scores_gemma":[0.9984245,0.00018122219,0.0007981901,0.00030027295,0.00012981604,0.00016604498],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011226358,0.00027785977,0.0006946454,0.00030234185,0.00010759667,0.00041990442,0.00058766786,0.00018058678,0.000005592081],"category_scores_gemma":[0.00010501839,0.00026400445,0.00002567415,0.00022073224,0.00012449772,0.0005732386,0.00030029233,0.00042111927,5.7199827e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007112164,0.00009661763,0.000010113981,0.00035239483,0.000031684183,0.0000034383634,0.0014707954,0.62635714,0.00039378038,0.045564316,0.00012474359,0.3248838],"study_design_scores_gemma":[0.0001720294,0.00018986502,0.0000071245704,0.00015829716,0.000025288522,0.000018136796,0.00062655204,0.98266727,0.0011502563,0.01409555,0.00065207813,0.0002375653],"about_ca_topic_score_codex":0.0002042331,"about_ca_topic_score_gemma":0.000090764705,"teacher_disagreement_score":0.75987184,"about_ca_system_score_codex":0.000043213982,"about_ca_system_score_gemma":0.00031054454,"threshold_uncertainty_score":0.9999812},"labels":[],"label_agreement":null},{"id":"W3154288935","doi":"","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","year":2021,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Python (programming language); Computer science; Information retrieval; Scripting language; Ranking (information retrieval); Empirical research; Data mining; Artificial intelligence; Machine learning; Programming language","score_opus":0.2521258103347477,"score_gpt":0.4196982070748599,"score_spread":0.1675723967401122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154288935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9456858,0.0000045097886,0.036558025,0.009070616,0.00019859843,0.00084359065,0.000017933105,0.000093735136,0.0075271702],"genre_scores_gemma":[0.91702884,0.000096107855,0.0798337,0.0008362213,0.000035796664,0.00017066466,0.00009401417,0.000013128527,0.0018915532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99571997,0.00024891188,0.00062057417,0.00065323146,0.0020881307,0.0006691936],"domain_scores_gemma":[0.99375564,0.0010642577,0.000073806834,0.0008341943,0.003718898,0.0005532088],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029066838,0.00017563606,0.00018322363,0.0013639842,0.0004045878,0.002344131,0.0011124208,0.00009120348,0.00014616681],"category_scores_gemma":[0.005595653,0.00016793978,0.000013636468,0.0017083387,0.00015025474,0.0042333556,0.0013589469,0.0005413272,0.0004254743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038567095,0.0010043255,0.06559446,0.00012531644,0.00012107972,0.0007415776,0.03975589,0.001585056,0.008696843,0.74159837,0.006391424,0.13052899],"study_design_scores_gemma":[0.0030094716,0.006619557,0.30385423,0.0010176913,0.0000043817213,0.00044837626,0.020490743,0.031394925,0.30355802,0.038069915,0.28944254,0.0020901435],"about_ca_topic_score_codex":0.00024576733,"about_ca_topic_score_gemma":0.00044660716,"teacher_disagreement_score":0.7035284,"about_ca_system_score_codex":0.00029914538,"about_ca_system_score_gemma":0.0013972596,"threshold_uncertainty_score":0.99869156},"labels":[],"label_agreement":null},{"id":"W3154483210","doi":"","title":"Okan Bulut: Visualizing Machine Learning Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.07265467531928853,"score_gpt":0.2909843049288183,"score_spread":0.21832962960952979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154483210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063238796,0.0004030608,0.9244776,0.0013133676,0.00021785976,0.00005391918,3.1461562e-7,0.00042301283,0.066787034],"genre_scores_gemma":[0.9258161,0.00006131282,0.063880034,0.0009152799,0.00006247377,0.0000072766343,0.0000035030039,0.000015523186,0.009238489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845505,0.00011703472,0.0002528135,0.00047492972,0.00029435754,0.00040580815],"domain_scores_gemma":[0.99903655,0.00011593083,0.000052661348,0.00049496925,0.00017797647,0.00012192975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034147323,0.00013503313,0.0001533406,0.0000814691,0.00026212374,0.0003460396,0.0006019628,0.00005349469,0.00023795423],"category_scores_gemma":[0.000123428,0.00013245647,0.00007281106,0.0006374558,0.000025918736,0.0010021898,0.00050541526,0.00021931874,0.00041608082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015432987,0.000056405515,0.00019755644,0.000008487303,0.000011418195,0.00014626163,0.0012881731,0.021960083,0.007834569,0.94403243,0.00022180351,0.024241287],"study_design_scores_gemma":[0.000040270603,0.000029176477,0.0000107101005,0.000011474171,0.000002138107,0.000030016141,0.00027512296,0.8313757,0.121467076,0.040416792,0.00616995,0.00017156065],"about_ca_topic_score_codex":0.00028990646,"about_ca_topic_score_gemma":0.00015931796,"teacher_disagreement_score":0.91949224,"about_ca_system_score_codex":0.0000460546,"about_ca_system_score_gemma":0.00009337259,"threshold_uncertainty_score":0.54014176},"labels":[],"label_agreement":null},{"id":"W3156251590","doi":"10.1088/1361-6560/ac3e0e","title":"Understanding machine learning classifier decisions in automated radiotherapy quality assurance","year":2021,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Quality assurance; Medicine","score_opus":0.5385558467910203,"score_gpt":0.4658012825977877,"score_spread":0.07275456419323262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156251590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0961013,0.0016135456,0.8948093,0.0057919547,0.00028227572,0.000083500345,0.0000010193356,0.00011173306,0.0012053931],"genre_scores_gemma":[0.9923588,0.001704041,0.00511127,0.00069367385,0.00008354284,0.0000055722103,0.0000076952065,0.000005397467,0.000030022002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854225,0.00039884224,0.00032836504,0.00037043978,0.0000913009,0.00026877667],"domain_scores_gemma":[0.9983659,0.0012366666,0.000076723816,0.00022684876,0.00004586973,0.000047996542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000811398,0.000110403664,0.00030948236,0.000099268356,0.000083421706,0.000020648164,0.00022287022,0.00007584129,0.000012234533],"category_scores_gemma":[0.0005621567,0.00008993884,0.000021242518,0.00082946394,0.00015842906,0.00014586361,0.00009240583,0.0003017653,0.0000028555392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025335441,0.00014335591,0.10274891,0.000020045052,0.00002459324,0.000119558936,0.0036084724,0.0025362535,0.060837004,0.7761009,0.00028759972,0.05354798],"study_design_scores_gemma":[0.00086996047,0.00020501955,0.009157265,0.00019132541,0.0000032259693,0.000017240922,0.0015757502,0.69591224,0.002827448,0.28655645,0.0024127786,0.00027127942],"about_ca_topic_score_codex":0.0003115635,"about_ca_topic_score_gemma":0.0006857447,"teacher_disagreement_score":0.89625746,"about_ca_system_score_codex":0.00009508599,"about_ca_system_score_gemma":0.00006507262,"threshold_uncertainty_score":0.36675993},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2186693162107233,"score_gpt":0.34444465728819823,"score_spread":0.12577534107747493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160343688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047815605,0.0011683305,0.9880927,0.00095238857,0.0005075938,0.00033177776,0.00016435754,0.000266427,0.0037348473],"genre_scores_gemma":[0.8802801,0.00012168623,0.11788898,0.0001361361,0.00009968916,0.000023619443,0.0007038504,0.00002540058,0.0007205649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667484,0.00023789826,0.0008042156,0.0011481757,0.0006103533,0.0005244937],"domain_scores_gemma":[0.9959716,0.00031902318,0.00018899204,0.0030458618,0.0002721126,0.00020241203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015931389,0.00020906817,0.00037350034,0.00026488918,0.0002541842,0.00032072948,0.004194744,0.00006607905,0.00011989822],"category_scores_gemma":[0.0011285198,0.00020931807,0.00003433166,0.001780242,0.000027910963,0.0022214428,0.0015170817,0.00025385976,0.000070314425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039486516,0.0008231025,0.0023853441,0.0005589144,0.00035911682,0.000960755,0.05232159,0.117556736,0.02078483,0.30860648,0.004410305,0.49119335],"study_design_scores_gemma":[0.00013533182,0.000079014564,0.000032149408,0.00016254962,0.000018132518,0.000047408772,0.004416615,0.949369,0.0063220453,0.00018918327,0.038931813,0.00029673264],"about_ca_topic_score_codex":0.0004321489,"about_ca_topic_score_gemma":0.00048955664,"teacher_disagreement_score":0.87549853,"about_ca_system_score_codex":0.000043194494,"about_ca_system_score_gemma":0.00031714336,"threshold_uncertainty_score":0.8535743},"labels":[],"label_agreement":null},{"id":"W3161175241","doi":"10.22215/etd/2021-14608","title":"Cause and Effect: Concept-based Explanation of Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Negation; Causality (physics); Artificial intelligence; Computer science; Task (project management); Artificial neural network; Set (abstract data type); Representation (politics); Class (philosophy); Machine learning; Focus (optics); Theoretical computer science","score_opus":0.024531483989773197,"score_gpt":0.277243979981604,"score_spread":0.2527124959918308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161175241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14684695,0.0005535053,0.85055614,0.00041032705,0.00080228393,0.00032109942,0.0000018792845,0.000118761775,0.00038904452],"genre_scores_gemma":[0.9922788,0.000021734437,0.007251645,0.00025962348,0.00006274476,0.00003203525,0.000028122708,0.0000103682805,0.00005491681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833935,0.00021685199,0.00035743424,0.0005796061,0.00026355812,0.00024317879],"domain_scores_gemma":[0.9983423,0.00041531306,0.0001974695,0.00074924575,0.00020580823,0.00008988999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003481744,0.00021579037,0.00034199323,0.00011209229,0.000058800037,0.0002742254,0.0006268466,0.00020981352,0.000038815167],"category_scores_gemma":[0.00010818163,0.00020294744,0.00008578847,0.00023900466,0.000091703965,0.0002492348,0.0008112881,0.00033524583,0.0000020851442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028890174,0.00012585171,0.0032728056,0.0003456854,0.00009829888,0.00029437043,0.002082281,0.8803093,0.0007827904,0.031593066,0.0007624239,0.08030425],"study_design_scores_gemma":[0.0000840255,0.00009014854,0.00047595863,0.000071106384,0.000013818475,0.0000039110523,0.00005940901,0.9607114,0.037939098,0.00034156232,0.000015736996,0.00019379427],"about_ca_topic_score_codex":0.0005255615,"about_ca_topic_score_gemma":0.0001674781,"teacher_disagreement_score":0.84543186,"about_ca_system_score_codex":0.00003938419,"about_ca_system_score_gemma":0.00009456154,"threshold_uncertainty_score":0.82759565},"labels":[],"label_agreement":null},{"id":"W3161449188","doi":"10.1109/smc52423.2021.9658917","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Feature (linguistics); Transition (genetics); Artificial intelligence; State (computer science); Machine learning; Pattern recognition (psychology); Algorithm","score_opus":0.047555661643850486,"score_gpt":0.27826063322828004,"score_spread":0.23070497158442954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161449188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069762785,0.000095111456,0.95039815,0.003346606,0.0015673557,0.000323667,0.000019255765,0.00010811416,0.03716544],"genre_scores_gemma":[0.9887746,0.000113976894,0.0011802715,0.0011228768,0.00012562817,0.00006590817,0.00007771518,0.000023921382,0.008515128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708855,0.00025816358,0.0004786337,0.0007839892,0.0009795409,0.00041112263],"domain_scores_gemma":[0.9979841,0.00018833623,0.00023331068,0.0005398114,0.0008835661,0.00017087717],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004687728,0.00032992457,0.00032376646,0.00025908256,0.00019159474,0.0010718156,0.00066735223,0.00013567647,0.0001446023],"category_scores_gemma":[0.00006408638,0.00033813633,0.0001040912,0.00026649266,0.00006209197,0.00045385244,0.0000866976,0.00043760656,0.00015461995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008393089,0.0001143601,0.00003902631,0.000057055415,0.000047379373,0.00011212643,0.0005711005,0.8248478,0.0016619015,0.16982757,0.00078050786,0.0018572122],"study_design_scores_gemma":[0.00035575137,0.0002961549,0.000017313077,0.00056555483,0.000011393781,0.000010313354,0.00043648822,0.97660506,0.014709972,0.0024209695,0.00422354,0.00034749805],"about_ca_topic_score_codex":0.00024870553,"about_ca_topic_score_gemma":0.00008513812,"teacher_disagreement_score":0.9817983,"about_ca_system_score_codex":0.00021349374,"about_ca_system_score_gemma":0.0003264814,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W3165167124","doi":"10.2196/27778","title":"A Roadmap for Automating Lineage Tracing to Aid Automatically Explaining Machine Learning Predictions for Clinical Decision Support","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Computer science; Machine learning; Raw data; Artificial intelligence; Function (biology); Feature (linguistics); Tracing; Data mining","score_opus":0.05455985297948563,"score_gpt":0.3945674415140535,"score_spread":0.34000758853456786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165167124","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018723028,0.000022953269,0.9759393,0.0015542601,0.0009164576,0.0011115588,0.000018542434,0.00079089147,0.0009230542],"genre_scores_gemma":[0.09655119,0.000026441006,0.8985246,0.0033254672,0.00045907462,0.00066277955,0.000077820085,0.000038633116,0.0003340435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946693,0.00013000681,0.002735037,0.0004234009,0.0011743688,0.0008678553],"domain_scores_gemma":[0.9925823,0.0047769607,0.0004361249,0.0006758523,0.000618858,0.0009098837],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0044841506,0.0002987401,0.00061622896,0.00023089293,0.00068035565,0.0004770522,0.0011268534,0.000367407,0.00013445223],"category_scores_gemma":[0.012824915,0.00027976313,0.00034442105,0.0007870053,0.00008748648,0.001217497,0.0006432724,0.00071526197,0.0001460477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101721926,0.0006224381,0.000738318,0.0007500347,0.0001306312,0.00008379428,0.03298019,0.008018114,0.00005179641,0.02014756,0.015760528,0.9206149],"study_design_scores_gemma":[0.0007196558,0.0006813999,0.00007391094,0.00042496048,0.000019820207,0.00008462277,0.0022227976,0.9606888,0.0008192006,0.00084337697,0.03311503,0.000306398],"about_ca_topic_score_codex":0.0000036399383,"about_ca_topic_score_gemma":0.0000274375,"teacher_disagreement_score":0.9526707,"about_ca_system_score_codex":0.00011100417,"about_ca_system_score_gemma":0.00084071094,"threshold_uncertainty_score":0.9999654},"labels":[],"label_agreement":null},{"id":"W3166531723","doi":"10.48550/arxiv.2106.09424","title":"Interpretable Machine Learning Classifiers for Brain Tumour Survival Prediction","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Interpretability; Machine learning; Black box; Artificial intelligence; Computer science; Predictive modelling; Post hoc; Clinical decision support system; Clinical Practice; Medicine; Decision support system; Internal medicine","score_opus":0.09325360024541861,"score_gpt":0.21066380922755848,"score_spread":0.11741020898213987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166531723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08279215,0.000082500876,0.91152954,0.00038769064,0.0018293906,0.0004333671,0.000027944761,0.00043640818,0.0024810059],"genre_scores_gemma":[0.9898463,0.000099955636,0.003192373,0.0001226645,0.00013459458,0.0000059000263,0.00009463034,0.000034400266,0.0064692213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704456,0.0003503648,0.0003407576,0.0015142715,0.00014928533,0.00060076505],"domain_scores_gemma":[0.99768376,0.0004460592,0.0003110865,0.0009620728,0.00038127153,0.00021575193],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008373726,0.0003812179,0.0004485104,0.00031313178,0.00038537628,0.00044053784,0.0017777056,0.00034945432,0.00006627037],"category_scores_gemma":[0.00042354452,0.0004804326,0.00035738954,0.0007115893,0.00010619263,0.00088160904,0.0019744993,0.000986172,0.000035879624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011351032,0.00018779049,0.004941728,0.00021977547,0.00024129935,0.0003742073,0.0016217518,0.823127,0.002066867,0.16387102,0.0009821564,0.0022529236],"study_design_scores_gemma":[0.00021486956,0.00012242088,0.00017502418,0.00013076169,0.00004916376,0.0000051659617,0.00084063975,0.9801278,0.0024380065,0.012988271,0.0024755865,0.00043226822],"about_ca_topic_score_codex":0.0005336094,"about_ca_topic_score_gemma":0.000376834,"teacher_disagreement_score":0.9083372,"about_ca_system_score_codex":0.00042592068,"about_ca_system_score_gemma":0.00036616615,"threshold_uncertainty_score":0.99976474},"labels":[],"label_agreement":null},{"id":"W3169492703","doi":"10.22541/au.162316905.55031484/v1","title":"Neural Response Time Analysis: XAI Using Only a Stopwatch","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute","funders":"","keywords":"Computer science; Inference; A priori and a posteriori; Artificial intelligence; Class (philosophy); Object (grammar); Machine learning; sort; Set (abstract data type); Identity (music); Artificial neural network; Pattern recognition (psychology)","score_opus":0.04839411735851892,"score_gpt":0.3157258831471231,"score_spread":0.2673317657886042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169492703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.500328,0.0001706765,0.4960549,0.001614742,0.00046147336,0.00021824508,0.000004067474,0.00033014332,0.0008177347],"genre_scores_gemma":[0.8919547,0.00001243052,0.10008972,0.00082047266,0.00013837998,0.000019135387,0.00002229095,0.000034399156,0.0069084647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953686,0.0009261407,0.0007307908,0.0015632315,0.00071983226,0.0006913832],"domain_scores_gemma":[0.99579114,0.00039285616,0.00029338142,0.002789497,0.0004977137,0.00023543253],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015674033,0.00045123947,0.0007652262,0.0007627427,0.000225404,0.001597789,0.0026465063,0.0003402543,0.00057855103],"category_scores_gemma":[0.00032362985,0.000453262,0.00063555903,0.0024898245,0.00008395875,0.000646554,0.0042869216,0.0007603999,0.00029431816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037304065,0.00069233775,0.0020392488,0.00013247908,0.0028200827,0.0029042987,0.012587629,0.9114496,0.0342513,0.009853071,0.0015322178,0.021364704],"study_design_scores_gemma":[0.000037855036,0.000039622624,0.0005318892,0.000045323097,0.00022241203,0.00003317586,0.00035417665,0.9879378,0.008900703,0.0010712928,0.00027847977,0.00054724875],"about_ca_topic_score_codex":0.0017494964,"about_ca_topic_score_gemma":0.0004521833,"teacher_disagreement_score":0.3959652,"about_ca_system_score_codex":0.00030502817,"about_ca_system_score_gemma":0.0011641573,"threshold_uncertainty_score":0.9997919},"labels":[],"label_agreement":null},{"id":"W3170544780","doi":"10.21428/594757db.62860442","title":"A User-Centered Design of Explainable AI for Clinical Decision Support","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Interpretability; Computer science; Construct (python library); Context (archaeology); Process (computing); Artificial intelligence; Decision support system; Machine learning; Human–computer interaction; Data science","score_opus":0.1535379592912031,"score_gpt":0.4066577552445856,"score_spread":0.2531197959533825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170544780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034259416,0.000060691327,0.99350965,0.000952595,0.0006184611,0.00038373753,0.000002703426,0.00010129933,0.0009449273],"genre_scores_gemma":[0.17699662,0.000115663664,0.8169157,0.0017316799,0.00008110045,0.000057761325,0.000005244144,0.000019322562,0.0040769214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976018,0.00016392833,0.00086047227,0.00060991535,0.0003207999,0.00044310105],"domain_scores_gemma":[0.99656385,0.0014365149,0.00014469125,0.00096286467,0.0007346333,0.00015745897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015657955,0.00014657891,0.00034636576,0.00009189568,0.00011487666,0.00014648752,0.0009474867,0.00011657188,0.00024391849],"category_scores_gemma":[0.0011417138,0.0001355977,0.0002064949,0.00050004665,0.000060873597,0.0007401905,0.0003944826,0.00011341421,0.00013147324],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041315088,0.0019868177,0.003466435,0.00010065019,0.000112948626,0.00032543155,0.0010123265,0.0023165646,0.007943648,0.46438313,0.20049615,0.31744274],"study_design_scores_gemma":[0.0011765542,0.0014737084,0.00038713825,0.000090532085,0.000025356288,0.000058689002,0.00069002,0.27590054,0.5375348,0.07984301,0.10227752,0.0005421552],"about_ca_topic_score_codex":0.000021963888,"about_ca_topic_score_gemma":0.000025920683,"teacher_disagreement_score":0.52959114,"about_ca_system_score_codex":0.000037639424,"about_ca_system_score_gemma":0.0004501437,"threshold_uncertainty_score":0.5529514},"labels":[],"label_agreement":null},{"id":"W3172131091","doi":"10.48550/arxiv.2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient\\n Based Explanations","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Unification; Robustness (evolution); Leverage (statistics); Perturbation (astronomy); Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.10785991392989547,"score_gpt":0.20165768293677863,"score_spread":0.09379776900688316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172131091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39402542,0.0000850125,0.6047147,0.0005304713,0.00014000684,0.0001522827,0.0000036899398,0.00003243902,0.00031601012],"genre_scores_gemma":[0.9971877,0.00021036131,0.0023287686,0.000035774716,0.000017975235,0.000001919625,0.000017979852,0.0000059049003,0.00019366627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989103,0.00015870969,0.00016022973,0.0005479913,0.000084562176,0.00013819853],"domain_scores_gemma":[0.9985921,0.00016542008,0.00018901262,0.00068353594,0.00030640315,0.000063534615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028705868,0.00014028429,0.000155304,0.00017028426,0.00018703277,0.00014492824,0.00061208394,0.0001156094,0.000008138929],"category_scores_gemma":[0.00008583656,0.00013465092,0.00005178702,0.000518477,0.00016733029,0.0003691566,0.000531233,0.0001950662,0.00000100226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000993745,0.00007803315,0.0010714377,0.00010634639,0.000036892143,0.000021237234,0.0014861741,0.41713178,0.00018593406,0.5767635,0.000029952475,0.0030787282],"study_design_scores_gemma":[0.000077217795,0.000021178541,0.004247733,0.000052612962,0.000035370602,0.0000022836823,0.00096893037,0.9821278,0.0015933823,0.010664889,0.00005767016,0.00015092571],"about_ca_topic_score_codex":0.00022652865,"about_ca_topic_score_gemma":0.00013497862,"teacher_disagreement_score":0.6031622,"about_ca_system_score_codex":0.000069254,"about_ca_system_score_gemma":0.00016936292,"threshold_uncertainty_score":0.5490905},"labels":[],"label_agreement":null},{"id":"W3174364973","doi":"10.1609/aaai.v35i7.16745","title":"Improving the Performance-Compatibility Tradeoff with Personalized Objective Functions","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Israel Science Foundation; Canadian Institute for Advanced Research","keywords":"Compatibility (geochemistry); Computer science; Machine learning; Artificial intelligence; Engineering","score_opus":0.05643723675586477,"score_gpt":0.26463388635323043,"score_spread":0.20819664959736567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174364973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8877514,0.00007527275,0.09011878,0.007072154,0.0007233932,0.0009308718,0.0000097752945,0.00021988395,0.013098479],"genre_scores_gemma":[0.99575835,0.000027605134,0.0028304958,0.00034173756,0.00009427409,0.000070382644,9.1328735e-7,0.000020536747,0.0008556795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967614,0.00007836583,0.0007027224,0.0009298248,0.0009018593,0.0006258619],"domain_scores_gemma":[0.99636024,0.00030822272,0.00050770066,0.00081163086,0.0018829093,0.0001292941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092842145,0.00036945048,0.00038333746,0.000110920526,0.00093733135,0.0005679989,0.0024027708,0.00010969731,0.00015801609],"category_scores_gemma":[0.0006320352,0.00022424723,0.00020479536,0.0018436854,0.0008940058,0.0009805316,0.0005116646,0.0006794858,0.00012459586],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022150917,0.00048978144,0.0016237207,0.00010751965,0.000078507626,0.0000038046724,0.010585544,0.0005951197,0.0824873,0.8154067,0.00014290315,0.088257596],"study_design_scores_gemma":[0.00004283535,0.00036214164,0.0009551792,0.00017913844,0.000036397287,0.000035467503,0.00900376,0.11242361,0.856837,0.01964371,0.00013984108,0.00034093516],"about_ca_topic_score_codex":0.00015834313,"about_ca_topic_score_gemma":0.000120093115,"teacher_disagreement_score":0.79576296,"about_ca_system_score_codex":0.00014724964,"about_ca_system_score_gemma":0.00054943445,"threshold_uncertainty_score":0.9144536},"labels":[],"label_agreement":null},{"id":"W3174694451","doi":"","title":"Comprehensible Counterfactual Interpretation on Kolmogorov-Smirnov Test.","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Counterfactual thinking; Kolmogorov–Smirnov test; Test (biology); Interpretation (philosophy); Computer science; Artificial intelligence; Natural language processing; Econometrics; Statistics; Statistical hypothesis testing; Mathematics; Psychology; Programming language; Geology; Social psychology","score_opus":0.09896852798624382,"score_gpt":0.19395359218226987,"score_spread":0.09498506419602605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174694451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21314617,0.000010786905,0.7778568,0.0008012474,0.00019119722,0.00017433471,0.000004598871,0.00035660175,0.007458252],"genre_scores_gemma":[0.9967875,0.000014112076,0.0007718905,0.0019119611,0.000051445135,5.1188687e-7,0.0000028231198,0.000013551225,0.00044619915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985312,0.00007901819,0.00018582013,0.00073468697,0.000121815036,0.00034741263],"domain_scores_gemma":[0.99864095,0.00036002096,0.00010917308,0.00051337585,0.00015537914,0.00022111548],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010676438,0.00020295629,0.00019112749,0.00012228775,0.00017601495,0.00013690427,0.0011160654,0.000077200304,0.00009136332],"category_scores_gemma":[0.00015056483,0.00023005792,0.00009066187,0.00093539496,0.00009753615,0.001004967,0.00028783732,0.00023042897,0.0018544572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028932682,0.00041139623,0.0036962691,0.000051907693,0.00007702444,0.0006972823,0.005599602,0.35741457,0.0070769195,0.61249095,0.0044541378,0.0077405693],"study_design_scores_gemma":[0.00021289455,0.0005190964,0.00027415692,0.000025635469,0.000010999399,0.0000033270564,0.000417808,0.97527325,0.014794183,0.005716116,0.0024669133,0.0002855965],"about_ca_topic_score_codex":0.000053900792,"about_ca_topic_score_gemma":0.000020285648,"teacher_disagreement_score":0.78364134,"about_ca_system_score_codex":0.00012358588,"about_ca_system_score_gemma":0.000071434,"threshold_uncertainty_score":0.9989227},"labels":[],"label_agreement":null},{"id":"W3176211557","doi":"10.1609/aaai.v35i13.17380","title":"Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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; Korea University","keywords":"Attribution; Computer science; Pascal (unit); Discriminative model; Backpropagation; Artificial intelligence; Artificial neural network; Relevance (law); Class (philosophy); Deep neural networks; Machine learning; Psychology; Social psychology","score_opus":0.04886274500150767,"score_gpt":0.2847071500924836,"score_spread":0.23584440509097593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176211557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36713538,0.00006850487,0.6266354,0.0020517525,0.00024919095,0.0004544033,0.0000049514133,0.00009041807,0.0033100185],"genre_scores_gemma":[0.99462485,0.000017295406,0.005021783,0.0001399628,0.00003982352,0.000044435797,0.0000034886398,0.000012776728,0.00009559561],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978317,0.00006549127,0.00055813824,0.00070208544,0.00045408393,0.00038850008],"domain_scores_gemma":[0.99746066,0.00029876377,0.0005102009,0.00024362878,0.001372568,0.000114155264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036890796,0.00027126283,0.00029383687,0.00012782897,0.00053381635,0.00046979357,0.00077611284,0.00009316934,0.000029435927],"category_scores_gemma":[0.00041806174,0.00021292569,0.00007441936,0.0012839695,0.00034733606,0.0013605179,0.00035521892,0.00050008885,0.000008924519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020016963,0.0002970682,0.004368684,0.000034230572,0.00009552368,0.0000028445706,0.008341777,0.00859357,0.04474688,0.90679157,0.000092778464,0.026434915],"study_design_scores_gemma":[0.000022316985,0.00018731624,0.00044995043,0.00015006633,0.000014284393,0.0000147499,0.0018066074,0.6587944,0.31815982,0.020177346,0.0000141226665,0.00020902132],"about_ca_topic_score_codex":0.000044771143,"about_ca_topic_score_gemma":0.000060720635,"teacher_disagreement_score":0.8866142,"about_ca_system_score_codex":0.00009900025,"about_ca_system_score_gemma":0.0000801118,"threshold_uncertainty_score":0.8682858},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.02470034312009067,"score_gpt":0.3228493839746241,"score_spread":0.2981490408545334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176714582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010277559,0.00085634843,0.9842946,0.00039596888,0.0003959655,0.00019201144,0.0000052686373,0.00021673267,0.0033655812],"genre_scores_gemma":[0.97500426,0.00006858991,0.019571176,0.00003964221,0.00006834042,0.00010558692,0.000027186317,0.000018240393,0.005097012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841213,0.00019130361,0.00032079214,0.0005779847,0.00013055411,0.00036721793],"domain_scores_gemma":[0.9982202,0.0008977762,0.000101262805,0.00029493214,0.00035669125,0.00012914336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005984294,0.00018223107,0.00021350467,0.00012044952,0.0006560164,0.00026447073,0.00020338371,0.00009439039,0.000037475074],"category_scores_gemma":[0.0012919524,0.00019408882,0.00007390993,0.0003184442,0.0000625087,0.0007288034,0.00016250063,0.00034568243,0.000041806383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012130531,0.0010224695,0.0025753288,0.00050613924,0.000073524345,0.00006964559,0.009029557,0.22742808,0.010324885,0.07777836,0.0009866345,0.67008406],"study_design_scores_gemma":[0.00015392939,0.00011899626,0.00009733292,0.000038208556,0.000019611414,0.000054534783,0.00039851942,0.96410286,0.006159951,0.007254877,0.021390202,0.0002109849],"about_ca_topic_score_codex":0.000080500526,"about_ca_topic_score_gemma":0.00047324336,"teacher_disagreement_score":0.9647267,"about_ca_system_score_codex":0.00013610153,"about_ca_system_score_gemma":0.00020974311,"threshold_uncertainty_score":0.7914712},"labels":[],"label_agreement":null},{"id":"W3177112732","doi":"10.1609/aaai.v35i13.17384","title":"Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Visualization; Aggregate (composite); Block (permutation group theory); Stability (learning theory); Machine learning; Sampling (signal processing); Data mining; Field (mathematics); Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.086346229526242,"score_gpt":0.3024044179087386,"score_spread":0.21605818838249663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177112732","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20963939,0.00045746643,0.7688997,0.017276473,0.0012150637,0.0006519268,0.000016595699,0.00025835098,0.0015850291],"genre_scores_gemma":[0.98584056,0.000069032314,0.012889733,0.00083533645,0.0001749539,0.000040541996,0.0000060716357,0.000020167055,0.00012360043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969751,0.0000664304,0.00071170065,0.00090830016,0.0007022741,0.00063617865],"domain_scores_gemma":[0.99670744,0.00041777935,0.0005220295,0.00044471177,0.001758145,0.00014987565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065515464,0.00037461676,0.00038960075,0.00012324091,0.000707953,0.0006219423,0.0012947635,0.00022474295,0.00003889968],"category_scores_gemma":[0.00094216526,0.00032973243,0.00016595202,0.0013363635,0.00048320877,0.0009986233,0.00052273896,0.000651224,0.00002117827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068618436,0.00014739524,0.0011531389,0.00004759352,0.000024031828,0.000004770991,0.001099685,0.016853468,0.017270807,0.93466574,0.00013767023,0.028527074],"study_design_scores_gemma":[0.00003783215,0.00010447489,0.000277967,0.00026913034,0.000016400754,0.000022719763,0.0006555146,0.6088154,0.335962,0.053360213,0.00018626977,0.00029209006],"about_ca_topic_score_codex":0.000054728396,"about_ca_topic_score_gemma":0.00003373188,"teacher_disagreement_score":0.8813055,"about_ca_system_score_codex":0.000119527096,"about_ca_system_score_gemma":0.0002739488,"threshold_uncertainty_score":0.9999155},"labels":[],"label_agreement":null},{"id":"W3180797935","doi":"10.1145/3450337.3483487","title":"Explainability via Interactivity? Supporting Nonexperts’ Sensemaking of pre-trained CNN by Interacting with Their Daily Surroundings","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sensemaking; Interactivity; Computer science; Convolutional neural network; Leverage (statistics); Artificial intelligence; Human–computer interaction; Data science; Multimedia","score_opus":0.02075778356643372,"score_gpt":0.29318418013963415,"score_spread":0.27242639657320045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180797935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46656144,0.00005936678,0.5300196,0.00052906945,0.0007329318,0.00053107576,0.000005838734,0.0002641089,0.0012965946],"genre_scores_gemma":[0.95557547,0.000009848325,0.0434821,0.00021261524,0.000110774796,0.00011478407,0.000046950205,0.00007438694,0.00037305415],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9932873,0.0006374626,0.00179974,0.0022712653,0.00086089864,0.0011432965],"domain_scores_gemma":[0.9915535,0.0025071385,0.0020479797,0.0025174832,0.001113522,0.00026039462],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025545042,0.0009045065,0.0013452395,0.00034802328,0.00032546202,0.0012682544,0.0022991227,0.0003874508,0.00017332357],"category_scores_gemma":[0.0015660485,0.0007823223,0.00042356717,0.00076896645,0.0002393734,0.0028054644,0.0042187436,0.0015787334,0.000006467271],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008146544,0.0034657768,0.018954126,0.00388244,0.0014612247,0.0010581278,0.26574284,0.008254628,0.51352495,0.005274665,0.0012552285,0.17631133],"study_design_scores_gemma":[0.00021474286,0.00031983686,0.0002912421,0.0018316322,0.00003947965,0.0001924871,0.02579887,0.25740352,0.7107095,0.001512823,0.00027702737,0.0014088158],"about_ca_topic_score_codex":0.0038145732,"about_ca_topic_score_gemma":0.0008278696,"teacher_disagreement_score":0.48901403,"about_ca_system_score_codex":0.0005965765,"about_ca_system_score_gemma":0.00058823486,"threshold_uncertainty_score":0.9997685},"labels":[],"label_agreement":null},{"id":"W3181485491","doi":"10.1145/3449726.3459460","title":"An evolutionary approach to interpretable learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Feature (linguistics); Metric (unit); Field (mathematics); Domain (mathematical analysis); Black box; Post hoc; Mathematics; Engineering","score_opus":0.024886900013187357,"score_gpt":0.252764617397513,"score_spread":0.22787771738432563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181485491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33654535,0.0002748056,0.6585381,0.00077848724,0.0002136067,0.00023315987,0.0000017649787,0.00010442244,0.0033102937],"genre_scores_gemma":[0.8309931,0.000024975428,0.1686338,0.000116000665,0.000046314173,0.000018835975,0.0000053807557,0.000008449742,0.00015311044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983228,0.00006559533,0.00037706163,0.00056031847,0.00039305884,0.00028119216],"domain_scores_gemma":[0.99827206,0.000056713783,0.00017843851,0.00018194102,0.0011612602,0.00014961358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021719979,0.00017322529,0.00020978175,0.00012338012,0.00041988402,0.00019918404,0.0007223016,0.000067771056,0.000010141611],"category_scores_gemma":[0.000110588575,0.00015979551,0.000058297377,0.00075168576,0.00011567489,0.00070216856,0.0005569315,0.00018910844,0.000013404842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006519403,0.0009367026,0.0483505,0.00029057573,0.00007854818,0.000002359918,0.010698172,0.31315088,0.08443018,0.49073884,0.0036417863,0.04761626],"study_design_scores_gemma":[0.000097034106,0.00012054868,0.082852505,0.00007705954,0.0000106570005,0.00008895366,0.0013587009,0.87516063,0.0038832664,0.035755794,0.00038783633,0.00020703072],"about_ca_topic_score_codex":0.000032700078,"about_ca_topic_score_gemma":8.611814e-7,"teacher_disagreement_score":0.56200975,"about_ca_system_score_codex":0.00007408354,"about_ca_system_score_gemma":0.00018753188,"threshold_uncertainty_score":0.6516272},"labels":[],"label_agreement":null},{"id":"W3184473617","doi":"10.1007/s10489-021-02662-2","title":"Evaluation of interpretability methods for multivariate time series forecasting","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Fidelity; Time series; Series (stratigraphy); Focus (optics); Multivariate statistics; Data mining","score_opus":0.12527732077834872,"score_gpt":0.4005119010539609,"score_spread":0.2752345802756122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184473617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031403212,0.00021687945,0.9889454,0.00017039597,0.00031986964,0.00072922837,0.0000046416594,0.00010437374,0.0063688853],"genre_scores_gemma":[0.44265422,0.000005325062,0.55697453,0.000054526867,0.00002969387,0.00018853946,0.000004732246,0.000012340178,0.000076091696],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971758,0.00042774633,0.00073742424,0.0007334011,0.0005225914,0.00040304335],"domain_scores_gemma":[0.9953986,0.0012825424,0.0002789022,0.00096092344,0.0019931823,0.00008584504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069167097,0.0002122724,0.0003514184,0.00009299912,0.0001539426,0.00011234981,0.00091015757,0.00010487212,0.00018093802],"category_scores_gemma":[0.0034683193,0.00021841019,0.00013811002,0.00076394336,0.0001433146,0.00056258595,0.00042726696,0.000141366,0.00006376064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024050545,0.00008806144,0.000009406794,0.00004140454,0.000040666455,7.913978e-7,0.002111341,0.0033770578,0.101013176,0.15168323,0.000018885707,0.74159193],"study_design_scores_gemma":[0.000028209959,0.00003523099,0.000009279839,0.000017419763,0.00002406329,0.000004660037,0.00020881595,0.38581118,0.46778572,0.14577857,0.00018640616,0.00011045844],"about_ca_topic_score_codex":0.000031052474,"about_ca_topic_score_gemma":0.00001748236,"teacher_disagreement_score":0.7414815,"about_ca_system_score_codex":0.00014655637,"about_ca_system_score_gemma":0.00039930036,"threshold_uncertainty_score":0.8906509},"labels":[],"label_agreement":null},{"id":"W3185459628","doi":"","title":"Research Agenda for Basic Explainable AI.","year":2021,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Computer science; Data science; Management science; Engineering","score_opus":0.07397705178376003,"score_gpt":0.35349000588645035,"score_spread":0.27951295410269034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185459628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004722079,0.0002607158,0.9618501,0.014120014,0.008563933,0.0013903026,0.00004003978,0.00004873545,0.009004086],"genre_scores_gemma":[0.98384714,0.000024898334,0.0038539504,0.0010045843,0.0006356464,0.00013304394,0.000008913386,0.0000124611715,0.0104793385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972233,0.00029179722,0.0009924372,0.00008684916,0.0010514618,0.00035411865],"domain_scores_gemma":[0.99010324,0.0011017758,0.0013440992,0.0003381918,0.0070494544,0.00006321174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008391939,0.00008224255,0.00021107569,0.00025059676,0.00058809534,0.0010229634,0.0008791031,0.00010848668,0.0000022828624],"category_scores_gemma":[0.004084245,0.000063174244,0.00024702924,0.000887813,0.000012594084,0.0039758896,0.00012270772,0.0002370756,0.00004446355],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050110088,0.00007979786,0.0008442978,0.00029003635,0.00017554028,0.0000019126123,0.008513602,0.018172972,0.0008403149,0.6072425,0.3583605,0.0054284297],"study_design_scores_gemma":[0.0004867362,0.00012209,0.000209029,0.00010443966,0.000014025199,0.00003862216,0.005210231,0.036654953,0.02034122,0.0068963426,0.9298065,0.000115871066],"about_ca_topic_score_codex":0.000018060338,"about_ca_topic_score_gemma":0.000007680384,"teacher_disagreement_score":0.9791251,"about_ca_system_score_codex":0.00095637323,"about_ca_system_score_gemma":0.0005966482,"threshold_uncertainty_score":0.986446},"labels":[],"label_agreement":null},{"id":"W3185849661","doi":"","title":"A Sparsity Algorithm with Applications to Corporate Credit Rating.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Counterfactual thinking; Computer science; Task (project management); Credit rating; Quarter (Canadian coin); Machine learning; Order (exchange); Artificial intelligence; Black box; Statement (logic); Econometrics; Algorithm; Finance; Economics","score_opus":0.12459237293906597,"score_gpt":0.20815060007738576,"score_spread":0.08355822713831978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185849661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049234167,0.000030676863,0.9474654,0.0002638059,0.00027837636,0.00074220647,0.000020139254,0.0003404144,0.0016247804],"genre_scores_gemma":[0.8667571,0.000039579973,0.1306716,0.00030933262,0.00015587536,0.000017229782,0.000037197562,0.000027073866,0.0019849895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725044,0.00014052803,0.0002446537,0.0016844377,0.0001810358,0.0004989344],"domain_scores_gemma":[0.9964093,0.00010388711,0.00039081532,0.0020399308,0.00067566324,0.00038039152],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028760295,0.00036935057,0.00038899493,0.00028115616,0.00035582457,0.00043103527,0.0023956771,0.00021919238,0.00004186586],"category_scores_gemma":[0.000032151547,0.0004288681,0.00013598418,0.0018819511,0.00013072159,0.0005439058,0.0027411943,0.0005891143,0.00029789947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048333684,0.00052682107,0.0023702958,0.00012950864,0.00025261086,0.0026989786,0.0017345728,0.654355,0.0002916537,0.31818032,0.0012060418,0.018205881],"study_design_scores_gemma":[0.0002645284,0.00022414913,0.0006862213,0.00021620243,0.00011546895,0.000031552598,0.0011020262,0.9418785,0.0061258445,0.04435693,0.0035842764,0.0014142848],"about_ca_topic_score_codex":0.0004745237,"about_ca_topic_score_gemma":0.00041430473,"teacher_disagreement_score":0.81752294,"about_ca_system_score_codex":0.00029190062,"about_ca_system_score_gemma":0.00059485476,"threshold_uncertainty_score":0.9998163},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretability; Computer science; Categorization; Artificial intelligence; Post hoc; Machine learning; Data science; Accountability; Medicine","score_opus":0.1804175306382501,"score_gpt":0.3942971125104791,"score_spread":0.213879581872229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187467055","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016441135,0.7628838,0.23017704,0.0000770268,0.0037863867,0.001927196,0.00026388615,0.0006046657,0.000115599985],"genre_scores_gemma":[0.0025014295,0.96274924,0.031096324,0.0004985003,0.00063997105,0.00044560895,0.0013739197,0.000322486,0.00037250403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9837036,0.010552932,0.0017624106,0.0020624108,0.0006589691,0.0012596507],"domain_scores_gemma":[0.970855,0.023123208,0.0009869301,0.0042577875,0.00052461505,0.00025246936],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.022674968,0.00087985524,0.0023367992,0.0004063899,0.0007641572,0.00066841685,0.009256629,0.00030475907,0.000101304984],"category_scores_gemma":[0.012255528,0.0008527988,0.0010921201,0.0018061808,0.0001418606,0.00045846394,0.00626866,0.0010910796,0.00013376406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006275165,0.00010177089,0.00010190349,0.001995891,0.000082164595,0.000015949121,0.00031097623,0.0000859437,1.4375804e-7,0.0005231227,0.00031986067,0.996456],"study_design_scores_gemma":[0.00014680166,0.0008566947,0.00049550756,0.0011867344,0.000115986884,0.00008884116,0.000038658683,0.045765504,0.000004083316,0.0012167392,0.9482879,0.0017965683],"about_ca_topic_score_codex":0.0017383151,"about_ca_topic_score_gemma":0.0007400788,"teacher_disagreement_score":0.9946594,"about_ca_system_score_codex":0.0005009563,"about_ca_system_score_gemma":0.00078430306,"threshold_uncertainty_score":0.9993923},"labels":[],"label_agreement":null},{"id":"W3187853654","doi":"","title":"Temporal Dependencies in Feature Importance for Time Series Predictions.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Feature (linguistics); Computer science; Series (stratigraphy); Time series; Artificial intelligence; Machine learning; Data mining; Multivariate statistics; Task (project management); Code (set theory); Pattern recognition (psychology)","score_opus":0.05508152365558667,"score_gpt":0.19808229214259343,"score_spread":0.14300076848700677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187853654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23156801,0.00042186,0.7627763,0.00089745736,0.0009729356,0.0009133828,0.00005309805,0.00044185843,0.0019550822],"genre_scores_gemma":[0.9790471,0.00014326477,0.012127531,0.00009578749,0.00009020494,0.000010534198,0.000064173575,0.000022188098,0.008399196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977766,0.00010610017,0.00026623055,0.0012538792,0.00011910101,0.00047804829],"domain_scores_gemma":[0.9979972,0.00011963883,0.0002357161,0.0011981409,0.0003197498,0.00012951164],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003427914,0.00032278718,0.00038906498,0.00028973908,0.00020339,0.00028006278,0.0016460818,0.00039741528,0.000044053962],"category_scores_gemma":[0.00012560714,0.00039770582,0.00022416147,0.00090821803,0.00012030002,0.0012872032,0.0013105065,0.0005915624,0.000039027065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020567272,0.0004859194,0.06799285,0.00046927607,0.00024659352,0.003357263,0.0032998296,0.46758613,0.0004732281,0.4479059,0.007130731,0.00084660307],"study_design_scores_gemma":[0.0004188631,0.00019330878,0.0038043607,0.00036019206,0.00006705798,0.00003853322,0.0020316008,0.8780078,0.005504851,0.10489965,0.0034174668,0.0012563159],"about_ca_topic_score_codex":0.00023733903,"about_ca_topic_score_gemma":0.0019054508,"teacher_disagreement_score":0.7506488,"about_ca_system_score_codex":0.00034872312,"about_ca_system_score_gemma":0.00054188806,"threshold_uncertainty_score":0.9998475},"labels":[],"label_agreement":null},{"id":"W3189593202","doi":"10.2196/28287","title":"Ranking Rule-Based Automatic Explanations for Machine Learning Predictions on Asthma Hospital Encounters in Patients With Asthma: Retrospective Cohort Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute","keywords":"Asthma; Machine learning; Ranking (information retrieval); Artificial intelligence; Medicine; Psychological intervention; Computer science; Rank (graph theory); Nursing","score_opus":0.007026208585640661,"score_gpt":0.2522357767612892,"score_spread":0.24520956817564857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189593202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6847324,0.0000038922194,0.31224674,0.00039473455,0.00030487493,0.0015648528,0.00001594505,0.00021870846,0.00051788706],"genre_scores_gemma":[0.98703593,0.0000016758205,0.011833347,0.00036441107,0.00003713745,0.0005793166,0.0000994708,0.00001757025,0.000031156742],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672115,0.00011690779,0.000805307,0.00029552123,0.0016138417,0.00044726118],"domain_scores_gemma":[0.9981907,0.00040866734,0.00028087012,0.00046312035,0.00045514054,0.00020151093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008484079,0.00023321541,0.00035273188,0.00031031194,0.00033950692,0.00022397969,0.0005679026,0.00011586408,0.000068074565],"category_scores_gemma":[0.0008877117,0.00020208237,0.000072146475,0.000979203,0.00008554091,0.0009106761,0.00013819631,0.0005829556,0.000032216176],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006151541,0.0037993772,0.9395273,0.0001287958,0.00014686323,0.0000634462,0.027330307,0.010311093,4.711326e-7,0.0046199956,0.0004251411,0.013585746],"study_design_scores_gemma":[0.0016163632,0.0016612568,0.25032368,0.00022341174,0.000009782348,0.0000027840535,0.0030362457,0.74243444,0.000038074577,0.0001391488,0.0002668266,0.00024796673],"about_ca_topic_score_codex":0.000029727598,"about_ca_topic_score_gemma":0.00015081462,"teacher_disagreement_score":0.7321234,"about_ca_system_score_codex":0.00041906402,"about_ca_system_score_gemma":0.00036926114,"threshold_uncertainty_score":0.824068},"labels":[],"label_agreement":null},{"id":"W3189803107","doi":"10.24963/ijcai.2021/564","title":"Counterfactual Explanations for Optimization-Based Decisions in the Context of the GDPR","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Counterfactual thinking; Context (archaeology); Computer science; Inverse; Mathematical optimization; Binary number; Maximum satisfiability problem; Optimization problem; Integer (computer science); Theoretical computer science; Artificial intelligence; Mathematics; Algorithm; Boolean function; Psychology; Social psychology; Arithmetic","score_opus":0.05216332480047825,"score_gpt":0.29837800968415173,"score_spread":0.24621468488367348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189803107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024076095,0.000031047206,0.98579055,0.0094857365,0.0001832104,0.00027985102,0.000010937263,0.000016823833,0.0017942562],"genre_scores_gemma":[0.9531245,0.000006125375,0.04395657,0.002636623,0.0000118408625,0.00005780491,0.000004519168,0.0000038623853,0.00019815519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990654,0.000100928424,0.00026214356,0.00018087219,0.00024284197,0.00014779888],"domain_scores_gemma":[0.99689454,0.0020951792,0.000063893116,0.0005955373,0.0003310815,0.000019754509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037091866,0.00006588416,0.00008703365,0.00005223189,0.00017114526,0.000104367835,0.0009577977,0.000031738717,0.00006237985],"category_scores_gemma":[0.00090853235,0.000038890485,0.000068060355,0.000673847,0.00005349256,0.00020082491,0.00007704062,0.00006323722,0.0000080626505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065188538,0.00020245834,0.00029878528,0.000003637927,0.000007810926,0.00000292537,0.0039336444,0.45807233,0.0002835003,0.5270832,0.004850295,0.0052549113],"study_design_scores_gemma":[0.00017210393,0.000031647272,0.00016369257,0.000022382863,0.0000043071072,0.0000029312578,0.005262042,0.93587524,0.04847636,0.003855963,0.0060485043,0.000084815445],"about_ca_topic_score_codex":0.00008529347,"about_ca_topic_score_gemma":0.0013022767,"teacher_disagreement_score":0.9507169,"about_ca_system_score_codex":0.000029041676,"about_ca_system_score_gemma":0.0002740378,"threshold_uncertainty_score":0.17798424},"labels":[],"label_agreement":null},{"id":"W3191911242","doi":"10.1007/978-3-030-84060-0_19","title":"On the Trustworthiness of Tree Ensemble Explainability Methods","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Georgian College","funders":"","keywords":"Computer science; Feature (linguistics); Stability (learning theory); Trustworthiness; Machine learning; Tree (set theory); Focus (optics); Artificial intelligence; Variety (cybernetics); Measure (data warehouse); Ensemble learning; Random forest; Data mining; Noise (video); Computer security; Mathematics","score_opus":0.04130715168566368,"score_gpt":0.3148927649232393,"score_spread":0.27358561323757563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191911242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052932295,0.00036961434,0.985951,0.0021609506,0.0016772698,0.0004799833,0.0000021889641,0.000091758506,0.008737926],"genre_scores_gemma":[0.2646533,0.000049921677,0.73169374,0.0023412644,0.0003146862,0.000036045956,0.0000027256078,0.000050749983,0.0008575553],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951353,0.00030749093,0.00084545417,0.0017662381,0.0012084334,0.00073707843],"domain_scores_gemma":[0.99064213,0.0048130713,0.00045193062,0.003251051,0.0006959773,0.00014582713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0041082045,0.0005717839,0.0007671275,0.0005345386,0.00036400466,0.00041123247,0.0052256295,0.00032694772,0.000080850055],"category_scores_gemma":[0.0013467225,0.0004168595,0.00027146927,0.0014095702,0.0012367696,0.0004909822,0.0018068874,0.0010567189,0.000025800071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006977897,0.0000462735,0.000012027282,0.000033577206,0.00001007873,0.000054120865,0.0010236655,0.016490532,0.0006050612,0.39751944,0.000015648766,0.5841826],"study_design_scores_gemma":[0.00006413291,0.00018787384,0.000048820635,0.00030313988,0.0000076273927,0.000027905198,0.0000022453478,0.23260607,0.09109135,0.6745309,0.0006563635,0.0004735561],"about_ca_topic_score_codex":0.00006494448,"about_ca_topic_score_gemma":0.00022167404,"teacher_disagreement_score":0.58370906,"about_ca_system_score_codex":0.00032398236,"about_ca_system_score_gemma":0.00086971954,"threshold_uncertainty_score":0.99982834},"labels":[],"label_agreement":null},{"id":"W3196986263","doi":"10.1162/tacl_a_00519","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Interpretability; Computer science; Representation (politics); Artificial intelligence; Domain (mathematical analysis); Adaptation (eye); Interpretation (philosophy); Artificial neural network; Domain adaptation; Machine learning; Natural language processing; Data science; Neuroscience","score_opus":0.054858845230862235,"score_gpt":0.2844312671001392,"score_spread":0.22957242186927698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196986263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015035472,0.000019350457,0.9958049,0.00020701492,0.0012518066,0.0002977118,0.00041834233,0.000035604793,0.00046170776],"genre_scores_gemma":[0.9622099,0.0000014450022,0.03735965,0.000075377044,0.000027582555,0.00004174737,0.00004126428,0.00001104868,0.0002320121],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982402,0.0002652663,0.0005298559,0.00019517256,0.00061463215,0.0001548797],"domain_scores_gemma":[0.9956962,0.0018085415,0.000604507,0.0002472107,0.0016157367,0.00002784106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010049124,0.00009404695,0.00017168598,0.00013598564,0.00041417367,0.000030647727,0.0007351246,0.00003713732,0.00000970963],"category_scores_gemma":[0.0015177942,0.000099308825,0.0001733835,0.000644578,0.00003250706,0.00010943483,0.000056757213,0.00015678904,0.0000014639982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002701781,0.00013361771,0.00028751095,0.0000143509715,0.000045478566,6.7492614e-8,0.0008840095,0.9043493,0.000017152313,0.09289635,0.00008256871,0.0012625512],"study_design_scores_gemma":[0.00014106164,0.00009210363,0.00219451,0.00000466263,0.000025049603,6.813883e-7,0.00008269501,0.89274883,0.00037825262,0.10402059,0.00023064786,0.000080930964],"about_ca_topic_score_codex":0.00017215633,"about_ca_topic_score_gemma":0.00010004921,"teacher_disagreement_score":0.96070635,"about_ca_system_score_codex":0.0002691149,"about_ca_system_score_gemma":0.0001850884,"threshold_uncertainty_score":0.40496963},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Intensive care medicine","score_opus":0.15080453337422625,"score_gpt":0.4157173319597567,"score_spread":0.2649127985855304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197107524","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.0001076e-8,0.93617946,0.056356646,0.0031946378,0.0021198385,0.00066265976,0.000014836271,0.000063214444,0.0014086525],"genre_scores_gemma":[4.6987472e-7,0.9705074,0.011402735,0.006641814,0.00022354617,0.00012326702,0.000008512306,0.00005180789,0.01104047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959662,0.000670615,0.001386246,0.0009903122,0.00051597896,0.0004706516],"domain_scores_gemma":[0.99553925,0.0012328862,0.00041287902,0.0020805977,0.0005322835,0.00020209825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001501432,0.0004189717,0.002279024,0.00015018748,0.000029441839,0.0000710806,0.0020781932,0.00018700385,0.00039740707],"category_scores_gemma":[0.004044416,0.00038221787,0.0010237879,0.0005113286,0.00014033586,0.00025439233,0.00086624577,0.00066321006,0.00039757357],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.010914e-7,0.00022438924,2.9515462e-7,0.01983732,0.00004986576,0.00013928027,0.00013147155,3.5299945e-7,1.871606e-7,0.011777966,0.23694365,0.7308945],"study_design_scores_gemma":[0.000014212839,0.00011217727,6.294893e-8,0.0459741,0.00019467028,0.00006114374,0.0000048676316,0.0000708174,0.0000042236243,0.0002849128,0.95292455,0.00035426632],"about_ca_topic_score_codex":0.000011277388,"about_ca_topic_score_gemma":0.000017419485,"teacher_disagreement_score":0.7305403,"about_ca_system_score_codex":0.00049073953,"about_ca_system_score_gemma":0.001696236,"threshold_uncertainty_score":0.99986297},"labels":[],"label_agreement":null},{"id":"W3198189810","doi":"10.1145/3465407","title":"Learn, Generate, Rank, Explain: A Case Study of Visual Explanation by Generative Machine Learning","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Guelph; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Discriminative model; Computer science; Ranking (information retrieval); Machine learning; Rank (graph theory); Artificial intelligence; Generative model; Generative grammar; Conceptualization; Motion (physics); Information retrieval; Mathematics","score_opus":0.0416245849989824,"score_gpt":0.3182963108914026,"score_spread":0.2766717258924202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198189810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32595697,0.00031795562,0.6713002,0.00014158429,0.0012589176,0.00069057086,0.00002259575,0.00014058247,0.00017061058],"genre_scores_gemma":[0.99582213,0.000119336095,0.0013282788,0.00007389857,0.000084616884,0.0003940253,0.000028655235,0.000049779686,0.0020992958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949282,0.0015007548,0.0012220712,0.0011116546,0.00073911203,0.00049820624],"domain_scores_gemma":[0.9960313,0.0010933873,0.0005072633,0.0010607238,0.0011069507,0.0002003898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054734707,0.00048438276,0.00063208106,0.000517197,0.0006245312,0.0003794223,0.0008278656,0.00015591017,0.00019323385],"category_scores_gemma":[0.00028103768,0.0004867387,0.00021582805,0.0012031136,0.00006739533,0.0012434439,0.00007269212,0.00084486936,0.00015456953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007369122,0.019076966,0.0012525788,0.00023763989,0.0028507637,0.0077496953,0.11494498,0.56791824,0.16033716,0.0021447807,0.0011228576,0.12162743],"study_design_scores_gemma":[0.00055222097,0.0022940845,0.0000051717006,0.00014019698,0.000067460875,0.001814898,0.10333469,0.22610454,0.6629801,0.00008736001,0.0020371687,0.0005821456],"about_ca_topic_score_codex":0.004462003,"about_ca_topic_score_gemma":0.0013572538,"teacher_disagreement_score":0.66997194,"about_ca_system_score_codex":0.00039795748,"about_ca_system_score_gemma":0.00013896945,"threshold_uncertainty_score":0.9997584},"labels":[],"label_agreement":null},{"id":"W3198633914","doi":"10.1162/artl_a_00339","title":"Explaining Evolutionary Agent-Based Models via Principled Simplification","year":2021,"lang":"en","type":"article","venue":"Artificial Life","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Evolutionary algorithm; Testbed; Fitness landscape; Evolutionary robotics; Machine learning; Population","score_opus":0.07388223477637697,"score_gpt":0.28520240180250245,"score_spread":0.2113201670261255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198633914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04363981,0.00018314175,0.9478621,0.0038855695,0.00074157905,0.00024701806,0.0000053731483,0.00046953067,0.0029658827],"genre_scores_gemma":[0.9582935,0.0000068537292,0.039221693,0.0018634612,0.00027335592,0.000078770296,0.000041499734,0.000027307016,0.0001935766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969157,0.00025132572,0.0007118757,0.0008569099,0.0006266884,0.00063752464],"domain_scores_gemma":[0.99750805,0.00029047424,0.00019976163,0.0011832779,0.00049157324,0.00032687734],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005522999,0.0002480748,0.00026316184,0.00017727488,0.0005640059,0.0002998465,0.0008322929,0.00013505343,0.00012755483],"category_scores_gemma":[0.00049829576,0.00028420912,0.00015443431,0.0011103147,0.00008703959,0.001214494,0.00028772498,0.0002206364,0.0008841428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042231,0.00045824403,0.00029951896,0.00002558135,0.000033543376,0.00013656236,0.0012595687,0.094560586,0.044096403,0.8318996,0.0013141881,0.025874011],"study_design_scores_gemma":[0.00008511083,0.000044816938,0.00029771854,0.000018912338,0.000009308902,0.000008786929,0.00028947208,0.8389171,0.09956682,0.057204057,0.0032337771,0.00032414866],"about_ca_topic_score_codex":0.00007018582,"about_ca_topic_score_gemma":0.00006890612,"teacher_disagreement_score":0.91465366,"about_ca_system_score_codex":0.0001646944,"about_ca_system_score_gemma":0.00070775463,"threshold_uncertainty_score":0.999961},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.11660385151181457,"score_gpt":0.3054948642189832,"score_spread":0.18889101270716863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201437744","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006134242,0.9832966,0.011300983,0.0010023859,0.0004723983,0.00035726864,0.0000054564052,0.0000038582552,0.003499744],"genre_scores_gemma":[0.015443872,0.9834648,0.0004804769,0.000059726797,0.00033279668,0.000025840873,0.0000047013946,0.000021462083,0.00016633057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958973,0.0022459663,0.0009313667,0.00028908957,0.00013237172,0.0005039348],"domain_scores_gemma":[0.99596477,0.002306803,0.0006511662,0.00051848387,0.00034049945,0.00021827896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002627563,0.00024402446,0.001740617,0.0004355362,0.00027064298,0.00011749459,0.0015349673,0.00023178855,0.0000034181944],"category_scores_gemma":[0.0025628365,0.00015097014,0.00041419503,0.00071115146,0.00049574,0.00019928862,0.00018318411,0.0012243824,0.0000051387683],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039200836,0.0000021093429,0.00047434983,0.00050700374,0.0005429852,0.0018775926,0.0029062168,0.026546346,0.000001913317,0.02045209,0.0018027115,0.94488275],"study_design_scores_gemma":[0.00006329673,0.00010605566,0.000037858597,0.0007984478,0.0001404959,0.00254007,0.0008258191,0.00031299525,0.0000024047001,0.0005134963,0.99451303,0.00014603858],"about_ca_topic_score_codex":0.001029061,"about_ca_topic_score_gemma":0.0029429672,"teacher_disagreement_score":0.9927103,"about_ca_system_score_codex":0.00018678777,"about_ca_system_score_gemma":0.0033710557,"threshold_uncertainty_score":0.6156384},"labels":[],"label_agreement":null},{"id":"W3202973005","doi":"","title":"Beyond Trivial Counterfactual Generations with Diverse Valuable Explanations","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"","keywords":"Counterfactual thinking; Counterfactual conditional; Computer science; Machine learning; Artificial intelligence; Debugging; Focus (optics); Causation; Causal structure; Psychology","score_opus":0.03298574985157375,"score_gpt":0.2629127552967122,"score_spread":0.22992700544513844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202973005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03443477,0.00003981482,0.917385,0.0020471087,0.00036199755,0.00012428258,0.000007975767,0.00018804797,0.045411028],"genre_scores_gemma":[0.8823864,0.000017694234,0.10300926,0.0012898684,0.0001510257,0.000038989594,0.000024885881,0.000012159319,0.013069741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986812,0.00006219506,0.0001953847,0.00039479937,0.0003732304,0.0002931949],"domain_scores_gemma":[0.9987931,0.00011582734,0.000044047603,0.0005399692,0.00039686201,0.00011016542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016010596,0.00012196858,0.00011904208,0.00008940778,0.00041532711,0.0004040951,0.00044192467,0.000043486958,0.00085472787],"category_scores_gemma":[0.000062724495,0.000105904975,0.00003985455,0.0006416924,0.000051853047,0.0011169821,0.00017163815,0.00009841905,0.00047599967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008079677,0.00024715494,0.00044706176,0.0000045586858,0.00005097435,0.00017859637,0.002864195,0.0100805955,0.006971416,0.95363796,0.020070774,0.005438609],"study_design_scores_gemma":[0.00071652734,0.00035428416,0.000405586,0.000020425001,0.00004681366,0.00019359062,0.0049616517,0.26720807,0.65578604,0.023947481,0.045492467,0.0008670472],"about_ca_topic_score_codex":0.00012968783,"about_ca_topic_score_gemma":0.0014893216,"teacher_disagreement_score":0.9296905,"about_ca_system_score_codex":0.00006649006,"about_ca_system_score_gemma":0.00036086852,"threshold_uncertainty_score":0.9358671},"labels":[],"label_agreement":null},{"id":"W3203091553","doi":"10.48550/arxiv.2109.15112","title":"Interpretability in Safety-Critical FinancialTrading Systems","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Robustness (evolution); Trading strategy; Computer science; Econometrics; Financial market; Machine learning; Economics; Finance","score_opus":0.08427118614751081,"score_gpt":0.21558792975526567,"score_spread":0.13131674360775486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203091553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24507487,0.0002518114,0.7486082,0.00016892853,0.0019195896,0.00031276708,0.000007486613,0.00018230654,0.0034740642],"genre_scores_gemma":[0.99823284,0.000120137,0.0012223377,0.00006308594,0.00007665796,0.0000028595553,0.000006816364,0.000017527516,0.000257717],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642587,0.0005359103,0.0005287581,0.0017083006,0.0001461143,0.00065505016],"domain_scores_gemma":[0.99696213,0.000628081,0.00015852822,0.0017633742,0.0002793112,0.00020859978],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008966016,0.0003614536,0.00059285783,0.0003442832,0.00016065173,0.00040456108,0.0023044047,0.00040296884,0.000042578555],"category_scores_gemma":[0.00068535673,0.0004676759,0.00024191201,0.0011441341,0.00021423047,0.0008952294,0.0025242341,0.0010785544,0.0000748464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032210373,0.00021478554,0.005806144,0.00029114514,0.000026046098,0.001992843,0.0013576893,0.2347093,0.000073120566,0.75466424,0.00003940139,0.00079308054],"study_design_scores_gemma":[0.000112084366,0.00004193611,0.0011569419,0.0005822342,0.000021447153,0.000013695698,0.0009400172,0.96035707,0.0005226183,0.03537796,0.0002762719,0.0005976922],"about_ca_topic_score_codex":0.0014154587,"about_ca_topic_score_gemma":0.0005385702,"teacher_disagreement_score":0.753158,"about_ca_system_score_codex":0.00089199224,"about_ca_system_score_gemma":0.00055492955,"threshold_uncertainty_score":0.9997775},"labels":[],"label_agreement":null},{"id":"W3204327147","doi":"10.23919/annsim52504.2021.9552151","title":"Use of Shapley Additive Explanations in Interpreting Agent-Based Simulations of Military Operational Scenarios","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Interpretability; Key (lock); Computer science; Operations research; Shapley value; Military intelligence; Management science; Risk analysis (engineering); Machine learning; Artificial intelligence; Game theory; Computer security; Engineering","score_opus":0.05972943626340973,"score_gpt":0.29811661354138047,"score_spread":0.23838717727797074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204327147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26536644,0.00006260527,0.73206556,0.0013311438,0.000119046104,0.00020458933,0.00010367995,0.000038431048,0.00070847303],"genre_scores_gemma":[0.92204785,0.0000047857498,0.07736964,0.00038805592,0.000007910022,0.000010366484,0.000060475024,0.0000045448573,0.00010636471],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871665,0.00013640548,0.00048448535,0.00026497283,0.00024376942,0.00015374411],"domain_scores_gemma":[0.99803245,0.0009791199,0.00006963382,0.0003312064,0.0005444801,0.00004312331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016844834,0.000085788255,0.00014848328,0.00021870914,0.00006333093,0.000023598812,0.00028180997,0.00004197162,0.00043828343],"category_scores_gemma":[0.0009552803,0.000091459005,0.000059705857,0.0007442981,0.000059249414,0.0008077534,0.00013444664,0.000084446365,0.000009776433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012663095,0.00045817578,0.0069374056,0.000020935944,0.000024466293,0.000029146839,0.0034662369,0.86438537,0.019451039,0.101055875,0.00070855574,0.0034501476],"study_design_scores_gemma":[0.000067524954,0.000027659613,0.0013818769,0.000067086425,0.0000023358975,9.807583e-7,0.00048551516,0.857116,0.13995501,0.0006109207,0.0002042572,0.000080830665],"about_ca_topic_score_codex":0.0007944574,"about_ca_topic_score_gemma":0.0033687418,"teacher_disagreement_score":0.6566814,"about_ca_system_score_codex":0.00005906438,"about_ca_system_score_gemma":0.00032743657,"threshold_uncertainty_score":0.47988963},"labels":[],"label_agreement":null},{"id":"W3204942516","doi":"10.1609/aiide.v17i1.18894","title":"Explaining Deep Reinforcement Learning Agents in the Atari Domain through a Surrogate Model","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Suite; Domain (mathematical analysis); Transformation (genetics); Replicate; Surrogate model; Representation (politics); Deep learning; Machine learning; Mathematics; Law","score_opus":0.07958754341074467,"score_gpt":0.30974145335092335,"score_spread":0.23015390994017867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204942516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60877573,0.0000705208,0.31856045,0.0074158865,0.00044665745,0.001106647,0.0000057782368,0.00008283298,0.06353548],"genre_scores_gemma":[0.99767596,0.00010731744,0.0008163754,0.00092297484,0.00003142947,0.00009175948,0.000004418082,0.000016171685,0.00033358738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695444,0.00006594676,0.000863683,0.0007557895,0.00076877984,0.0005913739],"domain_scores_gemma":[0.99832153,0.00028064585,0.00043904388,0.0003825388,0.0004886513,0.000087597255],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058513705,0.00037052232,0.0003566617,0.00012753293,0.0003331081,0.0011391304,0.0015605157,0.00008275819,0.000041457275],"category_scores_gemma":[0.0005554006,0.00026202545,0.00018065078,0.0006378042,0.00024877215,0.0023409221,0.00091391697,0.00060491177,0.000044334025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018990831,0.00053336634,0.00061794766,0.000046793528,0.00006278507,0.000020549993,0.056102548,0.013482056,0.0047804806,0.893064,0.000059642454,0.031039929],"study_design_scores_gemma":[0.000095067386,0.00043742225,0.00007677315,0.0005289183,0.000012810129,0.000027619808,0.05547073,0.57025534,0.20002283,0.17231014,0.00036773618,0.00039461436],"about_ca_topic_score_codex":0.000056770594,"about_ca_topic_score_gemma":0.000038707272,"teacher_disagreement_score":0.72075385,"about_ca_system_score_codex":0.00018930178,"about_ca_system_score_gemma":0.00010120068,"threshold_uncertainty_score":0.9999832},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Sensitivity (control systems); Engineering","score_opus":0.023482165211959893,"score_gpt":0.2383706673188567,"score_spread":0.2148885021068968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205978700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27879655,0.00019415643,0.720682,0.00007203391,0.00006250997,0.000058785725,0.000017735492,0.00006998891,0.000046176698],"genre_scores_gemma":[0.84114885,0.00004017305,0.15845048,0.000071944116,0.000024148776,0.0000048537695,0.00003960599,0.000012382387,0.00020752221],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981947,0.00013107233,0.0003758728,0.00057777244,0.00039489998,0.000325675],"domain_scores_gemma":[0.99872863,0.00021146491,0.0001345294,0.00079846906,0.000018291443,0.00010861697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003271019,0.0001814732,0.0003425043,0.00011368205,0.00017238967,0.000069611684,0.00032801874,0.00006832389,0.000048042893],"category_scores_gemma":[0.000030156643,0.00019601716,0.00023801198,0.0005998277,0.00011272237,0.00039511526,0.00051167683,0.0001655843,0.000049557057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005916917,0.00025101483,0.0076155686,0.000015840791,0.00016304743,0.00039959952,0.0019187732,0.9716314,0.011759756,0.0014568693,0.000007522594,0.0047746743],"study_design_scores_gemma":[0.0000806046,0.000027553537,0.0014796542,0.000026715303,0.0001096339,0.000013303886,0.00035013148,0.9178823,0.075697504,0.003948563,0.000117364994,0.00026663629],"about_ca_topic_score_codex":0.000080392434,"about_ca_topic_score_gemma":0.000062676925,"teacher_disagreement_score":0.5623523,"about_ca_system_score_codex":0.00009762402,"about_ca_system_score_gemma":0.00002726503,"threshold_uncertainty_score":0.7993348},"labels":[],"label_agreement":null},{"id":"W3206556855","doi":"10.1145/3450337.3483487","title":"Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interactivity; Sensemaking; Computer science; Human–computer interaction; Artificial intelligence; Computer vision; Computer graphics (images); Multimedia","score_opus":0.05515011285457429,"score_gpt":0.21703244408401398,"score_spread":0.16188233122943968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206556855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5111753,0.000026022853,0.4872549,0.00008596156,0.00039875935,0.00029401857,0.000006876683,0.00014773197,0.0006104391],"genre_scores_gemma":[0.9955564,0.000018386922,0.00390756,0.00007367662,0.000057000605,0.0000044072576,0.000030555642,0.000049860497,0.00030212977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99542505,0.0005612827,0.0007680572,0.0021245184,0.00026365355,0.00085742713],"domain_scores_gemma":[0.99400496,0.0014139501,0.0014997192,0.0020150573,0.00082168344,0.0002446019],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012542945,0.0006663236,0.0009175054,0.000374404,0.00032841048,0.0004581174,0.0020924907,0.00034086156,0.00007158576],"category_scores_gemma":[0.00066386245,0.0007023893,0.00037073685,0.0011613923,0.00028102295,0.0025311692,0.002989855,0.001271026,0.0000074820537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023266985,0.0061119813,0.12643269,0.005422866,0.0036373641,0.0117076095,0.19479826,0.30642325,0.22961839,0.064709865,0.00091741746,0.047893632],"study_design_scores_gemma":[0.00039109777,0.00031350402,0.00026641405,0.001370086,0.000091226655,0.00008604097,0.022189986,0.8161675,0.1534844,0.004068528,0.00015199435,0.0014192234],"about_ca_topic_score_codex":0.0015167581,"about_ca_topic_score_gemma":0.00039505394,"teacher_disagreement_score":0.5097442,"about_ca_system_score_codex":0.00070993486,"about_ca_system_score_gemma":0.00043327667,"threshold_uncertainty_score":0.9995427},"labels":[],"label_agreement":null},{"id":"W3206995700","doi":"10.18653/v1/2022.findings-emnlp.125","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Masking (illustration); Computer science; Retraining; Metric (unit); Artificial intelligence; Natural language processing; Task (project management); Machine learning; Closed captioning; Language model","score_opus":0.11364047283476893,"score_gpt":0.3655468697069478,"score_spread":0.25190639687217886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206995700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7878067,0.007119996,0.1859656,0.004752359,0.0015490905,0.0020089797,0.000051186522,0.00027045986,0.010475657],"genre_scores_gemma":[0.98201495,0.00018368101,0.017007025,0.0003318099,0.000046130637,0.0001930856,0.000010173537,0.000031578224,0.00018155154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950538,0.0005694288,0.0013823432,0.001182755,0.0011959602,0.00061565783],"domain_scores_gemma":[0.99671715,0.0006348664,0.0009951453,0.0013127174,0.0002452396,0.00009486135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006946386,0.00039107839,0.0005789277,0.00021741482,0.0003246935,0.00026281245,0.0023851637,0.00018686036,0.00014113275],"category_scores_gemma":[0.0009384563,0.0003249932,0.00012540403,0.0006686735,0.00017938601,0.00036549894,0.0029204313,0.001303857,0.000001292203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030087025,0.0007120951,0.08711891,0.00104845,0.00057708827,0.0006767751,0.16195151,0.060797025,0.02699578,0.3532073,0.0071518742,0.29946235],"study_design_scores_gemma":[0.00042132533,0.0006881657,0.00576121,0.00073894067,0.000065036846,0.00007229154,0.023023566,0.8086732,0.03409855,0.1234588,0.001190061,0.0018088527],"about_ca_topic_score_codex":0.0013628342,"about_ca_topic_score_gemma":0.000882242,"teacher_disagreement_score":0.74787617,"about_ca_system_score_codex":0.0002077833,"about_ca_system_score_gemma":0.0004775528,"threshold_uncertainty_score":0.9999202},"labels":[],"label_agreement":null},{"id":"W3208693767","doi":"10.1007/978-3-030-88900-5_27","title":"Explainable Artificial Intelligence (XAI): How the Visualization of AI Predictions Affects User Cognitive Load and Confidence","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in information systems and organisation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"CLARITY; Computer science; Visualization; Transparency (behavior); Artificial intelligence; Cognitive load; Cognition; Presentation (obstetrics); Psychology","score_opus":0.023498386934045722,"score_gpt":0.2561526430772192,"score_spread":0.23265425614317348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208693767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049053936,0.0006641018,0.99443644,0.0007789024,0.00051239075,0.0009619643,0.000020592222,0.00006544266,0.0020696232],"genre_scores_gemma":[0.9983285,0.00032615307,0.00033100092,0.0002798899,0.00011653753,0.000046302215,0.000070655486,0.000017361668,0.0004835762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809766,0.000109631066,0.0006752965,0.0003243654,0.00057703326,0.00021601422],"domain_scores_gemma":[0.9974441,0.00069556036,0.00062453165,0.0003373697,0.00083746825,0.00006096259],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007162843,0.00029134605,0.00035239058,0.00029421077,0.0002884256,0.0008202059,0.00024509805,0.00036618556,0.00002559277],"category_scores_gemma":[0.0006990794,0.0002468913,0.000043065418,0.00029821883,0.00017831991,0.0021441465,0.00016034156,0.00034870137,0.00001558183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001597553,0.000012094274,0.00010534804,0.0004238315,0.00003387764,0.0000034213392,0.015720826,0.002731214,0.00016190538,0.9582203,0.000040742743,0.022530442],"study_design_scores_gemma":[0.000550288,0.0010276166,0.00069539965,0.007000386,0.00025387126,0.00040022493,0.01326062,0.6252368,0.11180169,0.22080266,0.016585527,0.002384899],"about_ca_topic_score_codex":0.000214999,"about_ca_topic_score_gemma":0.00028046672,"teacher_disagreement_score":0.99783796,"about_ca_system_score_codex":0.00017239247,"about_ca_system_score_gemma":0.0003114958,"threshold_uncertainty_score":0.99999833},"labels":[],"label_agreement":null},{"id":"W3209014031","doi":"10.1109/iccvw54120.2021.00462","title":"SVEA: A Small-scale Benchmark for Validating the Usability of Post-hoc Explainable AI Solutions in Image and Signal Recognition","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Usability; Computer science; Benchmark (surveying); Scale (ratio); SIGNAL (programming language); Artificial intelligence; Computer vision; Image (mathematics); Post hoc; Speech recognition; Pattern recognition (psychology); Human–computer interaction; Programming language","score_opus":0.049363870428314034,"score_gpt":0.2791279378312783,"score_spread":0.2297640674029643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209014031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45183137,0.00011586302,0.54072446,0.00387875,0.000090661146,0.00048027126,0.000016081995,0.00004384453,0.002818718],"genre_scores_gemma":[0.8851453,0.000015236816,0.11393721,0.00046596056,0.00003530821,0.00013360627,0.000015577853,0.000007799228,0.00024400666],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99842227,0.00018386634,0.0004259943,0.00042708832,0.00015174955,0.0003890107],"domain_scores_gemma":[0.9979925,0.0008396231,0.00009024788,0.00040898123,0.0006094241,0.000059214733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014079737,0.00011522928,0.0001753487,0.00007154659,0.0003077872,0.0001749172,0.00034515694,0.00005827543,0.00012994048],"category_scores_gemma":[0.00051340193,0.00009696157,0.00007467723,0.00056991464,0.00013149428,0.0007528663,0.00032960073,0.00013464232,0.0000069631687],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023021626,0.001878798,0.0054636076,0.0006473775,0.000080555474,0.00006059028,0.02415592,0.001314584,0.47718564,0.111503854,0.0019419229,0.37553695],"study_design_scores_gemma":[0.00038913573,0.00044378595,0.0018616867,0.00010301908,0.00002027481,0.000037098005,0.012652168,0.19736765,0.62581426,0.16059443,0.00034067684,0.0003758181],"about_ca_topic_score_codex":0.00050359784,"about_ca_topic_score_gemma":0.0023780218,"teacher_disagreement_score":0.43331394,"about_ca_system_score_codex":0.00005939602,"about_ca_system_score_gemma":0.00017536424,"threshold_uncertainty_score":0.3953978},"labels":[],"label_agreement":null},{"id":"W3209486183","doi":"10.4230/lipics.cp.2021.35","title":"Counterfactual Explanations via Inverse Constraint Programming","year":2021,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Constraint programming; Mathematical optimization; Inverse; Computer science; Scheduling (production processes); Constraint (computer-aided design); Integer programming; Knapsack problem; Mathematics; Stochastic programming","score_opus":0.02717998728889445,"score_gpt":0.27272963290072283,"score_spread":0.24554964561182838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209486183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042606764,0.00004158208,0.94802547,0.0010177402,0.0013477267,0.0009454615,0.00017421902,0.0004387314,0.005402307],"genre_scores_gemma":[0.8224443,0.00003556267,0.17321566,0.0027308902,0.00019116011,0.00026855097,0.00046137764,0.000052670235,0.00059979904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965941,0.000061878556,0.0012312025,0.000437761,0.0006542313,0.0010208705],"domain_scores_gemma":[0.9971167,0.00026271518,0.0003879203,0.0010565743,0.0008497047,0.00032642743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006379563,0.0004076591,0.0004196622,0.00027247923,0.0005871327,0.0010294999,0.001274295,0.00021930871,0.00011609885],"category_scores_gemma":[0.00028942415,0.000415092,0.00025722972,0.0007016713,0.00023206064,0.0029786888,0.00056705915,0.00044701967,0.00055916165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013606409,0.002465169,0.004764265,0.0013460163,0.00089756784,0.00039499332,0.10992014,0.0028886667,0.0028120775,0.46117958,0.024408095,0.38878736],"study_design_scores_gemma":[0.0022385798,0.00048270397,0.0001513038,0.0002906617,0.00007424514,0.0007234556,0.021099133,0.47216654,0.062164623,0.0074331877,0.43146485,0.0017107121],"about_ca_topic_score_codex":0.000037201728,"about_ca_topic_score_gemma":0.00019613936,"teacher_disagreement_score":0.77983755,"about_ca_system_score_codex":0.00024389593,"about_ca_system_score_gemma":0.00034579358,"threshold_uncertainty_score":0.99983007},"labels":[],"label_agreement":null},{"id":"W3209896493","doi":"","title":"Partial order: Finding Consensus among Uncertain Feature Attributions","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Feature (linguistics); Computer science; Aggregate (composite); Order (exchange); Attribution; Rank (graph theory); Trustworthiness; Artificial intelligence; Machine learning; Post hoc; Psychology; Mathematics; Social psychology; Economics; Computer security","score_opus":0.11650029141222126,"score_gpt":0.22760598955533146,"score_spread":0.1111056981431102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209896493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4296786,0.00011903695,0.56614196,0.00072024105,0.0011253349,0.0003306663,0.000027107126,0.0003624777,0.001494595],"genre_scores_gemma":[0.9924825,0.000094190465,0.004032441,0.000117124924,0.00013430003,0.000003060989,0.0000637679,0.000022991402,0.0030496188],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967619,0.00035338465,0.000294146,0.0016409921,0.00017809228,0.0007714548],"domain_scores_gemma":[0.9967206,0.00030031224,0.00031871506,0.0017457862,0.00060816086,0.00030639602],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004012241,0.00044376627,0.0004676991,0.00029278448,0.00058092095,0.00050280214,0.0020465946,0.00057631516,0.00009978491],"category_scores_gemma":[0.0003187187,0.00055254163,0.00030708654,0.0018271452,0.00030783203,0.00043165465,0.0027391908,0.0012073285,0.00013793758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025716969,0.00019549837,0.010211087,0.000089215966,0.0002102175,0.0046354625,0.001070442,0.6185613,0.00023852843,0.3614079,0.002725761,0.0006288612],"study_design_scores_gemma":[0.00029879494,0.00006649342,0.0015352187,0.0003014638,0.00013394977,0.00003044671,0.0015610069,0.96533656,0.006693552,0.020302381,0.00251159,0.0012285602],"about_ca_topic_score_codex":0.0009396966,"about_ca_topic_score_gemma":0.00077401556,"teacher_disagreement_score":0.5628039,"about_ca_system_score_codex":0.0004930366,"about_ca_system_score_gemma":0.0007662332,"threshold_uncertainty_score":0.9996926},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3739980756580752,"score_gpt":0.4189385308826105,"score_spread":0.044940455224535325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209901185","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000031596899,0.95197767,0.039418623,0.005039571,0.00072948466,0.0021302453,0.00008657777,0.00008240087,0.0005322615],"genre_scores_gemma":[0.0007384335,0.99699783,0.0009983521,0.0003859252,0.0003874806,0.00032331076,0.000052311298,0.000046182366,0.00007017864],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936048,0.0009396195,0.002168175,0.0009850992,0.00071148743,0.0015908319],"domain_scores_gemma":[0.99491477,0.0012536524,0.0009815872,0.0023668853,0.00015244955,0.00033067324],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002998638,0.00054708344,0.002425744,0.00024570848,0.0005623596,0.0008559903,0.004112043,0.000114504335,0.0000025749835],"category_scores_gemma":[0.00049465144,0.00033788098,0.00036005516,0.0026258535,0.000198448,0.00048435296,0.0012590431,0.0009365882,0.0001243328],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005455045,0.000074121104,0.0000011310901,0.0060125343,0.0000109834045,0.0000048123748,0.003046591,0.000101907885,3.034525e-9,0.20663148,0.0005306547,0.7835803],"study_design_scores_gemma":[0.00001987423,0.00023928571,9.604635e-7,0.010883455,0.000006210078,0.000017563063,0.0029768737,0.00035953743,0.000007840085,0.009452533,0.9756694,0.00036647465],"about_ca_topic_score_codex":0.00033666284,"about_ca_topic_score_gemma":0.0009257427,"teacher_disagreement_score":0.9751387,"about_ca_system_score_codex":0.00073310174,"about_ca_system_score_gemma":0.0036154028,"threshold_uncertainty_score":0.9999073},"labels":[],"label_agreement":null},{"id":"W3210159868","doi":"10.1007/978-3-030-76409-8_4","title":"Explainable Artificial Intelligence for Predictive Analytics on Customer Turnover: A User-Friendly Interface for Non-expert Users","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Predictive analytics; Interface (matter); Analytics; Artificial intelligence; Business intelligence; Decision tree; Data science; Human–computer interaction; Machine learning; Knowledge management","score_opus":0.05034551028643598,"score_gpt":0.3081115915390668,"score_spread":0.25776608125263084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210159868","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014813225,0.00017945061,0.88856316,0.0010118318,0.0019942143,0.0025744906,0.00015481297,0.0003070995,0.10520013],"genre_scores_gemma":[0.021912973,0.0003920543,0.17044982,0.0021869994,0.0017678302,0.0013961967,0.00019078894,0.00047055483,0.80123276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.993919,0.000040115377,0.0014535754,0.0023407808,0.000914212,0.0013323168],"domain_scores_gemma":[0.99385804,0.0013976155,0.00062388746,0.002084041,0.0016251032,0.0004113119],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007881704,0.0011195139,0.0011828927,0.0006953355,0.00054262707,0.0008436639,0.0026707267,0.00080950424,0.00036216527],"category_scores_gemma":[0.00046595224,0.0011128901,0.00085937994,0.00038406183,0.00028350283,0.0010303103,0.0007681801,0.00072939944,0.00046997197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036006275,0.00019986353,7.123921e-7,0.00015816957,0.00030938437,0.000047738136,0.0011329119,0.0058502536,0.00026434576,0.9457615,0.030936811,0.014978239],"study_design_scores_gemma":[0.00018441626,0.0025854832,3.594166e-7,0.00080531306,0.00012929316,0.000017674902,0.001648253,0.24080147,0.12230864,0.07918608,0.5505051,0.0018279201],"about_ca_topic_score_codex":0.000085901396,"about_ca_topic_score_gemma":0.00031155962,"teacher_disagreement_score":0.8665754,"about_ca_system_score_codex":0.0008183545,"about_ca_system_score_gemma":0.00071218406,"threshold_uncertainty_score":0.9991321},"labels":[],"label_agreement":null},{"id":"W3210479060","doi":"10.14778/3461535.3461546","title":"Comprehensible counterfactual explanation on Kolmogorov-Smirnov test","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Simon Fraser University","funders":"","keywords":"Counterfactual thinking; Benchmark (surveying); Scalability; Test (biology); Set (abstract data type); Test set; Computer science; Exponential function; Algorithm; Artificial intelligence; Mathematics; Machine learning; Psychology; Database","score_opus":0.019585693011753096,"score_gpt":0.23513753534632073,"score_spread":0.21555184233456764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210479060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85226566,0.00039707668,0.016659427,0.018279618,0.002341863,0.0014393972,0.00002651317,0.0005125679,0.10807788],"genre_scores_gemma":[0.9948555,0.000033170065,0.0033953164,0.0006765409,0.00006242902,0.00003247577,0.0000010960182,0.000011983593,0.0009314618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826247,0.000010999039,0.00034875036,0.00042378507,0.0006320177,0.00032195565],"domain_scores_gemma":[0.9986642,0.00018850957,0.00022207508,0.00031090016,0.00054562045,0.00006866712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026512778,0.00017411426,0.00019143042,0.00008735147,0.00018724735,0.00019640531,0.0010296226,0.00005125859,0.00004109648],"category_scores_gemma":[0.00030350254,0.00013508718,0.00009409036,0.00058358756,0.0000675595,0.0005097957,0.00048090704,0.00016494957,0.000095479554],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034066354,0.0009856039,0.0035717292,0.00013247822,0.00006927861,0.000010007233,0.0039964537,0.00073765405,0.56101054,0.40172893,0.014625415,0.0130978245],"study_design_scores_gemma":[0.00015414032,0.0001557787,0.0007016729,0.00010110527,0.000008346779,0.000020380518,0.0006379215,0.0064215437,0.97733104,0.0080773365,0.0062378375,0.00015287066],"about_ca_topic_score_codex":0.000044442815,"about_ca_topic_score_gemma":0.000010035669,"teacher_disagreement_score":0.4163205,"about_ca_system_score_codex":0.00014935253,"about_ca_system_score_gemma":0.000076169374,"threshold_uncertainty_score":0.5508695},"labels":[],"label_agreement":null},{"id":"W3211105117","doi":"10.1109/dsaa53316.2021.9564166","title":"Explainable Artificial Intelligence for Data Science on Customer Churn","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Computer science; Artificial intelligence; Big data; Data science; Random forest; Business intelligence; Machine learning; Decision tree; Knowledge management; Data mining","score_opus":0.17344331826786868,"score_gpt":0.3710309403375801,"score_spread":0.19758762206971142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211105117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018406417,0.000068300484,0.96139556,0.0036733164,0.0012407288,0.00039593407,0.000012034478,0.00029587545,0.031077592],"genre_scores_gemma":[0.77843875,0.000053842723,0.21457177,0.002367803,0.00034352756,0.000098558456,0.0000292468,0.000034071643,0.0040624277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995708,0.00006330815,0.0005714022,0.001752376,0.00083593075,0.0010689943],"domain_scores_gemma":[0.9946158,0.00052010134,0.00011769361,0.003617317,0.000841921,0.00028719776],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020535425,0.0002631842,0.00026394645,0.00031780638,0.00088271266,0.0010916323,0.0054073804,0.000084373845,0.00022818494],"category_scores_gemma":[0.0016986831,0.00024978278,0.000079784804,0.0026905986,0.00038086454,0.003585247,0.001992682,0.00021401983,0.0014125649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012914576,0.00019331116,0.000007989682,0.000016237294,0.000006852898,0.00004135693,0.00028799317,0.0005104861,0.011357596,0.8770922,0.0015845103,0.10888857],"study_design_scores_gemma":[0.000029119277,0.000113428105,0.000010780487,0.000030035484,0.0000054976913,0.000023023505,0.0007567435,0.29177076,0.6187418,0.06453939,0.02363123,0.00034816505],"about_ca_topic_score_codex":0.00007761856,"about_ca_topic_score_gemma":0.000092588256,"teacher_disagreement_score":0.8125528,"about_ca_system_score_codex":0.000161259,"about_ca_system_score_gemma":0.0010075569,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W3211267996","doi":"10.1145/3459637.3482397","title":"The Skyline of Counterfactual Explanations for Machine Learning Decision Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nanyang Technological University; National Research Foundation Singapore; National Research Foundation","keywords":"Counterfactual thinking; Skyline; Computer science; Machine learning; Measure (data warehouse); Artificial intelligence; Function (biology); Frame (networking); Minification; Data mining; Mathematical optimization; Mathematics","score_opus":0.04505692472593091,"score_gpt":0.293800081891528,"score_spread":0.24874315716559708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211267996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047208834,0.0003105479,0.990916,0.0013508577,0.00018310043,0.00011106951,0.00000419359,0.00005371397,0.0023495904],"genre_scores_gemma":[0.89980346,0.00013529266,0.09684451,0.00013183283,0.000028294558,0.000020679532,0.0000070308047,0.0000075922576,0.003021287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903536,0.000041367748,0.00028161643,0.0002144094,0.00023574416,0.00019149571],"domain_scores_gemma":[0.99767405,0.0014067015,0.00007185394,0.00036645346,0.00044135313,0.000039562212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045668366,0.00007348001,0.00010128801,0.000041855114,0.00032691137,0.00013174338,0.000523466,0.000030554984,0.00003127318],"category_scores_gemma":[0.00048029423,0.000051646923,0.0000603215,0.00027717106,0.000032902346,0.0004175098,0.00017702926,0.00008282563,0.000015965163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016792912,0.00005755785,0.00003347261,0.0000052975465,0.000015529893,0.0000032592616,0.0008441925,0.08266359,0.0019147905,0.826361,0.0008691513,0.08721536],"study_design_scores_gemma":[0.00006816922,0.000049834638,0.0000067301744,0.000008259407,0.0000024334295,0.000004489973,0.00036551384,0.8529529,0.06458892,0.06851693,0.013375584,0.000060216273],"about_ca_topic_score_codex":0.000054977492,"about_ca_topic_score_gemma":0.00042127044,"teacher_disagreement_score":0.8950826,"about_ca_system_score_codex":0.00002307397,"about_ca_system_score_gemma":0.00008873909,"threshold_uncertainty_score":0.2514371},"labels":[],"label_agreement":null},{"id":"W3212509273","doi":"10.3390/make3040045","title":"A Multi-Component Framework for the Analysis and Design of Explainable Artificial Intelligence","year":2021,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Transparency (behavior); Computer science; Component (thermodynamics); Artificial intelligence; Knowledge management; Management science; Engineering","score_opus":0.06261654919714393,"score_gpt":0.3471028790874849,"score_spread":0.28448632989034095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212509273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004657322,0.0038488074,0.99046147,0.0005065777,0.00021964351,0.00020563508,0.0000011261037,0.000061616105,0.00003781497],"genre_scores_gemma":[0.7927445,0.00043381026,0.20635302,0.00001551894,0.00006353656,0.000041948057,0.0000032729868,0.00000938037,0.00033501623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858195,0.00029137998,0.000333386,0.00042729508,0.00012441116,0.00024158877],"domain_scores_gemma":[0.99707305,0.0021774112,0.00016895999,0.00026548,0.0002479466,0.00006716324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010929536,0.00014642398,0.00023814497,0.00018231294,0.0005637202,0.00020327812,0.00019896353,0.000088537556,0.000020391508],"category_scores_gemma":[0.0009810526,0.000120342585,0.00009268065,0.0009545727,0.000083151994,0.0002578353,0.00013992665,0.00033810822,0.0000075976413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105162646,0.00049727265,0.0021289908,0.00012986576,0.0003750182,0.00001499209,0.00821155,0.04707439,0.026767721,0.09364557,0.000012482247,0.821037],"study_design_scores_gemma":[0.000036225007,0.00008717148,0.00083081186,0.00003081785,0.00011912773,0.000014337331,0.0011730965,0.9417075,0.04413404,0.010649058,0.0010822845,0.0001355358],"about_ca_topic_score_codex":0.0001653431,"about_ca_topic_score_gemma":0.00016079182,"teacher_disagreement_score":0.8946331,"about_ca_system_score_codex":0.000027889226,"about_ca_system_score_gemma":0.00005563951,"threshold_uncertainty_score":0.49074283},"labels":[],"label_agreement":null},{"id":"W3212927945","doi":"10.48550/arxiv.2105.07033","title":"Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Hierarchy; Computer science; Artificial intelligence; Negation; Causality (physics); Machine learning; Set (abstract data type); Artificial neural network; Task (project management); Representation (politics); Class (philosophy); Focus (optics); Theoretical computer science","score_opus":0.05685303463562378,"score_gpt":0.20574219438641722,"score_spread":0.14888915975079345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212927945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4515201,0.000095569114,0.5476612,0.0000746769,0.00029589585,0.00017322534,0.0000031036593,0.00006906047,0.00010717389],"genre_scores_gemma":[0.99878436,0.0000460773,0.0009187176,0.00009685547,0.000049084098,0.0000013735696,0.00002695561,0.000012233509,0.0000643187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806327,0.00037842683,0.00024135906,0.0008927605,0.00010997054,0.00031423615],"domain_scores_gemma":[0.99808615,0.00048225117,0.00022592343,0.0008469275,0.00019441749,0.00016433027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027931534,0.00025770513,0.0003750299,0.00020780378,0.000114789866,0.00013705755,0.0009146635,0.0002747852,0.000019121826],"category_scores_gemma":[0.00009147367,0.00029708253,0.0001400837,0.00056128897,0.00024070022,0.00035807877,0.0010548525,0.0005687807,0.0000030215492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044718687,0.00006802493,0.0044942875,0.00008392822,0.00005396264,0.00061292516,0.00038879356,0.9223497,0.00008966888,0.069171995,0.000041150623,0.00260085],"study_design_scores_gemma":[0.00021848535,0.00012479529,0.0008577682,0.00008023055,0.000043874723,0.000004215386,0.000059184884,0.99248916,0.0032583768,0.002588706,0.000010697551,0.000264496],"about_ca_topic_score_codex":0.00026408694,"about_ca_topic_score_gemma":0.000103574916,"teacher_disagreement_score":0.5472643,"about_ca_system_score_codex":0.00009390152,"about_ca_system_score_gemma":0.00013348817,"threshold_uncertainty_score":0.99994814},"labels":[],"label_agreement":null},{"id":"W3213182304","doi":"","title":"Neural Algorithmic Reasoners are Implicit Planners","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Bottleneck; Computer science; Reinforcement learning; Computation; Graph; Artificial intelligence; Machine learning; Theoretical computer science; Algorithm","score_opus":0.02233425019800933,"score_gpt":0.26249117948677364,"score_spread":0.2401569292887643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213182304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1664288,0.0020049922,0.80116636,0.0069797165,0.006270987,0.0011224028,0.000034485027,0.002423507,0.013568739],"genre_scores_gemma":[0.9965331,0.0000077839595,0.0016794994,0.0011241909,0.0001659813,0.00005754923,0.000033034008,0.000012688141,0.00038616432],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779916,0.00009806249,0.0007352105,0.0003094073,0.0005545674,0.00050356967],"domain_scores_gemma":[0.9981201,0.0000577217,0.0005066994,0.00049732154,0.00065512885,0.00016300737],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00030780223,0.00023025164,0.00026384176,0.00019098037,0.00041434253,0.0019769997,0.00071750546,0.00011476686,0.000006430515],"category_scores_gemma":[0.00015715408,0.00021931909,0.00007393774,0.0010199003,0.00004576534,0.0076843323,0.00016982341,0.00024831388,0.00020940602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005779633,0.00016632958,0.0029610915,0.002215146,0.00008193741,0.00041259849,0.022900289,0.20267664,0.0060841343,0.049842305,0.02175617,0.69084555],"study_design_scores_gemma":[0.0001405023,0.00003400572,0.000333451,0.0001341742,0.0000053877575,0.0004197939,0.003649753,0.97985345,0.0046605812,0.00014368052,0.010310226,0.00031499862],"about_ca_topic_score_codex":0.000116170624,"about_ca_topic_score_gemma":0.000009023973,"teacher_disagreement_score":0.8301043,"about_ca_system_score_codex":0.00012980164,"about_ca_system_score_gemma":0.00018316429,"threshold_uncertainty_score":0.999059},"labels":[],"label_agreement":null},{"id":"W3213304991","doi":"","title":"Robust Counterfactual Explanations on Graph Neural Networks","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University","funders":"","keywords":"Counterfactual thinking; Computer science; Overfitting; Intuition; Artificial intelligence; Graph; Machine learning; Artificial neural network; Correlation; Theoretical computer science; Mathematics","score_opus":0.1172777720974386,"score_gpt":0.19123681610139345,"score_spread":0.07395904400395485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213304991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15359911,0.000034103934,0.8407377,0.0003211201,0.0004946592,0.000077597244,0.0000030450794,0.000189864,0.0045427787],"genre_scores_gemma":[0.997442,0.0000506183,0.0004831767,0.00057622313,0.00006150075,5.5774353e-7,0.000007266182,0.00001002563,0.0013686318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859226,0.00011415316,0.00014749034,0.00065509405,0.00009598575,0.00039501284],"domain_scores_gemma":[0.9986291,0.00020670962,0.00007237272,0.0007310204,0.00020714944,0.00015363371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013158038,0.00016573891,0.0001432743,0.00015680284,0.00031478866,0.00016004207,0.00083385286,0.00008493746,0.000113854934],"category_scores_gemma":[0.000051767536,0.00019414251,0.00010572147,0.0013415515,0.00008056844,0.0007824568,0.00023595855,0.00023665045,0.0001855197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008483525,0.00006845735,0.00045739635,0.0000017084171,0.000014384481,0.0004928349,0.00011704961,0.6667251,0.0000344685,0.33089337,0.0006235352,0.00056320685],"study_design_scores_gemma":[0.0001403029,0.000074223906,0.0003373658,0.000011500959,0.000011145537,0.000014900791,0.00039342872,0.9896282,0.0017000875,0.006774327,0.0006775998,0.00023693149],"about_ca_topic_score_codex":0.000056975885,"about_ca_topic_score_gemma":0.00019871409,"teacher_disagreement_score":0.84384286,"about_ca_system_score_codex":0.00010133158,"about_ca_system_score_gemma":0.000066849505,"threshold_uncertainty_score":0.7916902},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6211548340976271,"score_gpt":0.5750288304756365,"score_spread":0.0461260036219906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213880547","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017317051,0.7024844,0.23705812,0.057296455,0.0019809108,0.00096052256,0.000008699441,0.000032061427,0.000005614806],"genre_scores_gemma":[0.00074005115,0.924507,0.06275554,0.010687394,0.0010960777,0.00008373316,0.000008607641,0.000045989065,0.000075580945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9584046,0.024444913,0.013989366,0.0014254106,0.0004985276,0.001237163],"domain_scores_gemma":[0.7735104,0.214801,0.008022286,0.0013238393,0.001413443,0.00092903036],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09056282,0.0006484656,0.011307881,0.0006776213,0.00018175546,0.00008959671,0.0029274854,0.0011755448,0.00003577991],"category_scores_gemma":[0.44127235,0.0004429453,0.003307767,0.0011238756,0.00029931744,0.0005932054,0.00065868814,0.0040233852,0.00001965418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015028573,0.000230817,0.0053415345,0.007190407,0.000107222986,0.00016283468,0.0002312728,0.0033488919,4.560598e-7,0.007823633,0.0004554889,0.97495717],"study_design_scores_gemma":[0.00039789497,0.0028313508,0.0002734164,0.037705824,0.00020394423,0.00007306077,0.00021279113,0.023191663,0.000009648922,0.0059407754,0.9283947,0.0007649549],"about_ca_topic_score_codex":0.00033005976,"about_ca_topic_score_gemma":0.00043993772,"teacher_disagreement_score":0.9741922,"about_ca_system_score_codex":0.0005421545,"about_ca_system_score_gemma":0.003359228,"threshold_uncertainty_score":0.99980223},"labels":[],"label_agreement":null},{"id":"W3216764023","doi":"10.48550/arxiv.2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Suite; Domain (mathematical analysis); Transformation (genetics); Replicate; Deep learning; Representation (politics); Deep neural networks; Surrogate model; Machine learning; Mathematics; Law","score_opus":0.14076122880906267,"score_gpt":0.23146263916370807,"score_spread":0.0907014103546454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216764023","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25546905,0.000026555314,0.7336421,0.00023413716,0.000085737454,0.0001190605,2.1422758e-7,0.00007305153,0.010350088],"genre_scores_gemma":[0.99424124,0.00008634159,0.0038761785,0.0005915459,0.00002104023,0.0000018882307,0.000005469357,0.000010283295,0.0011659992],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808407,0.00030547983,0.0002384189,0.00066160905,0.00017403893,0.0005363961],"domain_scores_gemma":[0.9987123,0.00021169944,0.000115072005,0.0007710405,0.000113858754,0.00007601589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006051956,0.00018726113,0.00017761778,0.00010457553,0.0004016237,0.00016946785,0.0012934024,0.00007640709,0.000045509252],"category_scores_gemma":[0.000099634635,0.00018679429,0.00010368396,0.0014387988,0.00007503358,0.0012877707,0.000564081,0.0003638699,0.00014731359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008050812,0.000033439173,0.0007287117,0.0000046682794,0.00000953374,0.00073168817,0.0066466453,0.6283864,0.00006840319,0.3631999,0.000032033102,0.00015052529],"study_design_scores_gemma":[0.000248402,0.00004084252,0.00009518681,0.000026344269,0.000007900359,0.000010914245,0.0066458397,0.94027966,0.0010379294,0.050651606,0.00074269535,0.00021268349],"about_ca_topic_score_codex":0.00021582624,"about_ca_topic_score_gemma":0.00039588695,"teacher_disagreement_score":0.7387722,"about_ca_system_score_codex":0.00019828393,"about_ca_system_score_gemma":0.00013330409,"threshold_uncertainty_score":0.761725},"labels":[],"label_agreement":null},{"id":"W4200019611","doi":"10.1002/ail2.48","title":"Neural response time analysis: Explainable artificial intelligence using only a stopwatch","year":2021,"lang":"en","type":"article","venue":"Applied AI Letters","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Interface Biologics (Canada); Canadian Institute for Advanced Research; University of Guelph; Vector Institute","funders":"","keywords":"Computer science; Artificial intelligence; Inference; A priori and a posteriori; Class (philosophy); Object (grammar); Set (abstract data type); Machine learning; Artificial neural network; sort; Pattern recognition (psychology)","score_opus":0.029675035852880234,"score_gpt":0.2777795275372781,"score_spread":0.24810449168439785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200019611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38976845,0.000038517443,0.5995665,0.009711798,0.00019580325,0.0001992104,0.0000031309257,0.00023955641,0.0002770306],"genre_scores_gemma":[0.96059823,0.0000028057816,0.028254518,0.010621114,0.00016455796,0.00003581284,0.000012478518,0.00003544698,0.00027503286],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960209,0.00035464606,0.00072581327,0.0012153162,0.0006733592,0.0010099557],"domain_scores_gemma":[0.9974131,0.000445775,0.00019699696,0.0015039976,0.00020361754,0.00023652836],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010854262,0.00038543306,0.00051836914,0.00051537843,0.0004883752,0.00075806497,0.0013551788,0.0001289063,0.00022772515],"category_scores_gemma":[0.00014532846,0.0004250027,0.00028726071,0.0042624166,0.00017278818,0.0007790107,0.0005786275,0.00043247204,0.001006528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027273118,0.00022743164,0.00010650562,0.000019743546,0.00033367437,0.0010544163,0.0024798887,0.14203085,0.757016,0.07892388,0.00095962017,0.016575271],"study_design_scores_gemma":[0.00006621753,0.00005011829,0.00012407132,0.0000193323,0.00017654477,0.00007653276,0.0009490341,0.63141423,0.35735136,0.0076195607,0.0013754151,0.0007775586],"about_ca_topic_score_codex":0.000106742074,"about_ca_topic_score_gemma":0.000060613216,"teacher_disagreement_score":0.571312,"about_ca_system_score_codex":0.0002542826,"about_ca_system_score_gemma":0.0003260159,"threshold_uncertainty_score":0.9998202},"labels":[],"label_agreement":null},{"id":"W4200296112","doi":"10.1109/mcg.2021.3107875","title":"The Role of Interactive Visualization in Fostering Trust in AI","year":2021,"lang":"en","type":"article","venue":"IEEE Computer Graphics and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Engineering and Physical Sciences Research Council","keywords":"Visualization; Computer science; Interpretability; Relevance (law); Agency (philosophy); Human–computer interaction; Accountability; Trustworthiness; Data visualization; Data science; Artificial intelligence; Internet privacy","score_opus":0.018055466942014948,"score_gpt":0.2936592892494731,"score_spread":0.27560382230745817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200296112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05131025,0.00030788447,0.94735885,0.00045122733,0.000081520804,0.0002000206,0.0000013330142,0.000019695943,0.000269235],"genre_scores_gemma":[0.9976238,0.00019918977,0.0018758851,0.00017052851,0.000031964762,0.00008630683,0.000001793089,0.0000044339913,0.0000060729653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922884,0.00005185967,0.0002570178,0.00023844988,0.0000898481,0.00013398819],"domain_scores_gemma":[0.9992918,0.00018702398,0.000066613975,0.0003009432,0.00012538723,0.000028226794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017562661,0.00006808569,0.00009359465,0.00012411663,0.00010071226,0.00013012017,0.0003058435,0.000033421955,6.207485e-7],"category_scores_gemma":[0.0000066796906,0.00006293679,0.000025689831,0.00084823085,0.000055043645,0.00023268785,0.00020156623,0.00010926976,0.0000020474417],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018058562,0.00007824584,0.0027914946,0.0000065591244,0.0000043520963,0.0000019665065,0.0009030937,0.0005227332,0.0014732875,0.8944859,0.000009572747,0.099721],"study_design_scores_gemma":[0.00008773583,0.000023781504,0.0045459275,0.000037750367,0.0000017376249,0.0000067775745,0.00025993268,0.75917053,0.029384961,0.20065528,0.0057142237,0.0001113812],"about_ca_topic_score_codex":0.00006832884,"about_ca_topic_score_gemma":0.0004420533,"teacher_disagreement_score":0.94631356,"about_ca_system_score_codex":0.000015923739,"about_ca_system_score_gemma":0.000036107023,"threshold_uncertainty_score":0.25664878},"labels":[],"label_agreement":null},{"id":"W4200533225","doi":"10.1109/aivr52153.2021.00057","title":"AIive: Interactive Visualization and Sonification of Neural Networks in Virtual Reality","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sonification; Visualization; Computer science; Virtual reality; Human–computer interaction; Representation (politics); Artificial neural network; Artificial intelligence; Range (aeronautics); Auditory display; Data visualization; Hyperparameter; Multimedia; Engineering","score_opus":0.03832875622662141,"score_gpt":0.3368807341798562,"score_spread":0.2985519779532348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200533225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120721616,0.00009340057,0.87764597,0.000320704,0.0004050446,0.00025413264,0.0000013541456,0.000052997806,0.00050477387],"genre_scores_gemma":[0.99795854,0.00011473133,0.0016709039,0.00009095117,0.000040149178,0.000026045162,0.000037765883,0.0000081840235,0.000052721807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812555,0.00030621138,0.00053271285,0.0006391168,0.00020500994,0.0001913984],"domain_scores_gemma":[0.9985347,0.00020181133,0.0003080038,0.00059388095,0.00030896012,0.000052650117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005088691,0.00017020336,0.0002858999,0.00017083064,0.00003834514,0.00023321425,0.0005087826,0.00019648782,0.000016696273],"category_scores_gemma":[0.0001776743,0.00018033414,0.00005097082,0.00041262884,0.00006979293,0.00061727216,0.001171694,0.00035739338,0.0000011895587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053293046,0.0003908464,0.0029275496,0.00013612655,0.00004491986,0.00002936623,0.015967714,0.47210532,0.00084553147,0.3999181,0.00012284468,0.10745837],"study_design_scores_gemma":[0.000042329277,0.000042545704,0.0032607648,0.00008433754,0.0000041897465,0.0000024403114,0.0012323065,0.98439634,0.0076205917,0.0031488854,0.000007749827,0.00015749465],"about_ca_topic_score_codex":0.0015769589,"about_ca_topic_score_gemma":0.0009437941,"teacher_disagreement_score":0.87723696,"about_ca_system_score_codex":0.00010234204,"about_ca_system_score_gemma":0.00009524162,"threshold_uncertainty_score":0.7353813},"labels":[],"label_agreement":null},{"id":"W4200633865","doi":"10.1145/3512943","title":"Human-AI Collaboration for UX Evaluation: Effects of Explanation and Synchronization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada); University of Waterloo","funders":"","keywords":"Usability; Computer science; Human–computer interaction; Context (archaeology); Wizard of oz; Asynchronous communication; Synchronization (alternating current); Test (biology); User experience design","score_opus":0.04460961568483576,"score_gpt":0.35449577421542816,"score_spread":0.3098861585305924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200633865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94733363,0.000045494016,0.04601794,0.0026085686,0.0016721119,0.0018955355,0.000004108882,0.00008624437,0.00033636906],"genre_scores_gemma":[0.9949316,0.0000021236817,0.0042873225,0.00023037606,0.00015093556,0.00030326942,0.000009085042,0.000013697886,0.00007158644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983472,0.000056653153,0.0004498283,0.00038744212,0.0006080149,0.00015086409],"domain_scores_gemma":[0.99757355,0.00020092858,0.0006682805,0.0003728999,0.0011568556,0.000027456314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007954939,0.00014380153,0.00018329863,0.0002783709,0.0005951395,0.00016771557,0.0011002572,0.00004475872,0.000014088748],"category_scores_gemma":[0.00044886672,0.00013554127,0.00006868917,0.0005587428,0.000041811312,0.0012235293,0.0006466213,0.00015912918,0.0000012106592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020556878,0.001119719,0.0012897757,0.0013251017,0.00020294345,8.072843e-7,0.026202973,0.026006958,0.37919503,0.44910476,0.032482117,0.08286424],"study_design_scores_gemma":[0.0007027169,0.0016374857,0.0016568019,0.00020147192,0.000064188105,0.000011536599,0.0008952869,0.43751258,0.48891675,0.06728395,0.00086327083,0.0002539763],"about_ca_topic_score_codex":0.000019959809,"about_ca_topic_score_gemma":0.000006710036,"teacher_disagreement_score":0.4115056,"about_ca_system_score_codex":0.00029658977,"about_ca_system_score_gemma":0.000043813176,"threshold_uncertainty_score":0.55272126},"labels":[],"label_agreement":null},{"id":"W4205723429","doi":"10.1109/bigdata52589.2021.9671458","title":"Addressing Stability in Classifier Explanations","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Shapley value; Computer science; Classifier (UML); Artificial neural network; Artificial intelligence; Machine learning; Stability (learning theory); Monte Carlo method; Algorithm; Mathematics; Mathematical economics; Game theory; Statistics","score_opus":0.7275100894644405,"score_gpt":0.4292445498229833,"score_spread":0.2982655396414572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205723429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022513028,0.00018679758,0.86008424,0.026773497,0.01822612,0.0005577552,0.009804083,0.00022632937,0.06162813],"genre_scores_gemma":[0.98154235,0.0002927878,0.0076466384,0.00084627175,0.00091098034,0.000033196626,0.008074423,0.000020318257,0.0006330284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99562526,0.00031364177,0.00070557586,0.0018061571,0.001067586,0.00048179005],"domain_scores_gemma":[0.99326396,0.00041690152,0.0002125944,0.005259846,0.00067641324,0.000170257],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001155885,0.00027629882,0.00029208508,0.00030630222,0.00018389156,0.001131625,0.0078091174,0.00013329607,0.00077869254],"category_scores_gemma":[0.0015168386,0.00029719094,0.000042459153,0.0008246637,0.00014104425,0.00300679,0.0033625194,0.0005382115,0.0005425921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063695086,0.0011414664,0.0022302081,0.000037895625,0.00012363365,0.00084703084,0.00078002916,0.00017928326,0.017234404,0.21871309,0.027989162,0.7306601],"study_design_scores_gemma":[0.0008656759,0.00008719392,0.0035383853,0.0006302566,0.000025702328,0.000078149904,0.0021868856,0.7704624,0.060489807,0.02222227,0.13812679,0.0012865134],"about_ca_topic_score_codex":0.00042624993,"about_ca_topic_score_gemma":0.007966057,"teacher_disagreement_score":0.9590293,"about_ca_system_score_codex":0.00021497234,"about_ca_system_score_gemma":0.0011493284,"threshold_uncertainty_score":0.999948},"labels":[],"label_agreement":null},{"id":"W4205783425","doi":"10.1002/ail2.62","title":"Deep learning does not replace Bayesian modeling: Comparing research use via citation counting","year":2022,"lang":"en","type":"article","venue":"Applied AI Letters","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Safety Canada","funders":"Columbia University","keywords":"Artificial intelligence; Deep learning; Computer science; Surprise; Machine learning; Citation; Dominance (genetics); Data science; Psychology; World Wide Web","score_opus":0.07503285012804019,"score_gpt":0.30795810737452683,"score_spread":0.23292525724648666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205783425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25472456,0.00000710219,0.73919946,0.004871894,0.0002052581,0.00027059263,2.7298367e-7,0.00024994687,0.000470895],"genre_scores_gemma":[0.98064977,0.0000020615255,0.014640248,0.0042828326,0.000105016275,0.00016552432,0.000009180341,0.000033754746,0.00011160468],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963994,0.0003491348,0.00043919263,0.0008299094,0.0011776775,0.0008046998],"domain_scores_gemma":[0.9983927,0.000551191,0.00013292381,0.00067138195,0.00014527568,0.000106508975],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027430216,0.0001883064,0.00021279133,0.00041654098,0.0019147588,0.00075704063,0.0011847281,0.00004395168,0.00003366092],"category_scores_gemma":[0.00014529268,0.00019842939,0.0000594351,0.0011287151,0.00008499532,0.00087107293,0.0009616044,0.0012197561,0.00010971687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003560832,0.000031488576,0.0007414571,0.000013685391,0.0000137186535,0.000028930353,0.004489568,0.8716217,0.08746682,0.03064567,0.0002998475,0.004611474],"study_design_scores_gemma":[0.000108538195,0.000027754964,0.00004076836,0.0000073246033,0.0000036877025,0.0000062934346,0.0015600589,0.982793,0.011296471,0.0022816495,0.001617106,0.00025737708],"about_ca_topic_score_codex":0.00061783125,"about_ca_topic_score_gemma":0.000077072866,"teacher_disagreement_score":0.7259252,"about_ca_system_score_codex":0.00036026072,"about_ca_system_score_gemma":0.0000442583,"threshold_uncertainty_score":0.99938464},"labels":[],"label_agreement":null},{"id":"W4213331418","doi":"10.5220/0010899100003116","title":"BRL: A Toolkit for Learning How an Agent Performs Belief Revision","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Institute of Technology","funders":"","keywords":"Computer science; Belief revision; Artificial intelligence; Programming language; Human–computer interaction","score_opus":0.11639143688328618,"score_gpt":0.32710153440809564,"score_spread":0.21071009752480946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213331418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82992786,0.00006840428,0.12607671,0.030818637,0.0033666259,0.0019554964,0.000057914265,0.00024904285,0.0074793394],"genre_scores_gemma":[0.99474967,0.000080583864,0.0031171187,0.00049649953,0.00014166122,0.00010624166,0.000005555912,0.000017978637,0.0012847022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760157,0.00003666747,0.00048737152,0.0006657276,0.00084235944,0.00036631565],"domain_scores_gemma":[0.9984152,0.000084582614,0.00044806977,0.00023194595,0.00069699466,0.00012326143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010032736,0.00023623249,0.00022779676,0.00019801263,0.0009266098,0.000647606,0.002364025,0.0000531152,0.0001959726],"category_scores_gemma":[0.00040753535,0.00019050296,0.00013554607,0.00037532666,0.00014405731,0.0009297712,0.0010068524,0.00040365788,0.00000963764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103404054,0.00021978555,0.00034975843,0.000027998563,0.000024928175,0.0000010659521,0.0023811765,0.00093923067,0.0069194846,0.85326403,0.0003280889,0.13544105],"study_design_scores_gemma":[0.00007818228,0.0014129339,0.0002659083,0.00013758139,0.000017794424,0.000020196943,0.008050781,0.7398458,0.09411331,0.13609897,0.019493714,0.00046479446],"about_ca_topic_score_codex":0.00003868926,"about_ca_topic_score_gemma":0.0000058752244,"teacher_disagreement_score":0.7389066,"about_ca_system_score_codex":0.00012032542,"about_ca_system_score_gemma":0.00007080193,"threshold_uncertainty_score":0.7768485},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02558452781357945,"score_gpt":0.34661667891031656,"score_spread":0.3210321510967371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213371886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829216,0.0011520897,0.010433918,0.002759132,0.0023183678,0.00018683144,0.000002713844,0.000009189257,0.00021613191],"genre_scores_gemma":[0.99737054,0.000092009825,0.001894881,0.0001584097,0.0002006952,0.000021688107,2.9766218e-7,0.000008890971,0.00025257323],"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977549,0.00019004458,0.0007391501,0.00022036815,0.00085383723,0.00024170298],"domain_scores_gemma":[0.9972757,0.00080518186,0.00043434228,0.00021413293,0.0012167704,0.000053873693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018428548,0.0001594834,0.0003485242,0.0006154909,0.00040830745,0.00009676309,0.0011549086,0.000021585387,0.000003657459],"category_scores_gemma":[0.0002265031,0.00012315366,0.00009965553,0.00033704078,0.00012878024,0.00042337144,0.0011051792,0.00033505604,0.0000019852612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007652406,0.0021673464,0.010134326,0.00060792646,0.0021124887,0.010376493,0.31584632,0.027362244,0.007257692,0.29730776,0.026661308,0.29940084],"study_design_scores_gemma":[0.01699885,0.053571872,0.034059025,0.0077960114,0.00030334052,0.024240827,0.11290584,0.23108022,0.26553413,0.1396518,0.10971481,0.0041432614],"about_ca_topic_score_codex":0.000036802307,"about_ca_topic_score_gemma":0.0000509843,"teacher_disagreement_score":0.29525757,"about_ca_system_score_codex":0.0002597685,"about_ca_system_score_gemma":0.00006759975,"threshold_uncertainty_score":0.502206},"labels":[],"label_agreement":null},{"id":"W4220751222","doi":"10.1109/bigcomp54360.2022.00072","title":"Panel [Data-centric approaches for Trustworthy AI]","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Trustworthiness; Data science; Computer security","score_opus":0.22217240737456592,"score_gpt":0.30182933962296227,"score_spread":0.07965693224839634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220751222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015076951,0.0001733507,0.98705524,0.0047561238,0.0005590723,0.0005110451,0.000024761524,0.00029141016,0.0051213023],"genre_scores_gemma":[0.92934537,0.000008836571,0.062382396,0.002921211,0.00016749183,0.00035427164,0.00007261795,0.000023158398,0.0047246628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998184,0.000082698156,0.00025683496,0.00066941016,0.00034537615,0.00046163672],"domain_scores_gemma":[0.9982363,0.00018460579,0.00006896508,0.0013675847,0.00004959512,0.000092922244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079697353,0.00012687263,0.00014819142,0.00013339544,0.0005319124,0.00018423781,0.0030032734,0.000026551277,0.0002222983],"category_scores_gemma":[0.00008017407,0.00012264741,0.00006510343,0.00079144933,0.000031283296,0.0007667982,0.0018179954,0.00015863632,0.00008921358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017542714,0.00024214372,0.00024765672,0.0000149680045,0.000022759416,0.00001575511,0.00071017334,0.007176233,0.00004203993,0.74490994,0.038925365,0.20767543],"study_design_scores_gemma":[0.00010270179,0.00010860474,0.000038577335,7.622491e-7,0.0000059177814,0.00001504389,0.00060825545,0.7633505,0.0014531877,0.019682301,0.2144346,0.00019958359],"about_ca_topic_score_codex":0.0000811687,"about_ca_topic_score_gemma":0.000023587727,"teacher_disagreement_score":0.92783767,"about_ca_system_score_codex":0.000075806536,"about_ca_system_score_gemma":0.00011833986,"threshold_uncertainty_score":0.5580879},"labels":[],"label_agreement":null},{"id":"W4221125412","doi":"10.3389/frai.2022.826724","title":"Prediction, Knowledge, and Explainability: Examining the Use of General Value Functions in Machine Knowledge","year":2022,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"CLARITY; Computer science; Perspective (graphical); Reinforcement learning; Value (mathematics); Artificial intelligence; ENCODE; Point (geometry); Machine learning; Cognitive science; Psychology; Mathematics","score_opus":0.09464007280396282,"score_gpt":0.286303259787019,"score_spread":0.19166318698305618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221125412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16030039,0.0023923411,0.8318662,0.00056517404,0.0032780059,0.00076269725,0.000032370357,0.00010473801,0.00069807353],"genre_scores_gemma":[0.9797608,0.000093924835,0.019109344,0.00009894555,0.00009497764,0.00030469598,0.000007407411,0.000024648596,0.000505237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621254,0.0008952622,0.0011149752,0.0008279485,0.00036125298,0.00058804004],"domain_scores_gemma":[0.9979944,0.0006178516,0.0002008756,0.00091040717,0.00016776132,0.00010867908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020852576,0.00027241916,0.0003901036,0.0007462489,0.00058446685,0.00015384181,0.0011807377,0.00008687118,0.000043215052],"category_scores_gemma":[0.0006128416,0.00026122053,0.0000785022,0.0028363182,0.00044483715,0.0008517444,0.001043098,0.00068737054,0.000012284036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017484713,0.0015259202,0.07845523,0.0000742857,0.00004962419,0.000044466564,0.035466924,0.22654638,0.0010678818,0.25361565,0.005269873,0.39770892],"study_design_scores_gemma":[0.000049559763,0.00027785232,0.0032606006,0.00003464652,0.000010869563,0.000017459008,0.0053784414,0.9262041,0.005412778,0.048907097,0.01015162,0.00029497535],"about_ca_topic_score_codex":0.0009292978,"about_ca_topic_score_gemma":0.0010272278,"teacher_disagreement_score":0.81946045,"about_ca_system_score_codex":0.00040791134,"about_ca_system_score_gemma":0.00024056439,"threshold_uncertainty_score":0.999984},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1900154621451945,"score_gpt":0.369592466663248,"score_spread":0.17957700451805353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224940987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87435395,0.000011411587,0.12340453,0.00005941291,0.00066576066,0.0010955445,0.0000115458615,0.000114617826,0.00028325224],"genre_scores_gemma":[0.99955815,1.1887492e-7,0.000083456136,0.000056969584,0.00007197909,0.000104024126,0.00004628189,0.000015161702,0.00006387153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964155,0.0007806723,0.0010579383,0.00065022864,0.00078774075,0.00030792181],"domain_scores_gemma":[0.9980369,0.00015412881,0.00058880635,0.00058691687,0.000556263,0.000076992466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000852439,0.00025916315,0.00041750312,0.00046082275,0.0012957088,0.00041730265,0.0006882922,0.000062546875,0.000034942343],"category_scores_gemma":[0.000038769635,0.0002804086,0.000051853793,0.00071482593,0.000062464256,0.000499041,0.00027610437,0.00039623436,0.000004531716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012772775,0.0015440391,0.013936999,0.000056157318,0.0000493072,0.00039667884,0.045135304,0.43672097,0.005910361,0.49581945,0.00013984073,0.0002781024],"study_design_scores_gemma":[0.00073054415,0.0016870523,0.0025764785,0.00007493219,0.000009207359,0.00013912086,0.045837928,0.94335014,0.0018573395,0.003306733,0.000015291904,0.0004152134],"about_ca_topic_score_codex":0.0032741516,"about_ca_topic_score_gemma":0.0011679142,"teacher_disagreement_score":0.50662917,"about_ca_system_score_codex":0.0004675535,"about_ca_system_score_gemma":0.00016979584,"threshold_uncertainty_score":0.99996483},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"National Science Foundation","keywords":"Black box; Computer science; Artificial intelligence; Human–computer interaction","score_opus":0.09086952091528383,"score_gpt":0.3404376688759422,"score_spread":0.24956814796065835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225137238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9763351,0.000084063206,0.0063954447,0.0005118119,0.0016283114,0.0012623394,0.000018967396,0.00026754307,0.013496425],"genre_scores_gemma":[0.99864876,0.0000018735399,0.0001752352,0.00030757292,0.00012883023,0.00005489334,0.00002389091,0.0000511113,0.0006078162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99363106,0.0008182636,0.0018469408,0.0012460026,0.001286308,0.0011713943],"domain_scores_gemma":[0.9960983,0.0004331271,0.0011345737,0.0017776258,0.000351065,0.00020533311],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0024450605,0.000614465,0.0008679872,0.000600693,0.0019246375,0.00092111726,0.0041719563,0.00014936161,0.00012370622],"category_scores_gemma":[0.00014688396,0.0005379387,0.0002145137,0.00091137615,0.00032094694,0.0007413659,0.0015070377,0.0017490268,0.000034513472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002763916,0.0009086261,0.0028030733,0.0002297794,0.000091542206,0.0002503844,0.020793699,0.17940769,0.0105892625,0.7816602,0.0015210788,0.0017170118],"study_design_scores_gemma":[0.0047454494,0.005134439,0.13182856,0.0040657003,0.00010813327,0.00035761393,0.07132116,0.5468822,0.11239944,0.11049284,0.0059632864,0.0067011816],"about_ca_topic_score_codex":0.0018598456,"about_ca_topic_score_gemma":0.00011597895,"teacher_disagreement_score":0.6711674,"about_ca_system_score_codex":0.0005120659,"about_ca_system_score_gemma":0.00032495504,"threshold_uncertainty_score":0.9997072},"labels":[],"label_agreement":null},{"id":"W4226193037","doi":"10.1609/aaai.v36i11.21452","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"BC Cancer Foundation; Compute Canada; Nvidia","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Modal; Leverage (statistics); Machine learning; Metric (unit); Feature (linguistics); Medical imaging; Data mining; Engineering","score_opus":0.2772565168370234,"score_gpt":0.4433974170613346,"score_spread":0.16614090022431122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226193037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49289954,0.00026463033,0.3765475,0.078346655,0.012041298,0.00599046,0.000104702085,0.00166488,0.03214037],"genre_scores_gemma":[0.9854298,0.000022541783,0.010193336,0.0031594743,0.00028622674,0.00028191032,0.0000030215097,0.000054223376,0.00056945236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99101716,0.00034326492,0.0022286847,0.001737015,0.0033666957,0.0013071863],"domain_scores_gemma":[0.9951299,0.0007293821,0.0012531298,0.0009895228,0.0014463075,0.0004517453],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.007831675,0.000586075,0.00071320886,0.00040498743,0.0018404647,0.0005993588,0.0062212255,0.00015758966,0.00052277045],"category_scores_gemma":[0.005897599,0.000516841,0.00038827778,0.0018024754,0.00068911386,0.0008568312,0.0030630017,0.001922545,0.00014281434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020551238,0.0012096685,0.0009013289,0.000055722525,0.0000507319,0.0000359097,0.0036574134,0.0015901763,0.011684711,0.5876289,0.0006294381,0.3923505],"study_design_scores_gemma":[0.00013349977,0.0008956909,0.00009282611,0.00032262204,0.000025194555,0.000040581494,0.0047983998,0.836508,0.094052844,0.06195311,0.00055216276,0.00062508986],"about_ca_topic_score_codex":0.00054640474,"about_ca_topic_score_gemma":0.000057924153,"teacher_disagreement_score":0.8349178,"about_ca_system_score_codex":0.00045472238,"about_ca_system_score_gemma":0.00085877645,"threshold_uncertainty_score":0.9997283},"labels":[],"label_agreement":null},{"id":"W4226328072","doi":"10.1007/978-3-031-04083-2_1","title":"xxAI - Beyond Explainable Artificial Intelligence","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Bundesministerium für Bildung und Forschung; Austrian Science Fund; European Commission","keywords":"Computer science; Artificial intelligence; Generalization; Transparency (behavior); Field (mathematics); Machine learning; Artificial neural network; Reinforcement learning; Convolutional neural network; Big data; Data science; Data mining","score_opus":0.03385876189431535,"score_gpt":0.2695380502781973,"score_spread":0.23567928838388197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226328072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000055461507,0.00060811994,0.9746884,0.0019014286,0.004043281,0.000723853,0.000010415605,0.0003940719,0.017574947],"genre_scores_gemma":[0.27028444,0.000398239,0.7160314,0.0071480735,0.0022889362,0.00022165957,0.000039803366,0.00027983802,0.003307643],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916561,0.00010974205,0.0012646349,0.0030320755,0.002258546,0.00167887],"domain_scores_gemma":[0.99474293,0.0009564738,0.0005336764,0.002956659,0.00042492055,0.00038531373],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002396277,0.0009392804,0.0008536713,0.0018013237,0.0011844311,0.001304697,0.008531939,0.0004073023,0.0008474376],"category_scores_gemma":[0.00031529897,0.0009932262,0.00028305795,0.0021077807,0.0012546047,0.0020302918,0.004684505,0.0019611954,0.00049703295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008779994,0.000056210072,0.0000046981722,0.00002758329,0.0000090709655,0.0003496517,0.001171118,0.05888021,0.0001700394,0.4693819,0.000026135296,0.46991462],"study_design_scores_gemma":[0.000030044097,0.00030352833,0.0000030355325,0.00011504366,0.0000077866525,0.00009721271,0.000003571759,0.28160322,0.014516983,0.69567,0.006693518,0.0009560597],"about_ca_topic_score_codex":0.00017288029,"about_ca_topic_score_gemma":0.00024862238,"teacher_disagreement_score":0.46895856,"about_ca_system_score_codex":0.0011421493,"about_ca_system_score_gemma":0.0013093993,"threshold_uncertainty_score":0.999732},"labels":[],"label_agreement":null},{"id":"W4229442586","doi":"10.1145/3531146.3533179","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","year":2022,"lang":"en","type":"article","venue":"2022 ACM Conference on Fairness, Accountability, and Transparency","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Government of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Computer science; Fidelity; Audit; Quality (philosophy); Machine learning; Artificial intelligence; High fidelity; Data science","score_opus":0.0904029058685791,"score_gpt":0.2902133418712273,"score_spread":0.19981043600264822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229442586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92182595,0.00045244454,0.049387015,0.020466954,0.0009576859,0.0023515197,0.00020243139,0.00024927955,0.004106706],"genre_scores_gemma":[0.9980228,0.00013844293,0.00030032636,0.00032691998,0.000034643464,0.0009753839,0.0000067687683,0.000019787127,0.00017494001],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956153,0.00054522004,0.00076776906,0.0010582685,0.0013716626,0.0006417774],"domain_scores_gemma":[0.99512756,0.0010968092,0.0002530929,0.0027195017,0.00064093806,0.00016210492],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0024513246,0.00038305853,0.00042837992,0.00015227025,0.0023259583,0.00044651038,0.0039178245,0.00006390057,0.00026682738],"category_scores_gemma":[0.0004867352,0.00025014908,0.00012492071,0.001404038,0.00052355434,0.0007130652,0.00076572667,0.0005406384,0.000013081541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000794569,0.0016152087,0.10104906,0.00041589557,0.00020827612,0.000025343752,0.10101311,0.0022884014,0.001279929,0.6573207,0.00046501085,0.13352452],"study_design_scores_gemma":[0.0024920697,0.004275713,0.2930276,0.00028579938,0.00026234702,0.00009334836,0.20787923,0.03368642,0.026343841,0.39420274,0.033722464,0.0037284372],"about_ca_topic_score_codex":0.0032955834,"about_ca_topic_score_gemma":0.0065182517,"teacher_disagreement_score":0.26311794,"about_ca_system_score_codex":0.00018092278,"about_ca_system_score_gemma":0.0004914885,"threshold_uncertainty_score":0.99999505},"labels":[],"label_agreement":null},{"id":"W4230606177","doi":"10.4018/9781599049410.ch131","title":"Explaining Algorithms","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.052750584716825324,"score_gpt":0.26914162199014713,"score_spread":0.21639103727332182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230606177","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063460698,0.00028519362,0.13824372,0.000053316566,0.0015510444,0.00024205439,0.000018470375,0.0005042824,0.8590956],"genre_scores_gemma":[0.107797466,0.000052485455,0.11114382,0.0033390482,0.0023511709,0.00013595614,0.000009457653,0.00030270475,0.7748679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99704885,0.000027974458,0.00059041387,0.001028935,0.0005884505,0.00071540056],"domain_scores_gemma":[0.9975809,0.00007966998,0.00032055768,0.0014863104,0.00022516475,0.0003074276],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002652657,0.0005888766,0.00052155857,0.00012644686,0.0002219243,0.00029059156,0.0022824807,0.00049620523,0.000116417585],"category_scores_gemma":[0.00003963169,0.0006164984,0.000281055,0.000046769987,0.00015429623,0.0002841382,0.00086728134,0.0004449711,0.0030349572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005335741,0.000007512004,0.0000022114136,0.00001022356,0.000042487845,0.0003013929,0.00034713134,0.0000030360263,0.000008273137,0.93359095,0.0015386911,0.06414277],"study_design_scores_gemma":[0.00007076454,0.0001392214,0.0000030153037,0.00015783499,0.00002205105,0.0000943641,0.000020500893,0.00057186966,0.0009976226,0.90911,0.08809877,0.00071399834],"about_ca_topic_score_codex":0.00021655379,"about_ca_topic_score_gemma":0.0001002621,"teacher_disagreement_score":0.10779112,"about_ca_system_score_codex":0.00021847952,"about_ca_system_score_gemma":0.00028702384,"threshold_uncertainty_score":0.99962866},"labels":[],"label_agreement":null},{"id":"W4240690026","doi":"10.31234/osf.io/ygr4c","title":"Artificial Cognition: How Experimental Psychology Can Help Generate Explainable Artificial Intelligence","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of 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; Artificial intelligence; Field (mathematics); Computer science; Transparency (behavior); Black box; Artificial neural network; Artificial psychology; Cognitive science; Psychology; Management science; Artificial Intelligence System; Engineering","score_opus":0.11362926444542683,"score_gpt":0.342895723843789,"score_spread":0.2292664593983622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240690026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041708723,0.0011326076,0.9238595,0.015389655,0.007940743,0.0012392415,0.00003334435,0.00096861925,0.007727573],"genre_scores_gemma":[0.9356047,0.00017146491,0.05790306,0.002766152,0.0015640657,0.0006690573,0.0002422055,0.00009630742,0.0009830166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.991918,0.0006385722,0.0014293368,0.0032470555,0.001078974,0.001688042],"domain_scores_gemma":[0.9948116,0.00019792034,0.00057262013,0.0029240055,0.00094062864,0.0005532144],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009936428,0.0010923272,0.001066628,0.00059884967,0.00076276495,0.003452426,0.003492026,0.0009472066,0.0010921988],"category_scores_gemma":[0.0002358638,0.0012099762,0.0005216029,0.0012395717,0.00046006657,0.0010191726,0.0038196635,0.0015337121,0.0005140488],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016401871,0.0030239057,0.000026369402,0.00027793698,0.00042621655,0.0032598316,0.010752872,0.00820102,0.20063949,0.63801384,0.0065121795,0.12870233],"study_design_scores_gemma":[0.00003483857,0.00023921365,0.0000047422463,0.00012566034,0.00003323403,0.00011469187,0.005432754,0.040912453,0.85228693,0.09877731,0.0007451509,0.001293014],"about_ca_topic_score_codex":0.0004934801,"about_ca_topic_score_gemma":0.0010209992,"teacher_disagreement_score":0.8938959,"about_ca_system_score_codex":0.00039330905,"about_ca_system_score_gemma":0.00085678,"threshold_uncertainty_score":0.99982095},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Encoder; Computer science; Generative grammar; Artificial intelligence; Speech recognition; Electrical engineering; Engineering; Voltage","score_opus":0.054660225641968346,"score_gpt":0.27533200607630126,"score_spread":0.22067178043433291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243640523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039230645,0.00013291306,0.9534251,0.0024535956,0.0023127196,0.00051680824,0.00002104734,0.00024091611,0.0016662526],"genre_scores_gemma":[0.98280495,0.00039099605,0.01567179,0.00031168497,0.00029699446,0.000031171596,0.00003745784,0.000022594908,0.00043236246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978786,0.00018051796,0.00036258242,0.0009452221,0.00032260487,0.00031044427],"domain_scores_gemma":[0.9990524,0.00015091021,0.00009798581,0.00037380957,0.00011880045,0.00020609022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008038589,0.0002788612,0.00033518628,0.00009800485,0.00014304824,0.00059677195,0.00057627575,0.00025826241,0.000027409471],"category_scores_gemma":[0.000089151385,0.00027038073,0.00006880955,0.00019165095,0.00006528574,0.00040748983,0.000947942,0.0003937712,0.000034935012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101684185,0.00011398512,0.0015621266,0.00041574895,0.00017315146,0.00007308945,0.0042647044,0.00004590703,0.008239611,0.90138286,0.0021385734,0.081488535],"study_design_scores_gemma":[0.0007185218,0.0006748633,0.014633647,0.00021548041,0.00009966759,0.000049816623,0.0004957974,0.29007867,0.045836795,0.64000714,0.0048251897,0.002364428],"about_ca_topic_score_codex":0.0027112325,"about_ca_topic_score_gemma":0.0011359955,"teacher_disagreement_score":0.9435743,"about_ca_system_score_codex":0.00004213333,"about_ca_system_score_gemma":0.0001168103,"threshold_uncertainty_score":0.99997485},"labels":[],"label_agreement":null},{"id":"W4254583338","doi":"10.1109/msp.2021.3049658","title":"IEEE Signal Processing Magazine Special Issue on Explainability in Data Science: Interpretability, Reproducibility, and Replicability","year":2021,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Baycrest Hospital","funders":"","keywords":"Interpretability; Reproducibility; Computer science; Signal processing; SIGNAL (programming language); Data science; Artificial intelligence; Digital signal processing; Computer hardware; Mathematics; Statistics","score_opus":0.055449884744148754,"score_gpt":0.333217759885401,"score_spread":0.27776787514125223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254583338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7540669,0.0014308536,0.19859463,0.013599425,0.0021406808,0.0029219014,0.00008740868,0.0012047937,0.025953447],"genre_scores_gemma":[0.98322535,0.00002282065,0.01333513,0.000626728,0.002131443,0.000056472807,0.000018647665,0.000055610453,0.0005278039],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98578805,0.0006793137,0.0019144596,0.00814881,0.0018715719,0.0015977962],"domain_scores_gemma":[0.98925114,0.00057695527,0.0005382387,0.007278181,0.0017987794,0.00055668066],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.015347349,0.00077849225,0.0010246498,0.0005484663,0.00096040004,0.0019304557,0.004267652,0.00026601233,0.00029036685],"category_scores_gemma":[0.003479051,0.0007741958,0.000120482415,0.0048496695,0.0023673633,0.006605538,0.0025847754,0.0012555856,0.00019795186],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034658893,0.0020018185,0.0064018583,0.001082445,0.000013951345,0.0003354548,0.0036898074,0.001048761,0.083415836,0.0005333307,0.0015958116,0.89953434],"study_design_scores_gemma":[0.0011933061,0.0008800441,0.018275423,0.0013212197,0.00006556028,0.00040267393,0.00081469765,0.5556823,0.35526687,0.049881853,0.01372172,0.0024943543],"about_ca_topic_score_codex":0.00006543768,"about_ca_topic_score_gemma":0.0005204309,"teacher_disagreement_score":0.89704,"about_ca_system_score_codex":0.00077812216,"about_ca_system_score_gemma":0.0034154907,"threshold_uncertainty_score":0.9994709},"labels":[],"label_agreement":null},{"id":"W4283267930","doi":"10.1016/j.knosys.2022.109287","title":"Augmented Score-CAM: High resolution visual interpretations for deep neural networks","year":2022,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep neural networks; Resolution (logic); Computer vision; Machine learning","score_opus":0.0289454123552909,"score_gpt":0.28551196957289804,"score_spread":0.2565665572176071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283267930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010939149,0.0013480433,0.9795011,0.0002961547,0.0056311605,0.0013239331,0.000016635051,0.00044166105,0.0005021249],"genre_scores_gemma":[0.9953883,0.0000011090573,0.0018644999,0.00016785432,0.0003559986,0.0015832981,0.00008848742,0.000037924863,0.0005124921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968401,0.00066445733,0.00069400447,0.00072130875,0.00039344205,0.00068665866],"domain_scores_gemma":[0.9978414,0.0006185919,0.00027273843,0.0006923359,0.00040030247,0.00017461859],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011138413,0.00027042883,0.00032823865,0.0003561155,0.0011029186,0.00034973043,0.0011957693,0.00008368213,0.000039625],"category_scores_gemma":[0.00013775734,0.00029369787,0.00018262016,0.0012317335,0.0000775806,0.000423354,0.0003508148,0.00029969375,0.00006806871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009416586,0.000332596,0.00029437145,0.000081323764,0.00003716167,0.00000898326,0.0010569714,0.94395936,0.0004098515,0.042651676,0.0034976352,0.007575899],"study_design_scores_gemma":[0.00038488625,0.0005671448,0.00006611009,0.00004190836,0.000019268506,0.000010763143,0.0004358547,0.99286073,0.00058437773,0.00032210402,0.00439527,0.00031159905],"about_ca_topic_score_codex":0.0002779284,"about_ca_topic_score_gemma":0.00024606293,"teacher_disagreement_score":0.9844492,"about_ca_system_score_codex":0.0006001924,"about_ca_system_score_gemma":0.00018154416,"threshold_uncertainty_score":0.99995154},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016587815992635566,"score_gpt":0.22177399274944726,"score_spread":0.2051861767568117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283268983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017269464,0.0003681271,0.95813566,0.014157027,0.0005155742,0.00030271936,0.0000087315,0.0012949972,0.007947723],"genre_scores_gemma":[0.97722113,0.00002676316,0.021182096,0.0011330572,0.000021435739,0.00018558261,0.000011479516,0.0000057245466,0.0002127012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877125,0.00004265874,0.0004258875,0.00020093737,0.00022337557,0.00033589063],"domain_scores_gemma":[0.9992059,0.00008447868,0.00015394462,0.00044147158,0.00006243679,0.000051779014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031371278,0.00013337823,0.00014091836,0.00087608886,0.0011454981,0.00041029294,0.0010452477,0.00010255838,0.00019417262],"category_scores_gemma":[0.00014180521,0.0001420718,0.000028438659,0.0017329032,0.00027572192,0.006321644,0.0012554276,0.00035725467,0.0001584216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009550878,0.000017672926,0.000087004875,0.000009187904,0.0000050580447,0.000005251777,0.001939017,0.00033994112,0.00003209048,0.85035825,0.00047363192,0.14672332],"study_design_scores_gemma":[0.000025948948,0.00017538424,0.000023736788,0.00000467402,0.000002203161,0.00006489653,0.0095677925,0.023934232,0.043410726,0.8071698,0.11542198,0.00019861695],"about_ca_topic_score_codex":0.000015521504,"about_ca_topic_score_gemma":0.0000019628917,"teacher_disagreement_score":0.9599517,"about_ca_system_score_codex":0.000035248886,"about_ca_system_score_gemma":0.00010834577,"threshold_uncertainty_score":0.88103616},"labels":[],"label_agreement":null},{"id":"W4283382951","doi":"10.3389/fnins.2022.883385","title":"Designing for Confidence: The Impact of Visualizing Artificial Intelligence Decisions","year":2022,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CLARITY; Computer science; Transparency (behavior); Artificial intelligence; Cognition; Visualization; Presentation (obstetrics); Human–computer interaction; Knowledge management; Psychology","score_opus":0.09566457943843523,"score_gpt":0.36569619728714803,"score_spread":0.27003161784871277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283382951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014595516,0.00014685454,0.9820894,0.00037843466,0.0019440524,0.00061015435,0.000009864415,0.000050599956,0.00017509569],"genre_scores_gemma":[0.94537145,0.000024458304,0.054094397,0.00023761357,0.000027486178,0.0001693904,4.3416458e-7,0.000012194604,0.00006256134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970736,0.0003047571,0.00062259217,0.00069484586,0.0006637158,0.00064051716],"domain_scores_gemma":[0.9978677,0.0008724061,0.00027085675,0.0007668239,0.00012542514,0.00009679787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002333309,0.00018028273,0.00025775665,0.00041410056,0.00097235735,0.00020997811,0.00362271,0.00003209348,0.000016708018],"category_scores_gemma":[0.001825304,0.000146489,0.00018217824,0.0028638886,0.00041456794,0.0006854103,0.00077962363,0.0003196608,0.0000017303659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016703997,0.0005223435,0.004426767,0.000013937994,0.000011176939,0.000063843574,0.009932887,0.4531744,0.104865156,0.306034,0.010738745,0.1100497],"study_design_scores_gemma":[0.000033671782,0.0005068909,0.00050944195,0.000015996055,0.0000029707949,0.000019847375,0.0023526668,0.81542206,0.04145249,0.13907324,0.00041498718,0.00019573614],"about_ca_topic_score_codex":0.00015884102,"about_ca_topic_score_gemma":0.000007665234,"teacher_disagreement_score":0.93077594,"about_ca_system_score_codex":0.00020737697,"about_ca_system_score_gemma":0.00040422063,"threshold_uncertainty_score":0.7478685},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Fidelity; Transparency (behavior); Process (computing)","score_opus":0.08447499056083677,"score_gpt":0.3329501289657329,"score_spread":0.24847513840489613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283521686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025191035,0.00010574023,0.9605568,0.012613041,0.0005363477,0.00076285604,0.000024683975,0.00016169333,0.000047788995],"genre_scores_gemma":[0.9058504,0.000009060652,0.08767409,0.0057980563,0.000058464106,0.0005676825,0.000009651923,0.000025084702,0.000007474947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964392,0.00070772663,0.00067101396,0.00079286424,0.0006591443,0.00073001947],"domain_scores_gemma":[0.9963968,0.0018190935,0.00011286592,0.0012538022,0.00016744595,0.00025004064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022493606,0.00024681215,0.00024965507,0.0002939192,0.00067398127,0.0002666684,0.0025296898,0.000059882226,0.000027283133],"category_scores_gemma":[0.0013876443,0.00023556114,0.000076212695,0.0015726907,0.00009525816,0.00041426322,0.00083464105,0.0006464463,0.00005708255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026215333,0.00030731998,0.0007389706,0.000010005198,0.0000027797603,0.00006551509,0.008919026,0.81502944,0.00019886857,0.10872331,0.00012460965,0.065853916],"study_design_scores_gemma":[0.00002229593,0.00037680374,0.000056497847,0.000019734514,0.0000029970904,0.0000040733817,0.0024057843,0.90709585,0.014129995,0.07542839,0.00018769893,0.00026988727],"about_ca_topic_score_codex":0.00070155115,"about_ca_topic_score_gemma":0.0013760725,"teacher_disagreement_score":0.8806594,"about_ca_system_score_codex":0.00041031835,"about_ca_system_score_gemma":0.00040809595,"threshold_uncertainty_score":0.9605905},"labels":[],"label_agreement":null},{"id":"W4283800998","doi":"10.1609/aaai.v36i11.21452","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"BC Cancer Foundation; Compute Canada; Nvidia","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Leverage (statistics); Modal; Machine learning; Metric (unit); Feature (linguistics); Medical imaging; Data mining; Engineering","score_opus":0.2237399218700203,"score_gpt":0.4682253697246115,"score_spread":0.2444854478545912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283800998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03044361,0.00012398437,0.93924195,0.015237742,0.003240296,0.0008612267,0.00001052739,0.00092270575,0.0099179745],"genre_scores_gemma":[0.83318406,0.000009324244,0.1449094,0.017812103,0.0005552571,0.00037729985,0.000018564819,0.000068265006,0.0030657253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99207664,0.0011109511,0.001385839,0.0014748273,0.0027022501,0.0012495251],"domain_scores_gemma":[0.9966084,0.0009778894,0.00033978873,0.0012208949,0.00031382695,0.00053921575],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009532185,0.00036107862,0.00044879623,0.0002838503,0.0016860112,0.00037865856,0.0026808062,0.00008894761,0.0011423168],"category_scores_gemma":[0.0029967348,0.0003621658,0.00021786976,0.0010175117,0.00017721897,0.0007901887,0.00267439,0.00119714,0.00018633348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007200803,0.0015776369,0.004089578,0.000033734388,0.00007891975,0.0016221283,0.0038546596,0.008861851,0.00120659,0.08074598,0.008242092,0.8896148],"study_design_scores_gemma":[0.00062501285,0.0004664523,0.00015222748,0.00004123866,0.0000096936865,0.00008462306,0.0022346503,0.98537296,0.0012944337,0.0027369924,0.0065137967,0.00046793747],"about_ca_topic_score_codex":0.0016636829,"about_ca_topic_score_gemma":0.00016252529,"teacher_disagreement_score":0.97651106,"about_ca_system_score_codex":0.00055243634,"about_ca_system_score_gemma":0.0007903617,"threshold_uncertainty_score":0.99988306},"labels":[],"label_agreement":null},{"id":"W4283822641","doi":"10.1609/aaai.v36i11.21569","title":"Model AI Assignments 2022","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Session (web analytics); Variety (cybernetics); Dissemination; Computer science; Core (optical fiber); Artificial intelligence; Multimedia; World Wide Web; Telecommunications","score_opus":0.04123004811097956,"score_gpt":0.2843398882818237,"score_spread":0.24310984017084417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283822641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037067141,0.000027838156,0.9566481,0.0033305127,0.00033895823,0.000119936005,0.0000020798086,0.0002172296,0.03560864],"genre_scores_gemma":[0.95371693,0.0000027459837,0.020174997,0.0058397856,0.000020492076,0.000096836266,0.0000016841061,0.000009058568,0.02013747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986039,0.0000677807,0.00016938531,0.0003478711,0.0005032769,0.00030777723],"domain_scores_gemma":[0.999255,0.00003167195,0.000037460006,0.00056182087,0.000035424062,0.00007862369],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036184717,0.00008637087,0.00008179806,0.00008915956,0.0004322771,0.00010875304,0.0012918273,0.00001554562,0.0010769108],"category_scores_gemma":[0.000015765641,0.00008889512,0.000046097288,0.0004624423,0.000017746133,0.0005272369,0.0011643501,0.00018963938,0.0002848753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003838965,0.00014684246,0.00015994758,0.0000017987435,0.000008364249,0.00003082754,0.00077091187,0.1366097,0.0044839084,0.8006827,0.04204679,0.015054325],"study_design_scores_gemma":[0.000035534085,0.00005513281,0.0000105837535,4.563716e-7,9.892669e-7,0.000005851404,0.00015741636,0.9167258,0.008840214,0.063368484,0.010679787,0.00011973422],"about_ca_topic_score_codex":0.000060126193,"about_ca_topic_score_gemma":0.000009780026,"teacher_disagreement_score":0.95001024,"about_ca_system_score_codex":0.00013710352,"about_ca_system_score_gemma":0.00009692983,"threshold_uncertainty_score":0.99983627},"labels":[],"label_agreement":null},{"id":"W4284682843","doi":"10.1145/3511047.3537678","title":"Creating a User Model to Support User-specific Explanations of AI Systems","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Transparency (behavior); Position paper; User modeling; Context (archaeology); Human–computer interaction; Data science; Black box; User interface; Artificial intelligence; World Wide Web; Computer security","score_opus":0.0664910485843432,"score_gpt":0.3022684270206357,"score_spread":0.23577737843629254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284682843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025296917,0.000023643235,0.9553935,0.0009860625,0.00033445365,0.00036672843,0.000015688203,0.00017594318,0.01740705],"genre_scores_gemma":[0.95976555,0.000002296887,0.029901152,0.0006124936,0.000031328076,0.0002009687,0.0000051559746,0.000014339887,0.009466684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998114,0.00008386507,0.00047130336,0.0004140623,0.0005779402,0.00033883867],"domain_scores_gemma":[0.9987095,0.000118985205,0.000098626115,0.00073837186,0.00020792935,0.00012656399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056430034,0.0001230915,0.0001919743,0.00027573737,0.00037919855,0.00016834935,0.001186477,0.000026114682,0.0002888222],"category_scores_gemma":[0.00003915981,0.00012809296,0.000062864296,0.0009362822,0.00001970945,0.000607366,0.0006635242,0.00015691727,0.00012560935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034518623,0.00006629968,0.00024422206,0.000006561652,0.000006118645,0.000008620913,0.0023173206,0.3597695,0.002068675,0.6198561,0.015184664,0.00046842505],"study_design_scores_gemma":[0.000071259296,0.00022475337,0.000036333025,0.0000099584995,0.0000034244563,0.000019229621,0.0033455552,0.9473051,0.012114982,0.002207457,0.03441666,0.0002452913],"about_ca_topic_score_codex":0.000494058,"about_ca_topic_score_gemma":0.00006274526,"teacher_disagreement_score":0.9344687,"about_ca_system_score_codex":0.00014465075,"about_ca_system_score_gemma":0.00016652179,"threshold_uncertainty_score":0.5223479},"labels":[],"label_agreement":null},{"id":"W4285137928","doi":"10.1007/978-3-031-09342-5_6","title":"Explainable Clinical Decision Support: Towards Patient-Facing Explanations for Education and Long-Term Behavior Change","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Term (time); Behavior change; Work (physics); Computer science; Psychology; Applied psychology; Knowledge management; Medicine; Social psychology","score_opus":0.07493354672405587,"score_gpt":0.3572985281964533,"score_spread":0.2823649814723974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285137928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029912696,0.0005164859,0.9884394,0.00055754115,0.00481265,0.0020660767,0.000027379287,0.0001283174,0.00046091227],"genre_scores_gemma":[0.27306688,0.0005419626,0.71765137,0.004245214,0.0013842972,0.0022274482,0.0001416123,0.000119329285,0.0006218889],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954604,0.00006206201,0.00096861133,0.0018214309,0.0009608371,0.00072667876],"domain_scores_gemma":[0.9966561,0.00090534275,0.00045782252,0.001237951,0.00046405868,0.00027869723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014654702,0.0004738073,0.00052829826,0.0010288332,0.0008043261,0.00067333545,0.002152826,0.00028807073,0.00011239892],"category_scores_gemma":[0.00033073715,0.0004859455,0.00017266539,0.00058911333,0.0004032478,0.0017204786,0.0017659866,0.00066719466,0.000019579782],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000098381215,0.00013568319,0.00063655374,0.00003146158,0.000004914438,0.0000458939,0.0016247131,0.00033680513,0.000012567676,0.011964034,0.000046125464,0.9851514],"study_design_scores_gemma":[0.0023388495,0.010732395,0.020517262,0.002929782,0.00030424644,0.0014627789,0.00007278314,0.4072433,0.008165436,0.44093913,0.09632084,0.008973206],"about_ca_topic_score_codex":0.00008208708,"about_ca_topic_score_gemma":0.0002463221,"teacher_disagreement_score":0.9761782,"about_ca_system_score_codex":0.00047677426,"about_ca_system_score_gemma":0.0011327203,"threshold_uncertainty_score":0.9997592},"labels":[],"label_agreement":null},{"id":"W4285218816","doi":"10.1007/978-3-031-09342-5_9","title":"Extracting Surrogate Decision Trees from Black-Box Models to Explain the Temporal Importance of Clinical Features in Predicting Kidney Graft Survival","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Black box; Decision tree; Artificial intelligence; Transparency (behavior); Machine learning; Kidney transplant; Kidney transplantation; Transplantation; Medicine; Internal medicine","score_opus":0.06477605988601004,"score_gpt":0.3294905642090311,"score_spread":0.26471450432302107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285218816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026845222,0.00032374318,0.9656719,0.0016041521,0.0032469332,0.00081734423,0.000038568214,0.00012361133,0.0013285084],"genre_scores_gemma":[0.78839326,0.000071561546,0.2093481,0.0014472605,0.0005468664,0.00002752024,0.000013750343,0.000055573822,0.00009613725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917391,0.00035353296,0.0022147049,0.0024714351,0.0022264759,0.0009947439],"domain_scores_gemma":[0.9892511,0.0066631185,0.0010646881,0.0023251192,0.00031326845,0.00038273368],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0073062936,0.00067659415,0.0011341216,0.000843711,0.00046043098,0.00049570017,0.0065918597,0.00038440776,0.000054699518],"category_scores_gemma":[0.0020213013,0.0005556912,0.0003136914,0.0015898186,0.0008100626,0.0014505716,0.003471509,0.0022179103,0.000012126064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012974357,0.00014577297,0.020024054,0.000026010348,0.000030477117,0.00038673068,0.009360828,0.6122783,0.000213039,0.019630764,0.000110595705,0.33766374],"study_design_scores_gemma":[0.000302646,0.00029690732,0.0023901898,0.00073512056,0.000011633869,0.000018663264,0.000031687898,0.7786322,0.0013977241,0.2146493,0.00075523375,0.0007786395],"about_ca_topic_score_codex":0.0018901373,"about_ca_topic_score_gemma":0.009843014,"teacher_disagreement_score":0.76154804,"about_ca_system_score_codex":0.00033183824,"about_ca_system_score_gemma":0.001100682,"threshold_uncertainty_score":0.99968946},"labels":[],"label_agreement":null},{"id":"W4285345709","doi":"10.1109/smc52423.2021.9658985","title":"Cause and Effect: Concept-based Explanation of Neural Networks","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Computer science; Negation; Causality (physics); Artificial intelligence; Artificial neural network; Task (project management); Set (abstract data type); Representation (politics); Machine learning; Class (philosophy); Focus (optics); Theoretical computer science","score_opus":0.04856461375304874,"score_gpt":0.29493585116079446,"score_spread":0.24637123740774572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285345709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66785717,0.0020679934,0.3034153,0.0029666943,0.006578806,0.00088864885,0.00007912915,0.00014427784,0.016001983],"genre_scores_gemma":[0.9981884,0.00018383302,0.000277239,0.0002143407,0.00017673193,0.00002916471,0.000030984866,0.000012475401,0.0008868815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997982,0.00023709367,0.00048392452,0.0005309121,0.00051810074,0.0002479254],"domain_scores_gemma":[0.9982593,0.00036222138,0.00024478557,0.00037243625,0.0006385057,0.00012275133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003310128,0.0002224363,0.00031196311,0.000138908,0.00008941947,0.0004467072,0.00045054802,0.00012116278,0.00006702618],"category_scores_gemma":[0.00009606589,0.00021904652,0.000052420783,0.00020381054,0.00013146008,0.00027127558,0.000116143914,0.00019221315,0.000014274085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095697345,0.00019990864,0.0053443755,0.0001565051,0.00019020395,0.00032451027,0.0012320388,0.028990423,0.0060968148,0.93292767,0.0012496298,0.023192246],"study_design_scores_gemma":[0.0004062005,0.00025544834,0.0008312469,0.00021810624,0.000020225143,0.00004628547,0.00033885386,0.97736156,0.018711967,0.0006747614,0.00086839095,0.0002669291],"about_ca_topic_score_codex":0.000253415,"about_ca_topic_score_gemma":0.00013448432,"teacher_disagreement_score":0.9483712,"about_ca_system_score_codex":0.000050731487,"about_ca_system_score_gemma":0.00009255554,"threshold_uncertainty_score":0.8932458},"labels":[],"label_agreement":null},{"id":"W4286901498","doi":"","title":"SHAFF: Fast and consistent SHApley eFfect estimates via random Forests","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Random forest; Mathematics; Econometrics; Economics; Mathematical economics; Computer science; Artificial intelligence","score_opus":0.013767261746613881,"score_gpt":0.24077517706581417,"score_spread":0.22700791531920028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286901498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09996544,0.0025552497,0.8838697,0.0055254726,0.00041980794,0.0007650842,0.000013783657,0.00041271633,0.00647275],"genre_scores_gemma":[0.90425974,0.00038368077,0.093743965,0.00013863503,0.000023527236,0.0001670433,0.00016575817,0.00004638661,0.0010712836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922384,0.004439335,0.00070946966,0.0014328233,0.0005817164,0.0005982388],"domain_scores_gemma":[0.9898921,0.0042653466,0.0005009785,0.003078559,0.0019293692,0.0003336414],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0059864307,0.00053243473,0.0007240389,0.00024081867,0.0005401428,0.0020135604,0.0023486372,0.0003288755,0.00007395012],"category_scores_gemma":[0.0028513202,0.0005441351,0.0002908444,0.0005105217,0.0003890649,0.0004549601,0.0046471446,0.0007159261,0.00005521627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116705814,0.0016464075,0.02846964,0.0018748344,0.000696562,0.0003371985,0.047756,0.003262509,0.014651442,0.24798279,0.0016002579,0.65160567],"study_design_scores_gemma":[0.0008134104,0.000002454299,0.0042581274,0.0026135892,0.000085680535,0.00009306301,0.00013139033,0.7467334,0.2323057,0.011210146,0.00084911165,0.00090386166],"about_ca_topic_score_codex":0.0018182065,"about_ca_topic_score_gemma":0.004850377,"teacher_disagreement_score":0.8042943,"about_ca_system_score_codex":0.00013395702,"about_ca_system_score_gemma":0.00030599214,"threshold_uncertainty_score":0.999701},"labels":[],"label_agreement":null},{"id":"W4287181747","doi":"10.48550/arxiv.2105.07099","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Locality; Artificial intelligence; Feature (linguistics); Reinforcement; State (computer science); Function (biology); Action (physics); Machine learning; Engineering; Algorithm","score_opus":0.060631472379574926,"score_gpt":0.19499880798693472,"score_spread":0.1343673356073598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287181747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026201224,0.000024612395,0.9688629,0.00046502793,0.00045810858,0.00040117034,0.0000045232723,0.0003877111,0.0031947102],"genre_scores_gemma":[0.9941153,0.000035776266,0.003345736,0.0007328605,0.000030396219,0.0000045354086,0.00008713021,0.00003125979,0.0016169966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706155,0.00034524486,0.00025851556,0.0014707781,0.00026562755,0.000598268],"domain_scores_gemma":[0.9974758,0.0001671121,0.00027967966,0.0014643846,0.00039157635,0.00022143676],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045062962,0.0004577365,0.00041234703,0.00046831975,0.00030323068,0.00046592293,0.0015173794,0.0003075257,0.00005977086],"category_scores_gemma":[0.000048721933,0.0005625908,0.00032873166,0.0008333242,0.000073960306,0.00085847714,0.0006582514,0.0012096487,0.000077358585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009731867,0.000101793186,0.000033827127,0.000094214236,0.000037185306,0.00044035556,0.00054734224,0.98334944,0.00009758074,0.014801224,0.00010732595,0.00029236285],"study_design_scores_gemma":[0.00025981717,0.00018845503,0.0000075039543,0.00042047008,0.00003528842,8.3161666e-7,0.00023743366,0.98373574,0.006787883,0.007632725,0.0001502922,0.00054354744],"about_ca_topic_score_codex":0.0003844966,"about_ca_topic_score_gemma":0.00007951836,"teacher_disagreement_score":0.9679141,"about_ca_system_score_codex":0.00064750685,"about_ca_system_score_gemma":0.00061003986,"threshold_uncertainty_score":0.99968255},"labels":[],"label_agreement":null},{"id":"W4287887550","doi":"10.18653/v1/2022.trustnlp-1.8","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.15246286036077017,"score_gpt":0.36992961826150667,"score_spread":0.2174667579007365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287887550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012393127,0.00034699065,0.9704324,0.0050919917,0.00029030885,0.000873155,0.0000011807635,0.000084853535,0.0104859695],"genre_scores_gemma":[0.89082634,0.00001704026,0.107733816,0.00026230217,0.000015039639,0.0010190626,1.7487794e-7,0.000008612035,0.00011759613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750745,0.0006998782,0.0004261557,0.0005917319,0.00038683278,0.00038795482],"domain_scores_gemma":[0.9978815,0.0006415298,0.00008915761,0.0012116191,0.00010774279,0.00006844912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045432416,0.00013491846,0.00023204097,0.00016221097,0.00022533811,0.00004688001,0.0019967319,0.00003077366,0.000038079186],"category_scores_gemma":[0.00018189345,0.00010555364,0.00007173675,0.0009142236,0.00005209803,0.0004925868,0.0018175009,0.00024008972,0.0000061594737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010431165,0.000105508065,0.000030387446,0.000019631447,0.0000043932396,0.0000035402975,0.011399326,0.038976066,0.0027197946,0.55055285,0.000020013505,0.39615807],"study_design_scores_gemma":[0.00007298311,0.00020422389,0.00017587113,0.0000059865242,0.0000024054564,0.0000052065247,0.025169928,0.53600883,0.08307361,0.35267013,0.0023749333,0.00023589708],"about_ca_topic_score_codex":0.00086635444,"about_ca_topic_score_gemma":0.00031874658,"teacher_disagreement_score":0.8784332,"about_ca_system_score_codex":0.00016471748,"about_ca_system_score_gemma":0.00008931754,"threshold_uncertainty_score":0.43043527},"labels":[],"label_agreement":null},{"id":"W4287958231","doi":"10.1007/s00146-022-01536-6","title":"An explanation space to align user studies with the technical development of Explainable AI","year":2022,"lang":"en","type":"article","venue":"AI & Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Human–computer interaction; Context (archaeology); Process (computing); Formative assessment; Architecture; Situated; Space (punctuation); User interface; Interface (matter); Intersection (aeronautics); Cognitive architecture; Task (project management); Domain (mathematical analysis); End user; Perspective (graphical); Cognition; World Wide Web; Artificial intelligence; Engineering; Systems engineering","score_opus":0.03282383958958687,"score_gpt":0.31780738669493275,"score_spread":0.2849835471053459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287958231","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15714195,0.00019642033,0.81443614,0.027028905,0.00015856062,0.00062762806,0.0000025149884,0.000202129,0.00020575084],"genre_scores_gemma":[0.92516714,0.000011013693,0.06935276,0.004767219,0.000027962618,0.00033523797,0.0000026453558,0.000012987477,0.00032302784],"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982675,0.00011509579,0.0002494411,0.00040088344,0.00063117663,0.00033594348],"domain_scores_gemma":[0.99881375,0.00012898415,0.00010014329,0.00061474193,0.00027086295,0.00007154246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011578681,0.00014188593,0.00017393904,0.000037022368,0.0009119227,0.00008054914,0.001078516,0.00003122192,0.000018766043],"category_scores_gemma":[0.000029506144,0.00010328341,0.000062197985,0.00089504285,0.000089765796,0.0005284343,0.0004891121,0.00021158929,0.000013270527],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070799855,0.000767538,0.0012664158,0.00007508058,0.0003138822,0.000028320197,0.39235902,0.032699768,0.044292953,0.24142161,0.27289906,0.013805576],"study_design_scores_gemma":[0.0004530398,0.0017265165,0.0019105201,0.00006377665,0.000045687822,0.0000407188,0.26688495,0.018140413,0.38234058,0.0075068157,0.3197429,0.0011440748],"about_ca_topic_score_codex":0.00006717202,"about_ca_topic_score_gemma":0.00017532043,"teacher_disagreement_score":0.7680252,"about_ca_system_score_codex":0.00030253155,"about_ca_system_score_gemma":0.00023746102,"threshold_uncertainty_score":0.70138645},"labels":[],"label_agreement":null},{"id":"W4289119129","doi":"","title":"Objective-Driven Ensembles: Bridging the Gap Between Interpretable Sparsity and Algorithmic Prediction","year":2018,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interpretability; Selection (genetic algorithm); Computer science; Machine learning; Model selection; Artificial intelligence; Regression; Feature selection; Ensemble learning; Data mining; Mathematics; Statistics","score_opus":0.08310780070935496,"score_gpt":0.2906511631220702,"score_spread":0.2075433624127152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289119129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6089363,0.0003953388,0.38465592,0.0009188641,0.0025332114,0.0012348213,0.00006965432,0.00026765405,0.0009882268],"genre_scores_gemma":[0.99237025,0.0007039854,0.002752164,0.00031993198,0.0029373323,0.00011898204,0.00002766351,0.00008366842,0.0006860348],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99199635,0.0010125089,0.0014587534,0.002974398,0.00094372354,0.001614253],"domain_scores_gemma":[0.99381506,0.0008487211,0.0010191789,0.0029522732,0.000891353,0.00047339103],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025325576,0.0010772818,0.001113353,0.00040017397,0.0021610162,0.0011987346,0.0035913538,0.00071793905,0.000113973336],"category_scores_gemma":[0.0005410923,0.000984607,0.0003907331,0.0010101517,0.0014523942,0.0017804758,0.0069881445,0.0021984724,0.0010308519],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007934154,0.00021031847,0.91736716,0.00029156182,0.0007285107,0.000071494374,0.02728703,0.0021794704,0.0029719744,0.00067106436,0.001195889,0.0469462],"study_design_scores_gemma":[0.0003802156,0.0007962222,0.41129014,0.0017775779,0.0005027833,0.000112772075,0.0019923665,0.52353156,0.047211304,0.0073785726,0.0032838401,0.0017426529],"about_ca_topic_score_codex":0.0024491213,"about_ca_topic_score_gemma":0.00021050875,"teacher_disagreement_score":0.52135205,"about_ca_system_score_codex":0.00065059593,"about_ca_system_score_gemma":0.0005690776,"threshold_uncertainty_score":0.9998381},"labels":[],"label_agreement":null},{"id":"W4290994229","doi":"10.31222/osf.io/uxf39","title":"Do Pre-Registration and Pre-analysis Plans Reduce p-Hacking and Publication Bias?","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Credibility; Hacker; Publication bias; Randomized controlled trial; Test (biology); Point (geometry); Statistics; Actuarial science; Psychology; Medicine; Computer science; Meta-analysis; Political science; Economics; Internal medicine; Computer security; Law; Mathematics","score_opus":0.08586230330199067,"score_gpt":0.3360005757306544,"score_spread":0.2501382724286637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290994229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16702683,0.00038696994,0.8146404,0.004885984,0.00032004595,0.00075792766,0.000024939465,0.00035845564,0.011598465],"genre_scores_gemma":[0.9790472,0.00017757004,0.017599054,0.00018034567,0.000068868416,0.00018341086,0.0001082522,0.000012975692,0.002622316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972076,0.00021193195,0.0005816191,0.001224618,0.0004950032,0.00027923242],"domain_scores_gemma":[0.99762845,0.00020171973,0.00046217156,0.0013606951,0.00022157107,0.00012536935],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013303768,0.00024871677,0.00032817165,0.00054557464,0.00032114962,0.0021088936,0.0009821379,0.00016411979,0.00017239075],"category_scores_gemma":[0.0003079658,0.0002537357,0.00010147658,0.0009619014,0.00007702161,0.00083629094,0.0019327818,0.00044066546,0.000005690845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005446677,0.00031868034,0.03431064,0.00038105968,0.0014336929,0.000026273314,0.025631092,0.04842673,0.0012915245,0.73056567,0.004368792,0.15319137],"study_design_scores_gemma":[0.00010733033,0.00013977138,0.041370094,0.000049994967,0.00049004646,0.000024759815,0.0010265077,0.8949725,0.006084442,0.047960047,0.0067329584,0.0010415444],"about_ca_topic_score_codex":0.0019685233,"about_ca_topic_score_gemma":0.00078854564,"teacher_disagreement_score":0.84654576,"about_ca_system_score_codex":0.00011292957,"about_ca_system_score_gemma":0.00015408648,"threshold_uncertainty_score":0.9999915},"labels":[],"label_agreement":null},{"id":"W4291377769","doi":"10.1016/j.neunet.2022.08.009","title":"Interpretable Artificial Intelligence through Locality Guided Neural Networks","year":2022,"lang":"en","type":"article","venue":"Neural Networks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Locality; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Convolutional neural network; Layer (electronics); Pattern recognition (psychology); Topology (electrical circuits); Machine learning; Mathematics","score_opus":0.05669420740494637,"score_gpt":0.2999425370425506,"score_spread":0.2432483296376042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291377769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012249153,0.0007835171,0.97559786,0.0027345705,0.005421854,0.00062650756,0.000005298789,0.00073610316,0.001845129],"genre_scores_gemma":[0.9899675,0.000038459468,0.0033389626,0.005340779,0.0007823912,0.00018663741,0.000023255088,0.00005528337,0.00026667956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99398124,0.0007658012,0.0012637846,0.0014353016,0.00088842894,0.0016654632],"domain_scores_gemma":[0.99684864,0.0004968345,0.0003868438,0.001762093,0.00021077578,0.0002948072],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011866356,0.0005610079,0.0005802284,0.00014051948,0.0014395342,0.0006685283,0.003760978,0.00018391192,0.0006672144],"category_scores_gemma":[0.00013335001,0.00058891624,0.00033947753,0.0023238717,0.00028452,0.0016211928,0.0029225978,0.0017083433,0.00005072497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005976708,0.00013529768,0.00013842936,0.000004978518,0.000020574864,0.00019459719,0.00050927565,0.85609055,0.000036861406,0.049888235,0.004635017,0.08828644],"study_design_scores_gemma":[0.000051102386,0.00031436916,0.0000326573,0.000010052268,0.000015597661,0.00013191343,0.00034171835,0.97247684,0.00057272427,0.02220332,0.0032509165,0.00059879746],"about_ca_topic_score_codex":0.00056550244,"about_ca_topic_score_gemma":0.0001199099,"teacher_disagreement_score":0.9777184,"about_ca_system_score_codex":0.00031462184,"about_ca_system_score_gemma":0.000072198214,"threshold_uncertainty_score":0.99986047},"labels":[],"label_agreement":null},{"id":"W4292470341","doi":"10.1111/exsy.13118","title":"Subgroup mining for performance analysis of regression models","year":2022,"lang":"en","type":"article","venue":"Expert Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Relevance (law); Machine learning; Regression analysis; Boosting (machine learning); Multivariate statistics; Artificial intelligence; Regression; Data mining; Ask price; Field (mathematics); Statistics","score_opus":0.061783220802777115,"score_gpt":0.30011829611071017,"score_spread":0.23833507530793305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292470341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27389082,0.0014909419,0.7219644,0.00012588475,0.0010290525,0.00038169022,0.000009175277,0.00010478072,0.0010032183],"genre_scores_gemma":[0.9939501,0.000017089023,0.004863633,0.000067033296,0.000055404074,0.0003812895,0.000008608838,0.000010682955,0.0006461099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833184,0.000115214934,0.00044075167,0.0003779279,0.00045087916,0.00028338132],"domain_scores_gemma":[0.998746,0.00016674871,0.0002378486,0.00066888815,0.00012348393,0.000057069195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074587506,0.00011889799,0.00033876687,0.000393338,0.00038522322,0.00006292614,0.0009426127,0.000032537926,0.000016485472],"category_scores_gemma":[0.00002339454,0.00010785362,0.00015547714,0.0013856391,0.000022825476,0.0005195252,0.00029464642,0.00006320141,0.0000026192865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006720111,0.00018345824,0.0015361569,0.00009918792,0.00038461498,0.00001002401,0.037470277,0.8494026,0.011238892,0.08374617,0.0053662998,0.010495093],"study_design_scores_gemma":[0.00005821192,0.00013031918,0.000029880475,0.000023701505,0.000018225337,0.0000035334592,0.0029948654,0.9867598,0.006272489,0.00010081487,0.0034764272,0.0001317565],"about_ca_topic_score_codex":0.0003780717,"about_ca_topic_score_gemma":0.000009537033,"teacher_disagreement_score":0.72005934,"about_ca_system_score_codex":0.00011231227,"about_ca_system_score_gemma":0.000045627716,"threshold_uncertainty_score":0.4398143},"labels":[],"label_agreement":null},{"id":"W4293574627","doi":"10.21203/rs.3.rs-1867622/v1","title":"Pattern Discovery and Disentanglement: A New Interpretable Machine Learning Paradigm for Relational Datasets","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Statistical relational learning; Machine learning; Data science; Data mining; Relational database","score_opus":0.10763588827483661,"score_gpt":0.4015043464945937,"score_spread":0.2938684582197571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293574627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044259713,0.002814762,0.9821082,0.0055589285,0.00047813592,0.0020292713,0.0019396797,0.00014689406,0.000498176],"genre_scores_gemma":[0.97113144,0.00094057724,0.01124508,0.00023490681,0.00053204654,0.001356305,0.008122029,0.000102004306,0.006335596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958362,0.00057779066,0.00043062074,0.0011712983,0.0011876599,0.0007964184],"domain_scores_gemma":[0.9972914,0.0011214383,0.00015092305,0.0010640647,0.000102891885,0.0002693078],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002068829,0.00026676778,0.0003022474,0.0004196978,0.0007978013,0.0012254771,0.0015851252,0.000114052375,0.00032001242],"category_scores_gemma":[0.0005713276,0.00027243586,0.0001265426,0.00041970416,0.0001023365,0.0010199733,0.007931706,0.0016694866,0.00003381382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000528658,0.0009769541,0.077492975,0.0039027543,0.0005905878,0.000526776,0.016318835,0.05370897,0.00030525678,0.5030523,0.06995469,0.2726412],"study_design_scores_gemma":[0.00040494007,0.0006093712,0.0015732535,0.00056946266,0.000019590008,0.000014819744,0.0007262909,0.68097335,0.0004217242,0.11137899,0.20261832,0.0006898759],"about_ca_topic_score_codex":0.002097359,"about_ca_topic_score_gemma":0.0003544752,"teacher_disagreement_score":0.9708631,"about_ca_system_score_codex":0.00038022982,"about_ca_system_score_gemma":0.00054725213,"threshold_uncertainty_score":0.99997276},"labels":[],"label_agreement":null},{"id":"W4295768346","doi":"10.1109/fuzz-ieee55066.2022.9882723","title":"An End-to-End Trainable Deep Convolutional Neuro-Fuzzy Classifier","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Artificial intelligence; Computer science; Adaptive neuro fuzzy inference system; Convolutional neural network; Neuro-fuzzy; Deep learning; Fuzzy logic; Classifier (UML); Machine learning; Artificial neural network; End-to-end principle; Fuzzy control system","score_opus":0.07731007610972154,"score_gpt":0.3124345747853477,"score_spread":0.23512449867562615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295768346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26974165,0.00036337462,0.37094766,0.01828094,0.07738104,0.0049979673,0.0014519593,0.0021910323,0.25464436],"genre_scores_gemma":[0.9861851,0.000024571162,0.00083254144,0.002342335,0.0010817304,0.00097331917,0.0001108244,0.00007960724,0.008370003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911852,0.0010150557,0.0012961553,0.0020017475,0.003248581,0.0012532782],"domain_scores_gemma":[0.99559695,0.0004940371,0.0005737825,0.0016165933,0.0010291314,0.0006895201],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018454631,0.0006967883,0.0006705001,0.0010876568,0.0011555911,0.0012797826,0.005379204,0.00019513257,0.0018253173],"category_scores_gemma":[0.0001818016,0.00077987835,0.00029570903,0.0013244426,0.00022007398,0.0016337195,0.00049124955,0.0011912168,0.0013822113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021516075,0.00080128177,0.00038990105,0.00004244321,0.00018150953,0.0004932573,0.0026447682,0.06853585,0.043165028,0.8568169,0.021136401,0.0055775214],"study_design_scores_gemma":[0.001122064,0.0019609064,0.0008149928,0.00014454659,0.000044942622,0.0005547304,0.006676944,0.8520013,0.00928048,0.027790947,0.09733746,0.0022706978],"about_ca_topic_score_codex":0.0014546039,"about_ca_topic_score_gemma":0.0002820669,"teacher_disagreement_score":0.8290259,"about_ca_system_score_codex":0.0013137347,"about_ca_system_score_gemma":0.00085419184,"threshold_uncertainty_score":0.999757},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Taxonomy (biology); Generalization; Relevance (law); Perspective (graphical); Machine learning; Feature (linguistics); Interpretation (philosophy)","score_opus":0.09707560278384564,"score_gpt":0.3225294605025278,"score_spread":0.22545385771868215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296708919","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.0930004e-7,0.91663235,0.07848931,0.0004114894,0.00233618,0.0012756424,0.000017825305,0.00040752132,0.0004291912],"genre_scores_gemma":[0.000006198513,0.991998,0.0058101895,0.00042210703,0.0010074493,0.0003407029,0.000131777,0.000056178815,0.00022737037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99252427,0.0036848632,0.0011080251,0.0013459149,0.00043494924,0.0009019868],"domain_scores_gemma":[0.9942453,0.0027115208,0.0007283153,0.0019110074,0.00017088528,0.00023298558],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0052627884,0.0006813743,0.0018189347,0.00030437336,0.001315497,0.00037682787,0.0030654422,0.00022364961,0.0001963693],"category_scores_gemma":[0.0007178815,0.00066550757,0.00044831797,0.0022422057,0.00013025365,0.0004957028,0.0035562702,0.0012258417,0.00005028443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7760274e-7,0.000040812585,0.000012298168,0.0033356324,0.00007688328,0.000037355032,0.000039536826,0.00013718684,3.6604089e-9,0.002575463,0.0045320746,0.98921245],"study_design_scores_gemma":[0.000037409653,0.000055081597,0.000019530233,0.0016025193,0.0001716323,0.00029623025,0.00002065964,0.018619375,3.8476017e-8,0.00014303016,0.97840244,0.0006320429],"about_ca_topic_score_codex":0.00026829072,"about_ca_topic_score_gemma":0.000039861196,"teacher_disagreement_score":0.9885804,"about_ca_system_score_codex":0.00033416518,"about_ca_system_score_gemma":0.0003515761,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W4297081730","doi":"10.36227/techrxiv.21067438","title":"A Trustworthy View on XAI Method Evaluation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Trustworthiness; Computer science; Centroid; Process (computing); Cluster analysis; Data mining; Order (exchange); Feature (linguistics); Artificial intelligence; Business; Computer security","score_opus":0.12025309599460612,"score_gpt":0.41603309383123727,"score_spread":0.2957799978366311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297081730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006187751,0.00041861724,0.88821214,0.0030743063,0.0023185178,0.0012000577,0.0000042175957,0.00041417114,0.1037392],"genre_scores_gemma":[0.113809414,0.00039049264,0.8593702,0.009233121,0.0006882389,0.0032561722,0.000119530094,0.00011317527,0.013019711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949006,0.0012667888,0.0005667877,0.0013434545,0.0014843565,0.00043805386],"domain_scores_gemma":[0.99662596,0.00042229085,0.0002869821,0.0022227408,0.0003167088,0.00012534086],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053491974,0.00034639903,0.00041209895,0.0003268953,0.00026777023,0.00041636016,0.0026242682,0.000182211,0.0057593547],"category_scores_gemma":[0.00035076446,0.0003343758,0.00024266868,0.0006708386,0.000025621423,0.00027634524,0.0031399864,0.0009248846,0.0008882516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000943009,0.00014544306,0.000016625845,0.000055217057,0.00004607017,0.000021630149,0.0010789488,0.12063859,0.00003887537,0.29222766,0.00451586,0.58120567],"study_design_scores_gemma":[0.000062715306,0.00013618762,0.000063541906,0.00005273696,0.000032772765,0.0000051372003,0.00013732363,0.77659786,0.003383482,0.16757734,0.051509812,0.0004411104],"about_ca_topic_score_codex":0.00045389612,"about_ca_topic_score_gemma":0.00008680179,"teacher_disagreement_score":0.65595925,"about_ca_system_score_codex":0.0005233189,"about_ca_system_score_gemma":0.0006121055,"threshold_uncertainty_score":0.99991083},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07343320096530884,"score_gpt":0.3730624407105773,"score_spread":0.29962923974526845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297183943","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.5251056e-8,0.84419566,0.15103522,0.00015822894,0.00097624346,0.0011124222,0.0000029887153,0.000043951553,0.0024752053],"genre_scores_gemma":[0.000003708278,0.99437064,0.0041760015,0.0011938984,0.00004023255,0.00013933114,0.000002895036,0.000010176796,0.00006311468],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925253,0.00048524374,0.0038310979,0.00027212148,0.002313911,0.000572346],"domain_scores_gemma":[0.99067503,0.00072627125,0.0052583367,0.0012472611,0.001770539,0.00032256043],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.013190991,0.00039833717,0.0022305888,0.0028631012,0.0006868178,0.0011139525,0.007158196,0.00009382927,0.000114233524],"category_scores_gemma":[0.00448695,0.00028622508,0.0008238291,0.009190318,0.00023732251,0.013727571,0.0005944537,0.000858004,0.0004197192],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011399396,0.000057398534,6.272849e-8,0.75700635,0.000028910827,0.000022593318,0.00058182987,0.00011701928,1.550954e-7,0.011906805,0.0019116813,0.22836605],"study_design_scores_gemma":[0.00004318155,0.00013646188,3.2200646e-8,0.2436807,0.00021018363,0.0004831489,0.00012116082,0.0019435226,0.000009313821,0.00021106079,0.75287473,0.0002864992],"about_ca_topic_score_codex":0.0000040714112,"about_ca_topic_score_gemma":6.1633295e-7,"teacher_disagreement_score":0.75096303,"about_ca_system_score_codex":0.00096793217,"about_ca_system_score_gemma":0.006392972,"threshold_uncertainty_score":0.999959},"labels":[],"label_agreement":null},{"id":"W4297312826","doi":"10.3389/fdata.2022.979465","title":"The ABC recommendations for validation of supervised machine learning results in biomedical sciences","year":2022,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Front (military); Public opinion; Volume (thermodynamics); Data science; Public health; Artificial intelligence; Computer science; Medicine; Political science; Engineering; Data mining; Pathology; Mechanical engineering","score_opus":0.1559307450808685,"score_gpt":0.3363171335948982,"score_spread":0.1803863885140297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297312826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0097050015,0.0005716364,0.954067,0.030099116,0.0040250896,0.0006377345,0.000529512,0.00005318449,0.00031175165],"genre_scores_gemma":[0.7276583,0.00038267925,0.2693042,0.00024767825,0.000121492194,0.00018854544,0.0017779237,0.000016085154,0.0003031381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981838,0.0003202444,0.00046142467,0.00042875524,0.00033662634,0.00026917068],"domain_scores_gemma":[0.99860287,0.0004786617,0.00013876108,0.0007140477,0.000034153174,0.000031527223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004681274,0.00007058057,0.00012035648,0.00032424516,0.0006289316,0.00009193583,0.0029799426,0.000024291268,0.0000050181984],"category_scores_gemma":[0.0012526502,0.00006078115,0.000019424335,0.0015378367,0.00018204615,0.0004963463,0.0012330023,0.00020836917,0.0000012539581],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018390511,0.00037305892,0.012550885,0.000024216924,0.000020212945,0.000007653136,0.0053671985,0.008126047,0.00053258677,0.011657859,0.11580364,0.8453527],"study_design_scores_gemma":[0.0003028631,0.00015620535,0.00014029688,0.000014458083,0.0000020293605,0.0000012821745,0.0022764935,0.7900706,0.0010989427,0.006944322,0.19889884,0.000093654075],"about_ca_topic_score_codex":0.0004373878,"about_ca_topic_score_gemma":0.00018646778,"teacher_disagreement_score":0.8452591,"about_ca_system_score_codex":0.00008585957,"about_ca_system_score_gemma":0.0001590673,"threshold_uncertainty_score":0.5537524},"labels":[],"label_agreement":null},{"id":"W4297477913","doi":"10.3390/info13100459","title":"Knowledge Graphs and Explainable AI in Healthcare","year":2022,"lang":"en","type":"article","venue":"Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Cape Breton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Knowledge graph; Health care; Leverage (statistics); Computer science; Transparency (behavior); Knowledge management; Artificial intelligence; Political science","score_opus":0.018159375831761665,"score_gpt":0.274958069201226,"score_spread":0.25679869336946437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297477913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7516292,0.0022404827,0.1730024,0.03903528,0.002535128,0.0020346788,0.000018221439,0.001015603,0.028488994],"genre_scores_gemma":[0.9973956,0.000021773618,0.00083625625,0.0015652525,0.00000517671,0.00009628647,0.0000075879657,0.0000023037421,0.00006981445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991897,0.00006485688,0.00025988286,0.000103195394,0.00016597722,0.00021641818],"domain_scores_gemma":[0.9995731,0.000036505895,0.000063666615,0.00020880086,0.000068705114,0.000049214203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047888985,0.00006493111,0.00007386828,0.0003218275,0.0002839935,0.00013167101,0.00031946323,0.000022638844,0.0000128246365],"category_scores_gemma":[0.000031129937,0.00007302241,0.000015615951,0.0007519487,0.000016568283,0.0031953913,0.00031427882,0.000170829,0.00006892461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070571255,0.000027722275,0.0009826501,0.000040169834,0.000001437496,0.0000040245536,0.015254837,0.0009851886,0.000029557492,0.88230777,0.0017520918,0.098607495],"study_design_scores_gemma":[0.0004401455,0.00041577136,0.0068686176,0.000026607526,0.0000018708871,0.000068752095,0.0070698806,0.53888947,0.002771787,0.2397176,0.20325075,0.00047876203],"about_ca_topic_score_codex":0.00055664213,"about_ca_topic_score_gemma":0.000118157026,"teacher_disagreement_score":0.64259017,"about_ca_system_score_codex":0.00012768288,"about_ca_system_score_gemma":0.00008059393,"threshold_uncertainty_score":0.29777676},"labels":[],"label_agreement":null},{"id":"W4297685013","doi":"10.1109/ichi54592.2022.00127","title":"Towards Trustworthy Artificial Intelligence in Healthcare","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Trustworthiness; Health care; Computer science; Health informatics; Informatics; Data science; Artificial intelligence; Big data; Knowledge management; Data mining; Internet privacy; Engineering","score_opus":0.09984049810389588,"score_gpt":0.3520785432189064,"score_spread":0.2522380451150105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297685013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12505525,0.0004150571,0.50773776,0.27937424,0.029923553,0.004704431,0.00096984295,0.0014961397,0.05032373],"genre_scores_gemma":[0.9830972,0.00021907383,0.006916704,0.00869415,0.00022807754,0.0004571524,0.000102921316,0.00003334974,0.00025139758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932954,0.00046073925,0.0022034678,0.00068927935,0.0022758578,0.0010753007],"domain_scores_gemma":[0.9968768,0.00022484933,0.00072833453,0.001107323,0.0006570433,0.00040565545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001990348,0.00048126487,0.0005347352,0.00122204,0.0007302947,0.0004864877,0.0038610185,0.00016286757,0.0007803154],"category_scores_gemma":[0.0002276092,0.0005381183,0.0001853313,0.0017444685,0.000119970806,0.0012939319,0.0009714197,0.0018297138,0.0004187883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010508253,0.00019728659,0.00039866794,0.00007434767,0.000021015792,0.00006411925,0.005823937,0.0072014355,0.00002769883,0.82548183,0.0004512283,0.16015334],"study_design_scores_gemma":[0.00017118936,0.0010256794,0.00035006134,0.00012723323,0.000004121869,0.0000866459,0.008539687,0.8127678,0.0015960917,0.16877751,0.0057785586,0.0007753857],"about_ca_topic_score_codex":0.0022839797,"about_ca_topic_score_gemma":0.0018884623,"teacher_disagreement_score":0.85804194,"about_ca_system_score_codex":0.0013931723,"about_ca_system_score_gemma":0.0013885602,"threshold_uncertainty_score":0.99970704},"labels":[],"label_agreement":null},{"id":"W4297785970","doi":"10.36227/techrxiv.21067438.v1","title":"A Trustworthy View on XAI Method Evaluation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Trustworthiness; Computer science; Centroid; Process (computing); Cluster analysis; Data mining; Order (exchange); Feature (linguistics); Artificial intelligence; Business; Computer security","score_opus":0.12025309599460612,"score_gpt":0.41603309383123727,"score_spread":0.2957799978366311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297785970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006187751,0.00041861724,0.88821214,0.0030743063,0.0023185178,0.0012000577,0.0000042175957,0.00041417114,0.1037392],"genre_scores_gemma":[0.113809414,0.00039049264,0.8593702,0.009233121,0.0006882389,0.0032561722,0.000119530094,0.00011317527,0.013019711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949006,0.0012667888,0.0005667877,0.0013434545,0.0014843565,0.00043805386],"domain_scores_gemma":[0.99662596,0.00042229085,0.0002869821,0.0022227408,0.0003167088,0.00012534086],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053491974,0.00034639903,0.00041209895,0.0003268953,0.00026777023,0.00041636016,0.0026242682,0.000182211,0.0057593547],"category_scores_gemma":[0.00035076446,0.0003343758,0.00024266868,0.0006708386,0.000025621423,0.00027634524,0.0031399864,0.0009248846,0.0008882516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000943009,0.00014544306,0.000016625845,0.000055217057,0.00004607017,0.000021630149,0.0010789488,0.12063859,0.00003887537,0.29222766,0.00451586,0.58120567],"study_design_scores_gemma":[0.000062715306,0.00013618762,0.000063541906,0.00005273696,0.000032772765,0.0000051372003,0.00013732363,0.77659786,0.003383482,0.16757734,0.051509812,0.0004411104],"about_ca_topic_score_codex":0.00045389612,"about_ca_topic_score_gemma":0.00008680179,"teacher_disagreement_score":0.65595925,"about_ca_system_score_codex":0.0005233189,"about_ca_system_score_gemma":0.0006121055,"threshold_uncertainty_score":0.99991083},"labels":[],"label_agreement":null},{"id":"W4297831036","doi":"10.1007/s00146-022-01542-8","title":"Elephant motorbikes and too many neckties: epistemic spatialization as a framework for investigating patterns of bias in convolutional neural networks","year":2022,"lang":"en","type":"article","venue":"AI & Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Arts and Humanities Research Council","keywords":"Spatialization; Computer science; Identification (biology); Convolutional neural network; Visibility; Process (computing); Invisibility; Epistemology; Sociology; Artificial intelligence; Cognitive science; Data science; Psychology","score_opus":0.044391175893926486,"score_gpt":0.2966212434453263,"score_spread":0.2522300675513998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297831036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3952272,0.00020418027,0.60275793,0.0012848251,0.00020382146,0.00027165652,0.000010869004,0.000035254376,0.0000042832576],"genre_scores_gemma":[0.98047674,0.00003954563,0.016634181,0.0025692997,0.00007794836,0.00014296241,0.00001933924,0.000012452928,0.000027525986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985257,0.00013607451,0.0003990106,0.00034631466,0.00028362768,0.00030931798],"domain_scores_gemma":[0.9988494,0.000543813,0.00021276012,0.00023527915,0.00009837082,0.000060387865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064632576,0.0001278997,0.0001898368,0.000037985632,0.0003052532,0.000079476515,0.00039257196,0.00007552643,0.000016449236],"category_scores_gemma":[0.00021636218,0.00014227608,0.000104323364,0.00039098776,0.00009126454,0.0003434576,0.00034755535,0.00026472873,5.56462e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023435428,0.0001503912,0.1820067,0.00020694101,0.00005113672,0.000006216841,0.04076271,0.1512164,0.0012932726,0.6159767,0.0014500845,0.006856003],"study_design_scores_gemma":[0.00012518144,0.00014132618,0.0027760467,0.000045482237,0.0000048470997,0.0000070470073,0.0029057506,0.94147485,0.00060926075,0.051619615,0.00014735127,0.00014321944],"about_ca_topic_score_codex":0.00079119985,"about_ca_topic_score_gemma":0.000050833052,"teacher_disagreement_score":0.79025847,"about_ca_system_score_codex":0.00013628358,"about_ca_system_score_gemma":0.00009848141,"threshold_uncertainty_score":0.58018506},"labels":[],"label_agreement":null},{"id":"W4298500089","doi":"10.1609/aaai.v24i3.18837","title":"Model AI Assignments","year":2010,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Session (web analytics); Dissemination; Variety (cybernetics); Computer science; Core (optical fiber); Artificial intelligence; Multimedia; World Wide Web; Telecommunications","score_opus":0.031702383864057986,"score_gpt":0.2948359031720305,"score_spread":0.2631335193079725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298500089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01815845,0.0000020630853,0.9186436,0.0021462655,0.00039285203,0.00006926919,2.5613562e-7,0.00020996535,0.060377307],"genre_scores_gemma":[0.8748935,8.3707386e-7,0.11771239,0.002022549,0.000035211717,0.000009061893,2.4550332e-7,0.0000051200172,0.005321105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910456,0.000011044233,0.00013557941,0.00026628148,0.00021902862,0.0002635023],"domain_scores_gemma":[0.9991755,0.000027983391,0.000024806754,0.0005998361,0.00006738877,0.00010452571],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019629698,0.00008089548,0.00006699875,0.00005299605,0.0001000749,0.00017683482,0.00091076834,0.000053278884,0.00015644322],"category_scores_gemma":[0.0000391518,0.00007009032,0.000032839776,0.00018299249,0.000032710093,0.0007795396,0.00021553403,0.00018929326,0.0010525017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.387564e-7,0.000048837446,0.00020986538,0.0000011016323,0.0000027265874,0.000005321651,0.00020740135,0.0011982223,0.052563444,0.9243473,0.004481411,0.016933627],"study_design_scores_gemma":[0.00002226362,0.000012838094,0.000043856267,8.8704877e-7,6.206713e-7,0.000002780588,0.000010340314,0.8006378,0.10897918,0.0875527,0.0026432343,0.00009352541],"about_ca_topic_score_codex":0.000044023967,"about_ca_topic_score_gemma":0.000087984154,"teacher_disagreement_score":0.85673505,"about_ca_system_score_codex":0.00001312308,"about_ca_system_score_gemma":0.00005839402,"threshold_uncertainty_score":0.9997253},"labels":[],"label_agreement":null},{"id":"W4304097640","doi":"10.36227/techrxiv.21262041.v1","title":"Analyzing XAI Metrics: Summary of the Literature Review","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Multidisciplinary approach; Field (mathematics); Point (geometry); Computer science; Management science; Artificial intelligence; Operations research; Sociology; Economics; Engineering; Social science; Mathematics","score_opus":0.035355848591699206,"score_gpt":0.3053836625846889,"score_spread":0.2700278139929897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304097640","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052316085,0.6702857,0.24222769,0.0151871145,0.0051865494,0.0022698562,0.00005890855,0.00042038286,0.06384061],"genre_scores_gemma":[0.082447484,0.6766774,0.16016236,0.023952095,0.0008745229,0.0008094168,0.00016446266,0.0001844008,0.05472787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713004,0.00044042958,0.0006963229,0.0007386521,0.0006823653,0.00031222097],"domain_scores_gemma":[0.996035,0.00026876802,0.0004871048,0.0027938157,0.00034497303,0.00007036397],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0015849301,0.00027019135,0.0005143177,0.00033869938,0.00018331593,0.00025400234,0.0053315964,0.00014098066,0.00033552988],"category_scores_gemma":[0.00057245186,0.00018645152,0.00047661847,0.003916236,0.00005431379,0.00029215624,0.008684846,0.0011927849,0.000019703004],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010669225,0.00048643988,0.0033818998,0.022498015,0.0005050415,0.00025813017,0.00510432,0.0066130944,0.00041764637,0.5387194,0.20341633,0.218589],"study_design_scores_gemma":[0.00020514078,0.00029583715,0.0010341858,0.06356559,0.00055702694,0.00010574003,0.0006943772,0.071599774,0.042875346,0.19715777,0.618041,0.0038682227],"about_ca_topic_score_codex":0.0001517256,"about_ca_topic_score_gemma":0.000023996285,"teacher_disagreement_score":0.41462466,"about_ca_system_score_codex":0.00014446139,"about_ca_system_score_gemma":0.00027906368,"threshold_uncertainty_score":0.9993327},"labels":[],"label_agreement":null},{"id":"W4304820937","doi":"10.1007/978-3-031-18344-7_42","title":"A Comparative Analysis of Local Explainability of Models for Sentiment Detection","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Sentiment analysis; Computer science; Artificial intelligence; Natural language processing; Focus (optics); Encoder; Transformer; Machine learning; Engineering","score_opus":0.040044540914710026,"score_gpt":0.2758592440406493,"score_spread":0.2358147031259393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304820937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004570945,0.0030658962,0.99363244,0.000017803095,0.0003418773,0.000832364,0.000020917496,0.000018303072,0.001613315],"genre_scores_gemma":[0.9989683,0.00006906471,0.0005660769,0.00001325853,0.00005042426,0.00009653672,0.000019027204,0.000010387476,0.00020690195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980318,0.000117130876,0.00077965297,0.0005435741,0.00030067636,0.00022717511],"domain_scores_gemma":[0.997892,0.00079974014,0.0005252855,0.00051971315,0.00021621257,0.000047044283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074411824,0.00024822712,0.0010582297,0.0004086778,0.00009188136,0.000040206272,0.0003416218,0.00024158723,0.0000110343],"category_scores_gemma":[0.00001420862,0.00023212608,0.0002503112,0.00040732493,0.00012026722,0.00013195783,0.00016975075,0.00027351445,1.2004107e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042098127,0.000023351202,0.00001880895,0.0001157315,0.0003259473,0.000002006822,0.0011159643,0.9142784,0.000016116119,0.07630024,0.0000039693673,0.0077573857],"study_design_scores_gemma":[0.00006938811,0.0001780844,0.0000069309153,0.00008354646,0.00017455366,0.0000019799477,0.000074958145,0.9794616,0.00044042416,0.018848887,0.00047456077,0.00018508427],"about_ca_topic_score_codex":0.00059582095,"about_ca_topic_score_gemma":0.0011203196,"teacher_disagreement_score":0.99851125,"about_ca_system_score_codex":0.00018008656,"about_ca_system_score_gemma":0.000041673095,"threshold_uncertainty_score":0.94658273},"labels":[],"label_agreement":null},{"id":"W4306250647","doi":"10.1002/pra2.663","title":"Information Resilient Society in an <scp>AI</scp> World—Is <scp>XAI</scp> Sufficient?","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Independence (probability theory); Field (mathematics); Neutrality; Public relations; Business; Knowledge management; Computer science; Political science; Law","score_opus":0.01057743177266219,"score_gpt":0.24982558742937686,"score_spread":0.23924815565671467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306250647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820286,0.000024701583,0.002960577,0.005449475,0.00047954702,0.0011807426,0.000034223987,0.0002786785,0.0075634443],"genre_scores_gemma":[0.9957917,0.000014575404,0.001832235,0.0018057905,0.000012965893,0.00022168204,0.000005834791,0.0000048677252,0.00031039867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969521,0.000012353885,0.00079277175,0.00025549097,0.0013822301,0.00060504454],"domain_scores_gemma":[0.99575377,0.00021142619,0.0012625589,0.00027317816,0.0024269188,0.00007218272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043498194,0.0001587087,0.00020963975,0.0014840974,0.0012363201,0.0006295514,0.0021463153,0.0001337449,0.0000011753688],"category_scores_gemma":[0.0037983528,0.0001473126,0.00007627417,0.008402008,0.00027803387,0.0130446935,0.0011223849,0.00038988076,0.000012891359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037083867,0.00013418883,0.06449342,0.00008200271,0.000015966256,4.3039748e-8,0.049061526,0.0007486834,0.00414788,0.8504344,0.020752294,0.010125892],"study_design_scores_gemma":[0.0010503655,0.0006738627,0.021019198,0.000048582682,0.000025058262,0.000014048359,0.0918113,0.2670525,0.25344855,0.06513931,0.29949278,0.0002244694],"about_ca_topic_score_codex":0.00002236831,"about_ca_topic_score_gemma":0.000008625031,"teacher_disagreement_score":0.78529507,"about_ca_system_score_codex":0.00084671506,"about_ca_system_score_gemma":0.00032416874,"threshold_uncertainty_score":0.95088995},"labels":[],"label_agreement":null},{"id":"W4307290994","doi":"10.3389/frai.2022.1048568","title":"Editorial: Explanation in human-AI systems","year":2022,"lang":"en","type":"editorial","venue":"Frontiers in Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; McMaster University","funders":"","keywords":"Volume (thermodynamics); Front (military); Computer science; Engineering; Mechanical engineering; Physics; Thermodynamics","score_opus":0.02418234426498487,"score_gpt":0.30451817628556854,"score_spread":0.28033583202058365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307290994","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017975672,0.00074618147,0.30135196,0.00017838328,0.6958883,0.00082508987,0.000046004323,0.00021803059,0.00072809414],"genre_scores_gemma":[0.0031469609,0.0004243404,0.0032293748,0.000066833505,0.9912142,0.00084038876,0.00027263106,0.00012212667,0.0006831111],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898051,0.0009315787,0.0025981576,0.0021823365,0.0030179175,0.001464913],"domain_scores_gemma":[0.9956341,0.0009084561,0.00077889394,0.0018671006,0.00058124814,0.00023022677],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0040690093,0.0008369263,0.0012638037,0.0024626798,0.00046553995,0.0011458192,0.0052750353,0.0014016425,0.00010791477],"category_scores_gemma":[0.002147668,0.001024364,0.0002362081,0.003348192,0.00023898893,0.0016511568,0.0010523907,0.003765413,0.00015640832],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053615106,0.00027819356,0.000056769222,0.00008995832,0.000021966976,0.00014765738,0.0015415867,0.018854454,0.000056217687,0.032187827,0.9387764,0.007935351],"study_design_scores_gemma":[0.00005611412,0.00021567378,0.0000013591417,0.00022071338,0.000012081077,0.0000015599269,0.0020933882,0.06550796,0.0012254232,0.06597878,0.86363256,0.0010543708],"about_ca_topic_score_codex":0.004685838,"about_ca_topic_score_gemma":0.0014526751,"teacher_disagreement_score":0.29812258,"about_ca_system_score_codex":0.0025906742,"about_ca_system_score_gemma":0.0010058781,"threshold_uncertainty_score":0.99989474},"labels":[],"label_agreement":null},{"id":"W4307421239","doi":"10.5281/zenodo.7255934","title":"Can Ensembling Pre-processing Algorithms Lead to Better Machine Learning Fairness?","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal; Concordia University","funders":"","keywords":"Lead (geology); Computer science; Artificial intelligence; Machine learning","score_opus":0.04433373836655441,"score_gpt":0.2657895283475195,"score_spread":0.2214557899809651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307421239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045669932,0.0001810639,0.91906,0.010424931,0.00033675856,0.0007251118,0.00006280368,0.002771531,0.020767897],"genre_scores_gemma":[0.9895335,0.000009712687,0.0066549215,0.00096931605,0.0001439316,3.5481096e-7,0.00021786604,0.0007951461,0.00167527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713695,0.00054368953,0.00031087175,0.0006961109,0.0007060665,0.0006062936],"domain_scores_gemma":[0.99866295,0.000035536177,0.00012047812,0.0005511191,0.00041514632,0.00021474723],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012164507,0.00017414297,0.00016073168,0.0004194093,0.0060374117,0.0016416728,0.0025483724,0.000033726574,0.002614569],"category_scores_gemma":[0.00044229574,0.00020262747,0.000051866522,0.0016413846,0.00006552742,0.0005556022,0.004449703,0.0006011036,0.0019776167],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003748347,0.00013490368,0.000019246872,0.0000415282,0.000021007983,0.00008644229,0.014394761,0.016991949,0.011421499,0.005743517,0.011267476,0.9398402],"study_design_scores_gemma":[0.00015557787,0.0004022554,0.00008146266,0.000019734412,0.0000054717734,0.00015012082,0.0011124251,0.18186869,0.0048671314,0.00080931117,0.81019306,0.00033476925],"about_ca_topic_score_codex":0.00013331977,"about_ca_topic_score_gemma":0.0000019634335,"teacher_disagreement_score":0.9438636,"about_ca_system_score_codex":0.0003096355,"about_ca_system_score_gemma":0.00001075327,"threshold_uncertainty_score":0.9993947},"labels":[],"label_agreement":null},{"id":"W4307576169","doi":"10.1002/env.2772","title":"An illustration of model agnostic explainability methods applied to environmental data","year":2022,"lang":"en","type":"article","venue":"Environmetrics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"National Institute of Environmental Health Sciences; National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Variety (cybernetics); Focus (optics); Artificial intelligence; Transparency (behavior); Inference; Implementation; Machine learning; Deep learning; Feature (linguistics); Data science","score_opus":0.11218585795785195,"score_gpt":0.35044250544113453,"score_spread":0.23825664748328257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307576169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09450806,0.00006160945,0.9042636,0.00014586774,0.00012907191,0.00041138768,0.000098641605,0.000057308833,0.0003244552],"genre_scores_gemma":[0.6690558,0.000010523244,0.3305567,0.00017745758,0.000017304914,0.000054955643,0.00006798257,0.000012848713,0.00004639211],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972427,0.00033710466,0.00046530983,0.00090784853,0.00069320493,0.00035386358],"domain_scores_gemma":[0.99635845,0.0004312322,0.00016471714,0.002847918,0.000008008547,0.00018968168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023297602,0.00017822374,0.00022899162,0.00038176437,0.0003337002,0.000050163664,0.0031479024,0.00005358888,0.0001416453],"category_scores_gemma":[0.0003360046,0.00020991034,0.000041526106,0.0012406353,0.00009611864,0.0007202489,0.0024558632,0.00024989338,0.000042446234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001596359,0.00060847146,0.00040856077,0.000007529553,0.000008184005,0.000005131659,0.0016005026,0.799154,0.04885871,0.01161537,0.0002049594,0.13751264],"study_design_scores_gemma":[0.00008401029,0.00029680209,0.0016522176,7.990612e-7,0.000012944427,0.0000044008334,0.0007326931,0.94503474,0.04223137,0.0063479035,0.003304611,0.00029748352],"about_ca_topic_score_codex":0.000043155906,"about_ca_topic_score_gemma":0.0000036975116,"teacher_disagreement_score":0.57454777,"about_ca_system_score_codex":0.00030568696,"about_ca_system_score_gemma":0.000057704565,"threshold_uncertainty_score":0.8559895},"labels":[],"label_agreement":null},{"id":"W4307816715","doi":"10.1016/j.eswa.2022.119101","title":"Predicting and explaining performance and diversity of neural network architecture for semantic segmentation","year":2022,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Compute Canada","keywords":"Boosting (machine learning); Computer science; Artificial neural network; Artificial intelligence; Machine learning; Segmentation; Diversity (politics); Network architecture; Ensemble learning; Architecture; Data mining","score_opus":0.020764452668868522,"score_gpt":0.24731959830124683,"score_spread":0.2265551456323783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307816715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30759487,0.0004442048,0.6906671,0.00017542267,0.00006526065,0.0009297219,0.0000050905187,0.000058083617,0.000060266113],"genre_scores_gemma":[0.9847664,0.000011927728,0.013870362,0.000050760347,0.000065508706,0.001194393,0.0000054516536,0.000006549798,0.000028597953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991894,0.000044158143,0.0001701404,0.0002621192,0.00016829406,0.00016589752],"domain_scores_gemma":[0.9993946,0.0001481007,0.00014042748,0.00021771369,0.0000518628,0.000047283796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025079184,0.000080379934,0.00011547065,0.00005268705,0.0012219372,0.00004711986,0.00023596086,0.000015332462,8.7073744e-7],"category_scores_gemma":[0.0000052260325,0.00007549881,0.0000129757245,0.00026205205,0.00004573607,0.0002038627,0.00036795996,0.000071345836,2.1984384e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014776972,0.0001518454,0.24577907,0.0006388157,0.00012184098,0.0000037253367,0.07775548,0.54344004,0.0054788254,0.060271878,0.00085588417,0.06535482],"study_design_scores_gemma":[0.00025303542,0.00034671646,0.0021764426,0.000045162276,0.000011902452,0.00007950763,0.006686942,0.9869661,0.0009360805,0.00034743384,0.0019547504,0.00019596795],"about_ca_topic_score_codex":0.00018047809,"about_ca_topic_score_gemma":0.000016848062,"teacher_disagreement_score":0.6771716,"about_ca_system_score_codex":0.000028146516,"about_ca_system_score_gemma":0.000017525523,"threshold_uncertainty_score":0.9398277},"labels":[],"label_agreement":null},{"id":"W4307855632","doi":"10.31234/osf.io/3krx8","title":"Broad effects of shallow understanding: Explaining an unrelated phenomenon exposes the illusion of explanatory depth","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phenomenon; Illusion; Debiasing; Zipper; Psychology; Cognitive psychology; Social psychology; Epistemology; Ignorance; Salient; Feeling; Explanatory model; Positive economics; Computer science; Economics; Philosophy; Artificial intelligence","score_opus":0.0787166842005153,"score_gpt":0.29703942165506825,"score_spread":0.21832273745455294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307855632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33724827,0.0014013817,0.6355574,0.00028021913,0.002304313,0.001468586,0.000008746648,0.00042270543,0.021308351],"genre_scores_gemma":[0.9947454,0.00019780811,0.0045306566,0.00013275731,0.000045393568,0.00009460428,0.000018841043,0.000041041487,0.00019349591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959088,0.00068907224,0.0009166006,0.0009628637,0.0010040505,0.00051861006],"domain_scores_gemma":[0.99570763,0.0011644633,0.0008053404,0.002015085,0.00015909775,0.0001483799],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013677048,0.0004401539,0.00064277864,0.00045578054,0.00041048773,0.00013465906,0.0035044432,0.00025656566,0.00020213312],"category_scores_gemma":[0.00020471777,0.0003539726,0.00022668838,0.0007407168,0.00024176248,0.0005467456,0.0039936067,0.00085041823,0.0000077657405],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013962723,0.00088796415,0.0011962495,0.0012042072,0.0004046036,0.0001706209,0.07685821,0.04693313,0.020281637,0.83402205,0.00033631045,0.017565388],"study_design_scores_gemma":[0.0012041786,0.0039308257,0.0024611007,0.0019312929,0.00027353197,0.000036246347,0.092872635,0.33867216,0.2587103,0.29584512,0.001086884,0.0029757223],"about_ca_topic_score_codex":0.0007658416,"about_ca_topic_score_gemma":0.00024380992,"teacher_disagreement_score":0.6574971,"about_ca_system_score_codex":0.00048152095,"about_ca_system_score_gemma":0.00035929226,"threshold_uncertainty_score":0.9998912},"labels":[],"label_agreement":null},{"id":"W4308718476","doi":"10.3390/make4040047","title":"Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Kultúrna a Edukacná Grantová Agentúra MŠVVaŠ SR; Ministerstvo školstva, vedy, výskumu a športu Slovenskej republiky; Austrian Science Fund","keywords":"Class (philosophy); Range (aeronautics); Domain (mathematical analysis); Function (biology); Space (punctuation); Artificial intelligence; Computer science; Binary classification; Mathematics; Machine learning; Support vector machine","score_opus":0.04673742173121412,"score_gpt":0.3243509899479155,"score_spread":0.27761356821670136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308718476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058338735,0.0005618431,0.98873305,0.0018454636,0.00029341373,0.0009317512,0.000025436004,0.0003211472,0.0014540432],"genre_scores_gemma":[0.96114355,0.00006879192,0.025670161,0.00006222005,0.0001484655,0.0016887212,0.00029582833,0.000044517397,0.01087776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781597,0.00037384877,0.00036075676,0.00077159255,0.00024957315,0.00042824165],"domain_scores_gemma":[0.9975794,0.0013595031,0.0003284611,0.00020919867,0.00039029616,0.00013312418],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0012385171,0.0002576838,0.00024773125,0.00038640312,0.0034878384,0.00036753717,0.00015590132,0.000089017216,0.00006464191],"category_scores_gemma":[0.0005858237,0.00026228093,0.00006495818,0.0005743881,0.00007342084,0.0016938178,0.0001587838,0.00084066694,0.000010986057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035172137,0.0020790368,0.010551556,0.0004017959,0.0004261554,0.000017299164,0.018817566,0.07173761,0.0140133165,0.35105246,0.005576878,0.5218091],"study_design_scores_gemma":[0.00051645696,0.0012910174,0.0002232889,0.000020384685,0.000049177244,0.0001377542,0.005202887,0.73173654,0.00045942352,0.0010857832,0.2590193,0.00025799207],"about_ca_topic_score_codex":0.0007387496,"about_ca_topic_score_gemma":0.0006828542,"teacher_disagreement_score":0.9630629,"about_ca_system_score_codex":0.00028386177,"about_ca_system_score_gemma":0.00019811779,"threshold_uncertainty_score":0.99998295},"labels":[],"label_agreement":null},{"id":"W4309044635","doi":"10.36227/techrxiv.21067438.v2","title":"A Trustworthy View on XAI Method Evaluation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Trustworthiness; Computer science; Centroid; Process (computing); Cluster analysis; Data mining; Order (exchange); Feature (linguistics); Artificial intelligence; Business; Computer security","score_opus":0.12025309599460612,"score_gpt":0.41603309383123727,"score_spread":0.2957799978366311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309044635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006187751,0.00041861724,0.88821214,0.0030743063,0.0023185178,0.0012000577,0.0000042175957,0.00041417114,0.1037392],"genre_scores_gemma":[0.113809414,0.00039049264,0.8593702,0.009233121,0.0006882389,0.0032561722,0.000119530094,0.00011317527,0.013019711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949006,0.0012667888,0.0005667877,0.0013434545,0.0014843565,0.00043805386],"domain_scores_gemma":[0.99662596,0.00042229085,0.0002869821,0.0022227408,0.0003167088,0.00012534086],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053491974,0.00034639903,0.00041209895,0.0003268953,0.00026777023,0.00041636016,0.0026242682,0.000182211,0.0057593547],"category_scores_gemma":[0.00035076446,0.0003343758,0.00024266868,0.0006708386,0.000025621423,0.00027634524,0.0031399864,0.0009248846,0.0008882516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000943009,0.00014544306,0.000016625845,0.000055217057,0.00004607017,0.000021630149,0.0010789488,0.12063859,0.00003887537,0.29222766,0.00451586,0.58120567],"study_design_scores_gemma":[0.000062715306,0.00013618762,0.000063541906,0.00005273696,0.000032772765,0.0000051372003,0.00013732363,0.77659786,0.003383482,0.16757734,0.051509812,0.0004411104],"about_ca_topic_score_codex":0.00045389612,"about_ca_topic_score_gemma":0.00008680179,"teacher_disagreement_score":0.65595925,"about_ca_system_score_codex":0.0005233189,"about_ca_system_score_gemma":0.0006121055,"threshold_uncertainty_score":0.99991083},"labels":[],"label_agreement":null},{"id":"W4309203559","doi":"10.36227/techrxiv.21545478.v1","title":"The Analysis and Development of an XAI Process on Feature Contribution Explanation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Feature (linguistics); Computer science; Ranking (information retrieval); Process (computing); Data mining; Feature selection; Artificial intelligence; Information retrieval","score_opus":0.024819464223268996,"score_gpt":0.3125622218725441,"score_spread":0.28774275764927515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309203559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29188654,0.0001461236,0.7044087,0.0016520823,0.00031444945,0.00057928107,0.000010613542,0.00012539652,0.0008768215],"genre_scores_gemma":[0.98803544,0.00002953324,0.011363653,0.00009113128,0.000020536241,0.00013172507,0.0001075947,0.000005436214,0.00021496533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829215,0.00014015233,0.00032130335,0.00051810214,0.0005324537,0.00019583601],"domain_scores_gemma":[0.9985848,0.0001402849,0.00028402885,0.00061319256,0.0003191279,0.000058556507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009909977,0.00015836542,0.00022374098,0.0002568631,0.00046824155,0.00025328208,0.00096193136,0.00010611467,0.000026526004],"category_scores_gemma":[0.000093086936,0.000115464085,0.00005295,0.00067761977,0.00003737633,0.00021114771,0.00060507056,0.0003188224,0.0000029892242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018671472,0.00064790534,0.0034811704,0.00021806233,0.0016424516,0.000026492513,0.03281305,0.079392865,0.00063263427,0.29133862,0.0004985099,0.5891215],"study_design_scores_gemma":[0.0002574075,0.0003184816,0.0302571,0.00007843914,0.00023729175,0.000004834613,0.0072694574,0.5856133,0.3224207,0.042968106,0.009425872,0.0011489951],"about_ca_topic_score_codex":0.00007308207,"about_ca_topic_score_gemma":0.00075091555,"teacher_disagreement_score":0.6961489,"about_ca_system_score_codex":0.0001420132,"about_ca_system_score_gemma":0.00024868944,"threshold_uncertainty_score":0.4708489},"labels":[],"label_agreement":null},{"id":"W4309206502","doi":"10.36227/techrxiv.21545478","title":"The Analysis and Development of an XAI Process on Feature Contribution Explanation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Feature (linguistics); Computer science; Process (computing); Ranking (information retrieval); Data mining; Feature selection; Artificial intelligence; Information retrieval","score_opus":0.024819464223268996,"score_gpt":0.3125622218725441,"score_spread":0.28774275764927515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309206502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29188654,0.0001461236,0.7044087,0.0016520823,0.00031444945,0.00057928107,0.000010613542,0.00012539652,0.0008768215],"genre_scores_gemma":[0.98803544,0.00002953324,0.011363653,0.00009113128,0.000020536241,0.00013172507,0.0001075947,0.000005436214,0.00021496533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829215,0.00014015233,0.00032130335,0.00051810214,0.0005324537,0.00019583601],"domain_scores_gemma":[0.9985848,0.0001402849,0.00028402885,0.00061319256,0.0003191279,0.000058556507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009909977,0.00015836542,0.00022374098,0.0002568631,0.00046824155,0.00025328208,0.00096193136,0.00010611467,0.000026526004],"category_scores_gemma":[0.000093086936,0.000115464085,0.00005295,0.00067761977,0.00003737633,0.00021114771,0.00060507056,0.0003188224,0.0000029892242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018671472,0.00064790534,0.0034811704,0.00021806233,0.0016424516,0.000026492513,0.03281305,0.079392865,0.00063263427,0.29133862,0.0004985099,0.5891215],"study_design_scores_gemma":[0.0002574075,0.0003184816,0.0302571,0.00007843914,0.00023729175,0.000004834613,0.0072694574,0.5856133,0.3224207,0.042968106,0.009425872,0.0011489951],"about_ca_topic_score_codex":0.00007308207,"about_ca_topic_score_gemma":0.00075091555,"teacher_disagreement_score":0.6961489,"about_ca_system_score_codex":0.0001420132,"about_ca_system_score_gemma":0.00024868944,"threshold_uncertainty_score":0.4708489},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10646275466905696,"score_gpt":0.4673112791791384,"score_spread":0.3608485245100814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309630525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32091933,0.00075789355,0.6552469,0.021261988,0.00021841637,0.00028375073,0.000008958584,0.00008436309,0.0012183613],"genre_scores_gemma":[0.9821557,0.00023055113,0.014419653,0.0026942976,0.00012619405,0.000121504716,0.00005066841,0.000013844238,0.00018763467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98763376,0.0023496628,0.002491142,0.0010451744,0.005939686,0.0005405658],"domain_scores_gemma":[0.9955252,0.0010238172,0.00046351046,0.0011550032,0.0012601754,0.0005723198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031864963,0.0002342665,0.0012267776,0.0017993469,0.00024163596,0.00012553169,0.0018501924,0.00018305506,0.007003912],"category_scores_gemma":[0.015116978,0.00021769105,0.0006793704,0.011442973,0.0004437199,0.0007372114,0.00146413,0.000756394,0.000025284053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013743344,0.003131842,0.18903507,0.00009712,0.009828517,0.002493722,0.003499475,0.020918047,0.00060258195,0.0074073644,0.01603569,0.7468131],"study_design_scores_gemma":[0.00041919044,0.00008315849,0.008704822,0.000010543923,0.0022000936,0.000008409175,0.000725102,0.9841737,0.0003265788,0.0021868076,0.000944874,0.00021667585],"about_ca_topic_score_codex":0.0026045202,"about_ca_topic_score_gemma":0.0022368187,"teacher_disagreement_score":0.9632557,"about_ca_system_score_codex":0.00013195447,"about_ca_system_score_gemma":0.00088047364,"threshold_uncertainty_score":0.9968988},"labels":[],"label_agreement":null},{"id":"W4309786421","doi":"10.3390/app122211750","title":"Explainable-AI in Automated Medical Report Generation Using Chest X-ray Images","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transparency (behavior); Computer science; Trustworthiness; Field (mathematics); Data science; Computer security","score_opus":0.05818764195076393,"score_gpt":0.32765044737864485,"score_spread":0.2694628054278809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309786421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6777064,0.00016450221,0.30014357,0.0056529786,0.0014226234,0.0007009479,0.0000018853486,0.0010561468,0.013150932],"genre_scores_gemma":[0.97513455,0.0000041013627,0.023559166,0.0009802483,0.00009115528,0.00012535632,0.000004310565,0.000008339381,0.000092762144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629694,0.00015543413,0.0005560451,0.0008571552,0.0015343528,0.0006000769],"domain_scores_gemma":[0.9990088,0.00012458955,0.00018443033,0.00048403512,0.00006206886,0.00013608579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043360176,0.00016584505,0.00020629416,0.00037310453,0.001262052,0.0003779201,0.0018189606,0.0000589158,0.00017016979],"category_scores_gemma":[0.00020638936,0.0001625399,0.00003830737,0.0027033885,0.00033351575,0.0008618495,0.00082925946,0.00029732744,0.00003108716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016669654,0.0006606527,0.003215271,0.000032519245,0.000019106985,0.0036298414,0.0065669976,0.3610481,0.2895314,0.29795375,0.011136304,0.026189351],"study_design_scores_gemma":[0.000089603105,0.00005776063,0.00035883783,0.0000061129244,0.0000020665072,0.00019398126,0.0013328593,0.9652746,0.027304986,0.0032111735,0.0019089822,0.0002590421],"about_ca_topic_score_codex":0.0005151325,"about_ca_topic_score_gemma":0.00007243003,"teacher_disagreement_score":0.60422647,"about_ca_system_score_codex":0.00018362317,"about_ca_system_score_gemma":0.0007745014,"threshold_uncertainty_score":0.97068113},"labels":[],"label_agreement":null},{"id":"W4310496924","doi":"10.1016/j.artmed.2022.102471","title":"Why did AI get this one wrong? — Tree-based explanations of machine learning model predictions","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"European Commission","keywords":"Computer science; Machine learning; Artificial intelligence; Boosting (machine learning); Decision tree; Ensemble learning; Fidelity; Gradient boosting; Random forest","score_opus":0.0677420181985633,"score_gpt":0.3151730733071335,"score_spread":0.24743105510857022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310496924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051467717,0.00034619553,0.9688201,0.021623762,0.000610235,0.0005248203,0.000021325342,0.00034893342,0.002557867],"genre_scores_gemma":[0.98502535,0.00006747036,0.011258161,0.0029287376,0.00012912908,0.00026371054,0.00004164024,0.0000438138,0.0002420209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952797,0.00046244496,0.0014879699,0.0008106921,0.0012815595,0.0006776294],"domain_scores_gemma":[0.9973846,0.0007729487,0.00038483526,0.0009077933,0.00034614204,0.00020365536],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021189488,0.0003233361,0.00056423293,0.0011391554,0.00070987496,0.00005981351,0.0017157693,0.000099429424,0.0012442213],"category_scores_gemma":[0.0009882866,0.00034025518,0.00012911447,0.0029268647,0.00043663915,0.0006302689,0.00043582023,0.0011130125,0.00006082882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074473704,0.00067846605,0.0008952826,0.000026222246,0.000024058198,0.000034260556,0.005343143,0.78890115,0.005760436,0.16788027,0.0010786073,0.029303623],"study_design_scores_gemma":[0.00008088402,0.0006729873,0.000032410368,0.0000733606,0.00002321333,0.0000062297645,0.0014621831,0.9126665,0.0204702,0.062389676,0.0018493489,0.0002730143],"about_ca_topic_score_codex":0.0037179114,"about_ca_topic_score_gemma":0.0026646357,"teacher_disagreement_score":0.97987854,"about_ca_system_score_codex":0.00031480755,"about_ca_system_score_gemma":0.0002961847,"threshold_uncertainty_score":0.99990493},"labels":[],"label_agreement":null},{"id":"W4311133008","doi":"10.21432/cjlt28261","title":"Cognification in Learning, Teaching, and Training","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Blended learning; Certification; Educational technology; Process (computing); Quality (philosophy); Instructional design; Learning sciences; Knowledge management; Mathematics education; Multimedia; Psychology; Management","score_opus":0.017002125617920128,"score_gpt":0.24766906527189658,"score_spread":0.23066693965397644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311133008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98084766,0.0013817464,0.009552818,0.0067546326,0.00013722297,0.000049853847,2.3127413e-7,0.000040949315,0.0012348638],"genre_scores_gemma":[0.9973749,0.00002540376,0.002217964,0.000029715102,0.000014103522,0.0000032865946,3.1407887e-7,0.000005846755,0.00032847453],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990827,0.00021526893,0.00021908447,0.00015289136,0.00008396207,0.00024611293],"domain_scores_gemma":[0.9994869,0.0000874637,0.00016906594,0.00007245671,0.000051057996,0.00013305452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012639648,0.00006450648,0.00013348353,0.0010420615,0.00063263765,0.000069048976,0.0002965577,0.000055143253,0.000019540863],"category_scores_gemma":[0.00076596177,0.0000726825,0.000013484229,0.00043212116,0.00010408085,0.00015809534,0.00006439979,0.0016198615,0.0000014426693],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044744065,0.000013315204,0.17641658,0.0000072535004,0.000014149564,0.00050056516,0.016270319,0.0021983078,0.0012891853,0.1222181,0.000112146285,0.6809556],"study_design_scores_gemma":[0.0007725461,0.002615101,0.0042426414,0.00011557725,0.00001859865,0.0056377705,0.13138932,0.052299872,0.0012103593,0.046164457,0.754917,0.00061671645],"about_ca_topic_score_codex":0.00066808535,"about_ca_topic_score_gemma":0.0016482569,"teacher_disagreement_score":0.7548049,"about_ca_system_score_codex":0.000080709164,"about_ca_system_score_gemma":0.00032036798,"threshold_uncertainty_score":0.7037582},"labels":[],"label_agreement":null},{"id":"W4311218274","doi":"10.36227/techrxiv.21545478.v2","title":"The Analysis and Development of an XAI Process on Feature Contribution Explanation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Feature (linguistics); Computer science; Ranking (information retrieval); Process (computing); Data mining; Feature selection; Artificial intelligence","score_opus":0.024819464223268996,"score_gpt":0.3125622218725441,"score_spread":0.28774275764927515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311218274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29188654,0.0001461236,0.7044087,0.0016520823,0.00031444945,0.00057928107,0.000010613542,0.00012539652,0.0008768215],"genre_scores_gemma":[0.98803544,0.00002953324,0.011363653,0.00009113128,0.000020536241,0.00013172507,0.0001075947,0.000005436214,0.00021496533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829215,0.00014015233,0.00032130335,0.00051810214,0.0005324537,0.00019583601],"domain_scores_gemma":[0.9985848,0.0001402849,0.00028402885,0.00061319256,0.0003191279,0.000058556507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009909977,0.00015836542,0.00022374098,0.0002568631,0.00046824155,0.00025328208,0.00096193136,0.00010611467,0.000026526004],"category_scores_gemma":[0.000093086936,0.000115464085,0.00005295,0.00067761977,0.00003737633,0.00021114771,0.00060507056,0.0003188224,0.0000029892242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018671472,0.00064790534,0.0034811704,0.00021806233,0.0016424516,0.000026492513,0.03281305,0.079392865,0.00063263427,0.29133862,0.0004985099,0.5891215],"study_design_scores_gemma":[0.0002574075,0.0003184816,0.0302571,0.00007843914,0.00023729175,0.000004834613,0.0072694574,0.5856133,0.3224207,0.042968106,0.009425872,0.0011489951],"about_ca_topic_score_codex":0.00007308207,"about_ca_topic_score_gemma":0.00075091555,"teacher_disagreement_score":0.6961489,"about_ca_system_score_codex":0.0001420132,"about_ca_system_score_gemma":0.00024868944,"threshold_uncertainty_score":0.4708489},"labels":[],"label_agreement":null},{"id":"W4311557029","doi":"10.1371/journal.pcbi.1010718","title":"Eleven quick tips for data cleaning and feature engineering","year":2022,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Computer science; Feature (linguistics); Data science; Field (mathematics); Component (thermodynamics); Informatics; Preprocessor; Data pre-processing; Data mining; Key (lock); Health informatics; Artificial intelligence; Machine learning; Engineering; Health care; Deep learning","score_opus":0.06451839150280238,"score_gpt":0.28907768912242143,"score_spread":0.22455929761961907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311557029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022664117,0.0002286187,0.97299004,0.0033653206,0.00026353824,0.0002281891,0.00007680138,0.00012958099,0.00005377746],"genre_scores_gemma":[0.74780387,0.0000030889837,0.2510143,0.0006371521,0.000103568374,0.00005893689,0.00031874183,0.000011282424,0.000049054357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903727,0.000055863904,0.00014498024,0.00042788545,0.00011024545,0.00022376957],"domain_scores_gemma":[0.9989551,0.000592796,0.00005869678,0.00028343257,0.00006348417,0.000046500685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028371502,0.00009007188,0.00011899117,0.00009261517,0.00027610335,0.00004988659,0.0008644774,0.000033337914,0.000012527526],"category_scores_gemma":[0.00014641996,0.000097348246,0.000018632982,0.0001925686,0.000026533055,0.00021734787,0.0010636077,0.00014694357,0.000008142855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003063375,0.000106794454,0.0010407344,0.000039605053,0.00009031603,0.000011915182,0.0008494047,0.13571067,0.004531209,0.8248044,0.0059121586,0.026872117],"study_design_scores_gemma":[0.00008539841,0.00012381736,0.00018726377,0.000002999438,0.0000037408054,0.00003297026,0.00004720028,0.9548575,0.0002467565,0.02721547,0.01708088,0.000115980445],"about_ca_topic_score_codex":0.000010000049,"about_ca_topic_score_gemma":0.0000029258363,"teacher_disagreement_score":0.8191469,"about_ca_system_score_codex":0.000038224916,"about_ca_system_score_gemma":0.00006171525,"threshold_uncertainty_score":0.39697462},"labels":[],"label_agreement":null},{"id":"W4311681011","doi":"10.22215/etd/2022-15159","title":"Effective Explainable Artificial Intelligence using Visual Explanations in Images","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Relevance (law); Taxonomy (biology); Feature (linguistics); Contextual image classification; Architecture; Machine learning; Image (mathematics)","score_opus":0.032743406047617746,"score_gpt":0.35412209037228376,"score_spread":0.321378684324666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311681011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1177562,0.0007792299,0.8329804,0.00029035928,0.0050148033,0.0031339817,0.000023556167,0.00072958216,0.03929192],"genre_scores_gemma":[0.96939903,0.00009438461,0.021580333,0.00019302817,0.00027054953,0.0012562983,0.00038494947,0.0001170288,0.006704418],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958405,0.0003755865,0.0009330215,0.001217618,0.0008109272,0.0008223617],"domain_scores_gemma":[0.99795306,0.00057772023,0.00035306902,0.000694092,0.00028682075,0.00013524803],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00095896726,0.00050565356,0.00053166604,0.0013786235,0.00063173403,0.00052269624,0.0016536654,0.00026022628,0.0010188106],"category_scores_gemma":[0.00038436576,0.0005758471,0.00018151685,0.0024662428,0.00005491738,0.0014794137,0.00035272594,0.0008697294,0.00020012018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019307178,0.0013067292,0.00013551599,0.00034023268,0.00010621871,0.0008057851,0.021070788,0.03689128,0.014105642,0.64784104,0.0005199386,0.27668375],"study_design_scores_gemma":[0.00008064945,0.00045160804,0.00030695164,0.00025437417,0.000042102543,0.000031638872,0.049082175,0.37443897,0.45593768,0.11674152,0.00084713,0.0017851853],"about_ca_topic_score_codex":0.0028063527,"about_ca_topic_score_gemma":0.0038536696,"teacher_disagreement_score":0.8516428,"about_ca_system_score_codex":0.0008199823,"about_ca_system_score_gemma":0.0004887962,"threshold_uncertainty_score":0.9998944},"labels":[],"label_agreement":null},{"id":"W4312237232","doi":"10.1145/3555858.3555880","title":"Charting the Uncharted with GUR: How AI Playtesting Can Supplement Expert Evaluation","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science","score_opus":0.05651076799166636,"score_gpt":0.2969202972071227,"score_spread":0.24040952921545636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312237232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10289741,0.00014507012,0.6765829,0.21383439,0.0006735947,0.0019463267,0.000007801913,0.00061049795,0.0033020095],"genre_scores_gemma":[0.9881692,8.942442e-7,0.007029282,0.0038098602,0.000085144835,0.0005034882,0.00001052381,0.00001265952,0.00037896392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974773,0.00031216795,0.00022246585,0.00043906362,0.0010982279,0.0004507759],"domain_scores_gemma":[0.9987139,0.00019630835,0.00013602537,0.00063522975,0.00024977763,0.00006873475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020041715,0.0001460402,0.00010779815,0.00008559749,0.0012498888,0.0003702336,0.0009800766,0.000014481321,0.00061293616],"category_scores_gemma":[0.00014478124,0.0001004448,0.000034224693,0.00078371575,0.000040345025,0.0004312863,0.0005056466,0.00021783296,0.000015466792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071615825,0.0005100233,0.006453135,0.000026148462,0.0001692018,0.00012491972,0.101008564,0.14050576,0.037145007,0.33185,0.06842855,0.31370708],"study_design_scores_gemma":[0.00016618238,0.00025090546,0.00010941948,0.000007420653,0.0000075849493,0.000030164718,0.010160632,0.9416006,0.03569225,0.0015790993,0.010178841,0.00021689877],"about_ca_topic_score_codex":0.0007960269,"about_ca_topic_score_gemma":0.0005818989,"teacher_disagreement_score":0.8852718,"about_ca_system_score_codex":0.0002658368,"about_ca_system_score_gemma":0.00020657266,"threshold_uncertainty_score":0.96132606},"labels":[],"label_agreement":null},{"id":"W4313042655","doi":"10.1109/healthcom54947.2022.9982786","title":"Trustworthy Explanations for Knowledge Discovered from E-Health Records","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Computer science; Big data; Data science; Health records; Trustworthiness; Process (computing); Health care; Health informatics; Informatics; Knowledge extraction; Variety (cybernetics); Knowledge management; Data mining; Internet privacy; Artificial intelligence; Engineering; Political science","score_opus":0.0576662021283778,"score_gpt":0.31857399145376875,"score_spread":0.26090778932539094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313042655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033052913,0.00026649464,0.9773569,0.00723508,0.0014611251,0.0005193887,0.00013823686,0.00021853612,0.009498908],"genre_scores_gemma":[0.82590276,0.000039354498,0.15110344,0.0031699433,0.0003368784,0.0011312471,0.00022079071,0.000035908404,0.018059704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998478,0.00013290305,0.00032527716,0.00046749978,0.00021615748,0.0003801834],"domain_scores_gemma":[0.9986599,0.00045609413,0.0001079902,0.00058277894,0.000072565774,0.00012065377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048491353,0.000116392475,0.00016886296,0.00013505318,0.0008260075,0.00013455492,0.0010639203,0.000021093621,0.0006921657],"category_scores_gemma":[0.00008297654,0.00011934153,0.000090458474,0.0005940263,0.000020838508,0.0005074384,0.00043881172,0.0001300455,0.0001326526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021314176,0.00033428927,0.00023922983,0.000009668952,0.000028334596,0.0000036216204,0.006006665,0.001472269,0.00009500793,0.67935044,0.14102057,0.17141858],"study_design_scores_gemma":[0.00027293497,0.00043837336,0.00027831804,0.0000066366497,0.00000489224,0.000003737161,0.0035007107,0.20937191,0.0018857091,0.086659744,0.6972218,0.0003551969],"about_ca_topic_score_codex":0.0012448208,"about_ca_topic_score_gemma":0.0017841154,"teacher_disagreement_score":0.8262535,"about_ca_system_score_codex":0.0002445629,"about_ca_system_score_gemma":0.0003476832,"threshold_uncertainty_score":0.7578729},"labels":[],"label_agreement":null},{"id":"W4313430531","doi":"10.1038/s42256-022-00592-3","title":"Interpretability of artificial neural network models in artificial intelligence versus neuroscience","year":2022,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); York University","funders":"","keywords":"Interpretability; Artificial neural network; Artificial intelligence; Cognitive science; Computer science; Neuroscience; Neural system; Machine learning; Psychology","score_opus":0.0406434389929488,"score_gpt":0.31454382685757953,"score_spread":0.2739003878646307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313430531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065872766,0.0016067589,0.9205333,0.0018586178,0.0071490086,0.0009992436,0.000046017743,0.00032840922,0.0016058679],"genre_scores_gemma":[0.99020797,0.000041704712,0.008634777,0.0007208188,0.00018609804,0.00013012748,0.000009743503,0.000040536277,0.000028228853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99236083,0.000841411,0.0019308235,0.0018278213,0.0016545432,0.0013845674],"domain_scores_gemma":[0.9957694,0.001119247,0.0005817438,0.0019352627,0.00032684056,0.00026749892],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0030327663,0.00060217147,0.0007424586,0.00065411837,0.00062506064,0.00023784465,0.0058132117,0.00028414972,0.00021862547],"category_scores_gemma":[0.0011078086,0.00064038055,0.0003330763,0.0055335956,0.0005657996,0.0014321321,0.002919094,0.003243351,0.00002969932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003749417,0.00033205101,0.00021191606,0.000016781974,0.0000065053723,0.00006457492,0.0010442203,0.5547665,0.0007696564,0.3279367,0.000035171786,0.114441],"study_design_scores_gemma":[0.000032048036,0.00053521304,0.000094748895,0.000019848534,0.000008263642,0.000027882948,0.00043670918,0.7526555,0.019817816,0.22567698,0.00023719815,0.00045779944],"about_ca_topic_score_codex":0.00065174623,"about_ca_topic_score_gemma":0.00095664675,"teacher_disagreement_score":0.9243352,"about_ca_system_score_codex":0.000417566,"about_ca_system_score_gemma":0.00034642924,"threshold_uncertainty_score":0.99960476},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.17247013805736797,"score_gpt":0.4127461832334518,"score_spread":0.24027604517608384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313648826","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016491995,0.9962899,0.0011991026,0.00025172214,0.0003495461,0.0010763914,0.0000406505,0.00042287188,0.0003533293],"genre_scores_gemma":[0.000084846,0.99762267,0.0012885715,0.000062413215,0.000036599384,0.00006993923,0.00002998293,0.00005826459,0.0007467342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960828,0.0009934847,0.0011612613,0.0007353073,0.0003870615,0.0006401142],"domain_scores_gemma":[0.9971392,0.0007885475,0.00042960467,0.0012255124,0.00030653522,0.00011060948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002217089,0.00037471156,0.0015976417,0.00085407833,0.00006681421,0.000078570476,0.0016143366,0.0003777331,0.0000054688385],"category_scores_gemma":[0.0006302952,0.00034876697,0.00022291472,0.003511382,0.000077323486,0.00022264944,0.00046142953,0.00057766493,0.0002898249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014255945,0.000038409344,0.00004045642,0.009360183,0.000019542735,0.00013849467,0.00021382247,0.000016906675,2.1428147e-7,0.009427355,0.0006102986,0.9801329],"study_design_scores_gemma":[0.00003928703,0.00021317537,0.00006768738,0.01927325,0.000028719978,0.000028330585,0.00009086762,0.0016666837,0.0005171569,0.0042214263,0.97279865,0.0010547829],"about_ca_topic_score_codex":0.01717574,"about_ca_topic_score_gemma":0.0045236372,"teacher_disagreement_score":0.9790781,"about_ca_system_score_codex":0.00023896714,"about_ca_system_score_gemma":0.0006028484,"threshold_uncertainty_score":0.9998964},"labels":[],"label_agreement":null},{"id":"W4315926692","doi":"10.1109/cicn56167.2022.10008240","title":"A Data Mining Analysis of Cognitive Science and Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognition; Scopus; Scope (computer science); Computer science; Data science; Visualization; Artificial intelligence; Data visualization; Institution; China; Psychology; Political science; Sociology; Social science","score_opus":0.16496256934163753,"score_gpt":0.3729542460312511,"score_spread":0.20799167668961357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315926692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016485091,0.0005519118,0.9752853,0.003515233,0.0004252644,0.00038237663,0.00021176324,0.00009136124,0.003051713],"genre_scores_gemma":[0.98385906,0.00058997015,0.014154152,0.00076239434,0.00004048882,0.00009328777,0.00042957332,0.000013885928,0.0000571639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954821,0.00037838958,0.0009901095,0.001120655,0.0016302114,0.00039854806],"domain_scores_gemma":[0.99439055,0.0018293593,0.0006195946,0.0012730806,0.0017037407,0.00018365137],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002916554,0.00029021446,0.00040525044,0.0013028265,0.0011885118,0.0005578646,0.0050403154,0.00006421281,0.00043245597],"category_scores_gemma":[0.00068045955,0.00032854849,0.000077257304,0.0038314299,0.0010633649,0.0013022936,0.0048678173,0.0005763389,0.000009482597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006659539,0.0001928899,0.00021820686,0.000003572013,0.00021316131,0.0000043484833,0.0014124446,0.20367073,0.000024827661,0.6527711,0.00006462106,0.14135751],"study_design_scores_gemma":[0.00003785644,0.00020286089,0.0007033904,0.000053761698,0.00008359502,0.00001689767,0.0052243723,0.9361858,0.0001941358,0.056818623,0.00018068141,0.00029803105],"about_ca_topic_score_codex":0.0001388181,"about_ca_topic_score_gemma":0.00011582015,"teacher_disagreement_score":0.96737397,"about_ca_system_score_codex":0.00017674427,"about_ca_system_score_gemma":0.0004733486,"threshold_uncertainty_score":0.9999167},"labels":[],"label_agreement":null},{"id":"W4316663035","doi":"10.1007/s10677-022-10359-9","title":"Self-fulfilling Prophecy in Practical and Automated Prediction","year":2023,"lang":"en","type":"article","venue":"Ethical Theory and Moral Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; University of Twente","keywords":"Philosophy of medicine; Political philosophy; Ontology; Epistemology; Philosophy; Political science; Politics; Medicine; Law","score_opus":0.05157492020365166,"score_gpt":0.3670678756114968,"score_spread":0.3154929554078451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316663035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38730836,0.000623373,0.346925,0.230816,0.0016967468,0.001942533,0.000008583568,0.009755926,0.020923488],"genre_scores_gemma":[0.9586566,0.0003455273,0.038663603,0.002084554,0.0000788194,0.000031241823,0.000002070392,0.000012824464,0.00012475581],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710006,0.0014931419,0.00029451572,0.00047507105,0.00029205877,0.00034514454],"domain_scores_gemma":[0.99387205,0.0055136527,0.000095786345,0.0002592771,0.000111579124,0.00014765322],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070751477,0.00013326132,0.00015512513,0.00013477154,0.00023688555,0.00027433253,0.00018012905,0.0002990822,0.000007778473],"category_scores_gemma":[0.009294376,0.000120242286,0.000020417196,0.0007784178,0.00015015583,0.0018521462,0.0002925079,0.0011680772,0.000108008564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015436439,0.000089228124,0.00011129524,0.000039727303,0.000014873626,0.00029192024,0.0035485907,0.00016042612,0.00048360205,0.9901797,0.00020947123,0.0047167805],"study_design_scores_gemma":[0.0002816484,0.0003071114,0.0012539504,0.000057352918,0.00002736962,0.00030498987,0.0017914372,0.5891606,0.0016978307,0.39159432,0.013256214,0.00026717674],"about_ca_topic_score_codex":0.00002472623,"about_ca_topic_score_gemma":0.00000433824,"teacher_disagreement_score":0.5985854,"about_ca_system_score_codex":0.000031410622,"about_ca_system_score_gemma":0.00011437598,"threshold_uncertainty_score":0.99905074},"labels":[],"label_agreement":null},{"id":"W4317826891","doi":"10.1109/iv56949.2022.00066","title":"Evaluation of Deep Learning Context-Sensitive Visualization Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Visualization; Artificial intelligence; Machine learning; Classifier (UML); Debugging; Natural language processing; Artificial neural network; Context (archaeology); Quality (philosophy); Creative visualization; Transformer","score_opus":0.07864008344659594,"score_gpt":0.329978200570619,"score_spread":0.25133811712402304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317826891","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039607577,0.000070932445,0.9480671,0.00012720286,0.00013580018,0.0002204306,3.7439128e-7,0.000093200615,0.011677357],"genre_scores_gemma":[0.9976867,0.000002853013,0.0019199562,0.00015171523,0.000011173038,0.00003664524,0.0000042957813,0.000006274159,0.00018038816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762326,0.0006976085,0.0002343136,0.00024605196,0.0010478061,0.00015097286],"domain_scores_gemma":[0.99871665,0.00010836705,0.00013130509,0.0002116345,0.0008011431,0.0000308699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026654082,0.0000684021,0.00009987384,0.00012952322,0.00025945582,0.000038937284,0.00030069522,0.000018432995,0.00021257203],"category_scores_gemma":[0.00019624489,0.000074706346,0.000037364414,0.00055116013,0.000024159926,0.0006057757,0.00026707846,0.00009536153,0.000018969915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003017954,0.000033008724,0.000019850651,0.0000013176227,0.000007425304,9.341558e-7,0.00384196,0.50235736,0.0013375286,0.39189628,0.00001835379,0.10048297],"study_design_scores_gemma":[0.00007708683,0.000105654806,0.00003212947,0.0000020023065,0.000010679768,0.0000033039707,0.0040011085,0.91928655,0.03812866,0.0381776,0.00009639296,0.00007882905],"about_ca_topic_score_codex":0.00019811194,"about_ca_topic_score_gemma":0.00006840994,"teacher_disagreement_score":0.9580791,"about_ca_system_score_codex":0.00016887339,"about_ca_system_score_gemma":0.00009344561,"threshold_uncertainty_score":0.30464363},"labels":[],"label_agreement":null},{"id":"W4318145939","doi":"10.48550/arxiv.2301.10074","title":"Explainable Data-Driven Optimization: From Context to Decision and Back Again","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Interpretability; Counterfactual thinking; Computer science; Random forest; Bridge (graph theory); Machine learning; Context (archaeology); Decision tree; Artificial intelligence; Key (lock); Data science; Data mining","score_opus":0.20320976523873663,"score_gpt":0.23959857443275917,"score_spread":0.03638880919402254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318145939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048062425,0.00007071129,0.9491027,0.00043549735,0.0008177058,0.00052127434,0.00011311322,0.00031489186,0.0005616721],"genre_scores_gemma":[0.89678603,0.0005220305,0.09760425,0.00048494348,0.00015913109,0.0000034166012,0.00022483646,0.000053789325,0.004161582],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657285,0.00016169535,0.00034035766,0.002259973,0.00017450794,0.00049060653],"domain_scores_gemma":[0.99534,0.0005814523,0.00020546424,0.0032435842,0.00026635706,0.00036316676],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041771098,0.000370432,0.0004314665,0.00037818478,0.00027666157,0.0004940724,0.00426587,0.00029182064,0.00015967083],"category_scores_gemma":[0.00026229356,0.00044797402,0.00008128133,0.001027175,0.000101066405,0.0011773787,0.011374564,0.000403846,0.0019230689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046593537,0.000041121435,0.00035043567,0.000019915446,0.000049816845,0.0004162557,0.0005501843,0.97148716,0.000013225799,0.019076778,0.005369586,0.0025789475],"study_design_scores_gemma":[0.00017670679,0.00004924577,0.00011343106,0.00018685222,0.000029099749,0.0000015821657,0.0005826344,0.97197497,0.00018766275,0.022980815,0.003230756,0.00048626174],"about_ca_topic_score_codex":0.0017613792,"about_ca_topic_score_gemma":0.00073190324,"teacher_disagreement_score":0.8514984,"about_ca_system_score_codex":0.00021358051,"about_ca_system_score_gemma":0.00020125724,"threshold_uncertainty_score":0.9997972},"labels":[],"label_agreement":null},{"id":"W4318605527","doi":"10.1109/ssci51031.2022.10022301","title":"Explainable AI Applied to the Analysis of the Climatic Behavior of 11 Years of Meteosat Water Vapor Images","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Satellite; Environmental science; Troposphere; Meteorology; Water vapor; Convolutional neural network; Remote sensing; Climatology; Atmospheric model; Artificial neural network; Computer science; Geography; Artificial intelligence; Geology","score_opus":0.018020663410805812,"score_gpt":0.2670007057219184,"score_spread":0.2489800423111126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318605527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68564934,0.000066445275,0.30305305,0.0065021105,0.0017527328,0.0019480197,0.00029785093,0.000094343355,0.0006361124],"genre_scores_gemma":[0.9944691,0.000010321309,0.004155379,0.0005762538,0.000027039145,0.00034271862,0.00002625316,0.000022893864,0.00037005043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99587256,0.00034789494,0.0011401422,0.0006215674,0.0015474246,0.00047043845],"domain_scores_gemma":[0.99715835,0.0005935009,0.0004926548,0.0012077404,0.00045703774,0.00009068824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013020501,0.00027072988,0.0005824261,0.00064993993,0.00050034974,0.00009049226,0.0029702168,0.000051152747,0.0003004101],"category_scores_gemma":[0.00006298175,0.00019712507,0.00040290682,0.0036593846,0.0003542469,0.00035967625,0.0010886457,0.00030028942,0.000030892905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066803994,0.00030566612,0.00034042788,0.000035700647,0.00016938357,0.0000066090274,0.0067688175,0.92408705,0.023188949,0.04271902,0.00035286104,0.0019587306],"study_design_scores_gemma":[0.00008586105,0.00070055394,0.0027046215,0.000027941516,0.00042499934,0.00001585019,0.005624315,0.12962593,0.84921306,0.010012416,0.0011015424,0.00046290678],"about_ca_topic_score_codex":0.0003681093,"about_ca_topic_score_gemma":0.00012453049,"teacher_disagreement_score":0.8260241,"about_ca_system_score_codex":0.0001541686,"about_ca_system_score_gemma":0.00017354352,"threshold_uncertainty_score":0.80385274},"labels":[],"label_agreement":null},{"id":"W4318614900","doi":"10.2196/41516","title":"Calibrating a Transformer-Based Model’s Confidence on Community-Engaged Research Studies: Decision Support Evaluation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Center for Clinical and Translational Research; National Institutes of Health; Virginia Commonwealth University","keywords":"Overfitting; Computer science; Artificial intelligence; Machine learning; Transformer; Data science; Artificial neural network; Engineering","score_opus":0.6147354217783509,"score_gpt":0.5846268103837878,"score_spread":0.030108611394563112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318614900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8697135,0.000029977053,0.11873341,0.0016694302,0.00024077832,0.004761003,0.000013626624,0.00042624536,0.004412026],"genre_scores_gemma":[0.9964493,0.00003274562,0.00094404456,0.00010089357,0.00003066954,0.0022011197,0.000017564014,0.000032125823,0.00019154283],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9489091,0.040079106,0.0009841166,0.0007647156,0.0074974718,0.0017655113],"domain_scores_gemma":[0.9600053,0.033511717,0.0001156841,0.001747351,0.004338353,0.00028159973],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16890877,0.00029096572,0.0004188552,0.0022777927,0.010767925,0.00071967836,0.0029866928,0.00013624376,0.000054420405],"category_scores_gemma":[0.013301862,0.00025113762,0.00011066382,0.0074749687,0.0005861284,0.002429139,0.00081240525,0.008354225,0.0015415103],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038099661,0.0021848246,0.0001444908,0.00022173011,0.000094924966,0.000079489626,0.8120146,0.060288314,0.0024337878,0.017838247,0.015279932,0.08903867],"study_design_scores_gemma":[0.0005656481,0.0033174953,0.00039055533,0.00021265613,0.0000029256405,0.000001312914,0.21060246,0.7385927,0.011438444,0.034595758,0.000075605385,0.0002044795],"about_ca_topic_score_codex":0.00029213374,"about_ca_topic_score_gemma":0.00076438277,"teacher_disagreement_score":0.6783043,"about_ca_system_score_codex":0.00093941635,"about_ca_system_score_gemma":0.0013075076,"threshold_uncertainty_score":0.9999941},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12907051364670613,"score_gpt":0.3893030887555342,"score_spread":0.2602325751088281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319165740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91793865,0.000017962398,0.008105711,0.06964734,0.0014024199,0.0012959994,0.0000010300681,0.00032484304,0.0012660384],"genre_scores_gemma":[0.9937917,0.000007850965,0.002372418,0.003007332,0.0003799955,0.00025097438,5.349748e-7,0.00002822067,0.00016096006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99717855,0.000087829474,0.0007467211,0.0006793138,0.00062996295,0.0006776261],"domain_scores_gemma":[0.99731076,0.0009016776,0.00037494604,0.0011005717,0.00024697874,0.0000650414],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0021481426,0.00027651028,0.00030403933,0.0004363673,0.0005173797,0.0005481352,0.005765006,0.00016540269,0.000016491244],"category_scores_gemma":[0.0014639167,0.00017285376,0.00016978315,0.0022573175,0.00011283685,0.001062873,0.0030338627,0.0013295145,0.00016540561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003396735,0.0009704392,0.0065986225,0.00034219542,0.000104157465,0.000036802736,0.114852704,0.02548163,0.051725883,0.66312826,0.06094433,0.075475305],"study_design_scores_gemma":[0.00047106313,0.00078342657,0.01683164,0.0029707302,0.000021599952,0.000049254024,0.009020353,0.27572256,0.19838056,0.4878279,0.0069577564,0.0009631545],"about_ca_topic_score_codex":0.0002543983,"about_ca_topic_score_gemma":0.0000830385,"teacher_disagreement_score":0.25024092,"about_ca_system_score_codex":0.00030673167,"about_ca_system_score_gemma":0.00003115616,"threshold_uncertainty_score":0.9996143},"labels":[],"label_agreement":null},{"id":"W4319790235","doi":"10.1111/emip.12539","title":"Machine Learning Literacy for Measurement Professionals: A Practical Tutorial","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Toolbox; Computer science; Python (programming language); Data science; Context (archaeology); Artificial intelligence","score_opus":0.19356892700389544,"score_gpt":0.4464950114435416,"score_spread":0.25292608443964615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319790235","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012623277,0.009274556,0.17189871,0.7974012,0.010064101,0.002651719,0.000012697221,0.00065155403,0.0067831236],"genre_scores_gemma":[0.6779231,0.0013029289,0.3006404,0.0040454026,0.006503541,0.001802153,0.000087874636,0.00009295139,0.0076016807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99619615,0.0006087186,0.00041978425,0.00056431897,0.001790801,0.0004202135],"domain_scores_gemma":[0.99402237,0.0025288619,0.0002588505,0.00031773894,0.0026929672,0.00017922922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008937494,0.00020091592,0.0001840253,0.00016337585,0.00065697654,0.00059128023,0.00032414746,0.00007163228,0.00006990657],"category_scores_gemma":[0.027692406,0.00018587803,0.00006183858,0.0005415924,0.00003771522,0.0024995415,0.00016027196,0.00028169857,0.00025486163],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006714257,0.002015183,0.0005219921,0.0002912403,0.00030830054,0.000020230775,0.016153187,0.0002782043,0.006922656,0.81537926,0.10676059,0.05067773],"study_design_scores_gemma":[0.0002718051,0.00024223347,0.00046088808,0.000116329444,0.00004231407,0.00003760927,0.0009699821,0.011925931,0.0015346659,0.021895234,0.9622102,0.00029282385],"about_ca_topic_score_codex":0.00015123878,"about_ca_topic_score_gemma":0.000014297683,"teacher_disagreement_score":0.8554496,"about_ca_system_score_codex":0.00021276169,"about_ca_system_score_gemma":0.000774089,"threshold_uncertainty_score":0.9804978},"labels":[],"label_agreement":null},{"id":"W4319866359","doi":"10.2139/ssrn.4339925","title":"Danlip: Deep Autoregressive Networks for Locally Interpretable Probabilistic Forecasting","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Autoregressive model; Probabilistic logic; Artificial intelligence; Computer science; Nonlinear autoregressive exogenous model; Econometrics; SETAR; Machine learning; STAR model; Statistics; Autoregressive integrated moving average; Mathematics; Time series","score_opus":0.023306085348002468,"score_gpt":0.26472721585451736,"score_spread":0.2414211305065149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319866359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064969594,0.0007843465,0.9899171,0.00076200627,0.00084213004,0.0004356006,8.834826e-7,0.00030343817,0.00045751102],"genre_scores_gemma":[0.9915351,0.00032988033,0.0055596526,0.0001658483,0.0005862537,0.000101483514,0.000005620835,0.00004840815,0.0016677238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99456865,0.000110506524,0.00053321157,0.0004983187,0.0003432545,0.003946062],"domain_scores_gemma":[0.99826276,0.00048059988,0.00029789814,0.0004298291,0.00036134225,0.00016757555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030531674,0.00025222925,0.00027684084,0.00023641616,0.0006407596,0.00044198422,0.0015464883,0.0001175837,0.0000078841385],"category_scores_gemma":[0.0007792,0.00022694176,0.00019209624,0.00082371745,0.00007724201,0.0008557097,0.0002853549,0.001317539,0.00007037855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054281325,0.000051169918,0.00013710876,0.000021741975,0.00011659893,0.00003958451,0.00095495314,0.13765576,0.00010572375,0.6157118,0.0004828394,0.24466841],"study_design_scores_gemma":[0.00012848654,0.0003278059,0.000010287251,0.000051328047,0.00001145805,0.00023033017,0.00052533834,0.63850236,0.0001207679,0.35936233,0.0005534935,0.0001760306],"about_ca_topic_score_codex":0.00003173491,"about_ca_topic_score_gemma":0.0007711532,"teacher_disagreement_score":0.98503816,"about_ca_system_score_codex":0.0009884977,"about_ca_system_score_gemma":0.0016669866,"threshold_uncertainty_score":0.9254416},"labels":[],"label_agreement":null},{"id":"W4320024021","doi":"10.1109/bigdata55660.2022.10020313","title":"The Analysis and Development of an XAI Process on Feature Contribution Explanation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Computer science; Feature (linguistics); Process (computing); Ranking (information retrieval); Data mining; Feature selection; Artificial intelligence; Information retrieval","score_opus":0.2539979832914212,"score_gpt":0.37115651489714635,"score_spread":0.11715853160572515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26161376,0.0001632976,0.6978266,0.014175231,0.007875231,0.0012740586,0.0148841385,0.00024638145,0.0019412617],"genre_scores_gemma":[0.98577327,0.00006843157,0.0012098926,0.00027794528,0.0001594196,0.00006967019,0.012298395,0.000008522232,0.00013448106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967165,0.00022616226,0.0004401158,0.0009718127,0.0013824123,0.000262992],"domain_scores_gemma":[0.9967681,0.0002245786,0.0003788739,0.0021303708,0.0004056574,0.00009238906],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00166766,0.00019089831,0.00020843322,0.0003809528,0.0007296043,0.0004268448,0.0062341774,0.000049258146,0.000060334234],"category_scores_gemma":[0.0003087125,0.00016358559,0.000024735898,0.0008142921,0.000086259686,0.0011422085,0.0017751167,0.00035542558,0.00001751127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003562506,0.00057003263,0.0006175959,0.000015625692,0.0006535724,0.000036629262,0.0016061486,0.0012349364,0.0027786,0.08992799,0.004991137,0.8972115],"study_design_scores_gemma":[0.00061470055,0.00040175335,0.0050265607,0.000052472085,0.00010041053,0.000022759323,0.0030414173,0.866309,0.03197844,0.005367869,0.08639202,0.0006926274],"about_ca_topic_score_codex":0.0001019392,"about_ca_topic_score_gemma":0.0016057742,"teacher_disagreement_score":0.8965188,"about_ca_system_score_codex":0.00015144872,"about_ca_system_score_gemma":0.00039667965,"threshold_uncertainty_score":0.9991426},"labels":[],"label_agreement":null},{"id":"W4320710261","doi":"10.1080/08989621.2023.2179919","title":"Can ChatGPT be trusted to provide reliable estimates?","year":2023,"lang":"en","type":"letter","venue":"Accountability in Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Direct Anonymous Attestation; Computer security; Internet privacy; Computer science; Scientific misconduct; Trusted Computing; Medicine","score_opus":0.25348492229708014,"score_gpt":0.44915107833577544,"score_spread":0.1956661560386953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320710261","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011622091,0.00003833435,0.00077556807,0.98088056,0.00093584607,0.0029494304,0.000058883274,0.0005706608,0.0021686046],"genre_scores_gemma":[0.040229656,0.000111558315,0.014381901,0.9107402,0.0039546546,0.006423162,0.0003753536,0.0004902538,0.023293281],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98970926,0.0007376699,0.0010391623,0.0023780651,0.0032403101,0.0028955436],"domain_scores_gemma":[0.990083,0.003800906,0.0001268163,0.0042900327,0.001413774,0.0002855085],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009342914,0.00052732934,0.00075349887,0.0018584328,0.00044109623,0.0013843076,0.0064173047,0.0010551644,0.00018457054],"category_scores_gemma":[0.006289001,0.00053592236,0.00014589034,0.006809411,0.00040913562,0.0009048234,0.0031179374,0.00566786,0.0027527756],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027384378,0.00009874188,0.001560197,0.0004169177,0.000016399745,0.00070996705,0.00288145,0.00030402114,0.000112462636,0.00074519176,0.9902774,0.0028498722],"study_design_scores_gemma":[0.00014520543,0.00035344914,0.0008600486,0.00040855244,0.000005800862,0.000013959849,0.0005753678,0.015451848,0.004539295,0.037045702,0.9396437,0.00095707114],"about_ca_topic_score_codex":0.055247303,"about_ca_topic_score_gemma":0.014672861,"teacher_disagreement_score":0.0701404,"about_ca_system_score_codex":0.0021552693,"about_ca_system_score_gemma":0.0015869522,"threshold_uncertainty_score":0.99970925},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4321004017","doi":"10.1037/met0000540","title":"Let the algorithm speak: How to use neural networks for automatic item generation in psychological scale development.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council; Cambridge Trust","keywords":"Computer science; Scale (ratio); Generator (circuit theory); Process (computing); Code (set theory); Artificial neural network; Generative grammar; Artificial intelligence; Machine learning; Algorithm; Natural language processing; Programming language","score_opus":0.23907500105885265,"score_gpt":0.46337447013331007,"score_spread":0.2242994690744574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321004017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07411549,0.00008549393,0.91106474,0.0119102765,0.0011803115,0.0011106624,0.0000018248157,0.00043506423,0.00009612246],"genre_scores_gemma":[0.053017616,0.000048092174,0.93781954,0.007820833,0.00023754772,0.0007199142,0.000013623088,0.0000191978,0.00030360883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959932,0.0012194695,0.0005803063,0.0010266319,0.00032158612,0.00085881364],"domain_scores_gemma":[0.99664396,0.0020683785,0.0001233855,0.0008489978,0.00011777626,0.00019749497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004531591,0.00028026057,0.00036463115,0.00019536473,0.00030283383,0.00044193523,0.001537306,0.00020989255,0.000033890185],"category_scores_gemma":[0.0017317653,0.00018557292,0.00012476393,0.0023741482,0.00009809187,0.00043936033,0.00034120187,0.0003707081,0.00008744636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009278595,0.00014124229,0.00018635918,0.000008106033,0.000006891726,0.00002309204,0.00041569883,0.0020780782,0.00090935966,0.0010481013,0.00908913,0.98608464],"study_design_scores_gemma":[0.00015118907,0.00027650245,0.024087226,0.000027194947,0.0000044848966,0.000024291905,0.00006333544,0.9632928,0.0010798048,0.0025249291,0.008160195,0.0003080499],"about_ca_topic_score_codex":0.0000064422866,"about_ca_topic_score_gemma":0.00002030858,"teacher_disagreement_score":0.9857766,"about_ca_system_score_codex":0.00006952805,"about_ca_system_score_gemma":0.0000107075875,"threshold_uncertainty_score":0.7567444},"labels":[],"label_agreement":null},{"id":"W4322002798","doi":"10.5194/egusphere-egu23-12261","title":"Peeking Inside Hydrologists' Minds: Comparing Human Judgment and Quantitative Metrics of Hydrographs","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Metric (unit); Consistency (knowledge bases); Benchmarking; Set (abstract data type); Computer science; Hydrograph; Quality (philosophy); Similarity (geometry); Artificial intelligence; Scale (ratio); Data science; Preference; Machine learning; Psychology; Cognitive psychology; Mathematics; Statistics; Epistemology; Marketing; Ecology; Geography","score_opus":0.19450038129868139,"score_gpt":0.3616460499875889,"score_spread":0.16714566868890754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322002798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48461634,0.00055552786,0.5068997,0.0004578721,0.00065234833,0.00060097524,0.000004592258,0.00047588395,0.0057367603],"genre_scores_gemma":[0.940638,0.00011058263,0.058912612,0.00007169182,0.000024797406,0.00004611327,0.000009885397,0.000024999761,0.00016132147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674124,0.00017506396,0.0008913278,0.0010733762,0.0006104307,0.0005085478],"domain_scores_gemma":[0.99730635,0.00064691453,0.000567247,0.0010839332,0.00025758703,0.00013795675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013596045,0.00037373096,0.00072981056,0.001256209,0.00021796036,0.0003374886,0.0016373658,0.00024183404,0.000007341179],"category_scores_gemma":[0.0003148985,0.0003733679,0.00018168987,0.0013268568,0.0003003919,0.0002934721,0.0045142565,0.0006037263,0.000030334402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019622763,0.00037815954,0.03751235,0.00068880094,0.00047124614,0.00017108857,0.012251798,0.03600976,0.0034054408,0.89927,0.0006179536,0.0092037935],"study_design_scores_gemma":[0.00019423458,0.00046825272,0.0037620168,0.00040590728,0.000067641224,0.000007603466,0.0019754672,0.7044999,0.07479334,0.21269628,0.00017979588,0.0009495636],"about_ca_topic_score_codex":0.003852622,"about_ca_topic_score_gemma":0.0013227367,"teacher_disagreement_score":0.6865737,"about_ca_system_score_codex":0.00009495268,"about_ca_system_score_gemma":0.00008326054,"threshold_uncertainty_score":0.99987185},"labels":[],"label_agreement":null},{"id":"W4323045233","doi":"10.31219/osf.io/m52yz","title":"The scientific value of explanation and prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Value (mathematics); Predictive value; Scientific modelling; Artificial neural network; Work (physics); Epistemology; Positive economics; Computer science; Artificial intelligence; Economics; Philosophy; Machine learning; Engineering; Medicine","score_opus":0.05602667095228834,"score_gpt":0.2891724972852192,"score_spread":0.23314582633293088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323045233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056260988,0.00026000547,0.9313368,0.003257998,0.005560172,0.0005379425,0.00001382778,0.0004282087,0.002344038],"genre_scores_gemma":[0.9832523,0.00024522824,0.00997202,0.000031939875,0.00010682683,0.00007708333,0.000018457296,0.000014944562,0.006281189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998525,0.00007737528,0.00033124007,0.00047626952,0.00041097714,0.00017912337],"domain_scores_gemma":[0.99847704,0.00028845912,0.00016337834,0.000805986,0.00022299116,0.000042115524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014604072,0.00010349604,0.00010850682,0.00016610988,0.00034663852,0.00066796504,0.0009033938,0.00009697389,0.000002879318],"category_scores_gemma":[0.00021358415,0.00007555299,0.00004298872,0.00036537493,0.00018422048,0.00025031573,0.0012692793,0.00017646747,0.000041802337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038075661,0.000024724897,0.0005209609,0.00007275423,0.000027057464,0.0000026610187,0.001980079,0.0070120376,0.0011448775,0.9536591,0.006064631,0.029487299],"study_design_scores_gemma":[0.000023020582,0.000029761526,0.0021172978,0.000061011848,0.0000066477232,0.0000018751866,0.00032688686,0.698877,0.026180897,0.27015513,0.0021094051,0.00011109776],"about_ca_topic_score_codex":0.0002626027,"about_ca_topic_score_gemma":0.00016494063,"teacher_disagreement_score":0.92699134,"about_ca_system_score_codex":0.00003828582,"about_ca_system_score_gemma":0.00012379358,"threshold_uncertainty_score":0.6441202},"labels":[],"label_agreement":null},{"id":"W4323075198","doi":"10.31234/osf.io/jzgu5","title":"The scientific value of explanation and prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Value (mathematics); Predictive value; Artificial neural network; Scientific modelling; Predictive modelling; Work (physics); Positive economics; Epistemology; Data science; Computer science; Artificial intelligence; Economics; Machine learning; Philosophy; Engineering; Medicine","score_opus":0.05602667095228834,"score_gpt":0.2891724972852192,"score_spread":0.23314582633293088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323075198","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056260988,0.00026000547,0.9313368,0.003257998,0.005560172,0.0005379425,0.00001382778,0.0004282087,0.002344038],"genre_scores_gemma":[0.9832523,0.00024522824,0.00997202,0.000031939875,0.00010682683,0.00007708333,0.000018457296,0.000014944562,0.006281189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998525,0.00007737528,0.00033124007,0.00047626952,0.00041097714,0.00017912337],"domain_scores_gemma":[0.99847704,0.00028845912,0.00016337834,0.000805986,0.00022299116,0.000042115524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014604072,0.00010349604,0.00010850682,0.00016610988,0.00034663852,0.00066796504,0.0009033938,0.00009697389,0.000002879318],"category_scores_gemma":[0.00021358415,0.00007555299,0.00004298872,0.00036537493,0.00018422048,0.00025031573,0.0012692793,0.00017646747,0.000041802337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038075661,0.000024724897,0.0005209609,0.00007275423,0.000027057464,0.0000026610187,0.001980079,0.0070120376,0.0011448775,0.9536591,0.006064631,0.029487299],"study_design_scores_gemma":[0.000023020582,0.000029761526,0.0021172978,0.000061011848,0.0000066477232,0.0000018751866,0.00032688686,0.698877,0.026180897,0.27015513,0.0021094051,0.00011109776],"about_ca_topic_score_codex":0.0002626027,"about_ca_topic_score_gemma":0.00016494063,"teacher_disagreement_score":0.92699134,"about_ca_system_score_codex":0.00003828582,"about_ca_system_score_gemma":0.00012379358,"threshold_uncertainty_score":0.6441202},"labels":[],"label_agreement":null},{"id":"W4323565362","doi":"10.3390/make5010017","title":"Painting the Black Box White: Experimental Findings from Applying XAI to an ECG Reading Setting","year":2023,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ministero della Salute; Università degli Studi di Siena","keywords":"Usability; Computer science; Perception; Relevance (law); Transparency (behavior); Reading (process); Data science; Human–computer interaction; Psychology; Computer security","score_opus":0.023069008272530413,"score_gpt":0.32517115363827465,"score_spread":0.30210214536574426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323565362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8414201,0.00024273315,0.15261945,0.0010956544,0.0006379332,0.00032793096,0.0000013067931,0.0009125536,0.0027423247],"genre_scores_gemma":[0.9918453,0.0000128030815,0.005797698,0.000100195575,0.00034697913,0.00005577051,0.00001788057,0.000033369302,0.001789974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979512,0.00035795328,0.0003205463,0.00065153796,0.00022729061,0.0004914391],"domain_scores_gemma":[0.99881554,0.00054321834,0.000119196775,0.00030306494,0.00006746842,0.00015148974],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017673606,0.00022109268,0.00017506337,0.00023921837,0.0013659495,0.0007025484,0.00041422126,0.00008645751,0.000040171242],"category_scores_gemma":[0.00044078505,0.00019541716,0.000056048542,0.0008565997,0.00004689288,0.0008588991,0.00037574908,0.00061644707,0.00054219365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041921998,0.00015441995,0.057346515,0.000041198786,0.000041650652,0.000046259313,0.1071003,0.010911113,0.26986742,0.0025085963,0.0011387381,0.5508019],"study_design_scores_gemma":[0.00010058859,0.00012976192,0.003970169,0.00008815331,0.000008493915,0.000013667372,0.013430889,0.93419623,0.03401347,0.00037397209,0.0133593045,0.00031527012],"about_ca_topic_score_codex":0.0004581802,"about_ca_topic_score_gemma":0.00011313529,"teacher_disagreement_score":0.9232851,"about_ca_system_score_codex":0.0000983256,"about_ca_system_score_gemma":0.000027616252,"threshold_uncertainty_score":0.99993414},"labels":[],"label_agreement":null},{"id":"W4323571926","doi":"10.48550/arxiv.2303.04437","title":"Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Polytechnique Montréal","funders":"Centre International de Mathématiques et Informatique de Toulouse; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Interpretability; Computer science; Artificial intelligence; Black box; Machine learning; Taxonomy (biology); Inference; Generalization; Mathematics","score_opus":0.1914077921336387,"score_gpt":0.24906164618582544,"score_spread":0.05765385405218673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323571926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02269955,0.00014028886,0.969499,0.00008756615,0.0006523246,0.00038560675,0.000004510305,0.00073014904,0.0058009857],"genre_scores_gemma":[0.9541117,0.00042506048,0.037502933,0.00007125487,0.000052587944,0.0000076376855,0.0000061917967,0.000039544277,0.0077830977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966313,0.0008478532,0.00028714753,0.0015733778,0.00009183988,0.00056847406],"domain_scores_gemma":[0.9973681,0.000731395,0.0002684475,0.0012353366,0.00017593875,0.00022080886],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017617602,0.00038884534,0.00045261005,0.00043696017,0.00031842457,0.0003909197,0.0021323278,0.00020945388,0.000031168383],"category_scores_gemma":[0.0001835246,0.00046191458,0.00018784971,0.0005921389,0.0002034487,0.0010042222,0.005583327,0.0010346698,0.00021955755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018721394,0.000023084938,0.0001829342,0.000049449205,0.00007681986,0.00022407967,0.0005120517,0.5225438,0.000033606535,0.46697396,0.00011402753,0.009247499],"study_design_scores_gemma":[0.00004707382,0.000037738875,0.000010187851,0.000064829816,0.00002821298,0.0000049760706,0.00036300355,0.6005462,0.00074433204,0.3971388,0.000720358,0.00029429913],"about_ca_topic_score_codex":0.00039438615,"about_ca_topic_score_gemma":0.000029751604,"teacher_disagreement_score":0.9319961,"about_ca_system_score_codex":0.0002026381,"about_ca_system_score_gemma":0.00017065431,"threshold_uncertainty_score":0.9997833},"labels":[],"label_agreement":null},{"id":"W4327657264","doi":"10.1007/978-3-031-26387-3_23","title":"Neural Networks with Feature Attribution and Contrastive Explanations","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Feature (linguistics); Attribution; Pattern recognition (psychology); Natural language processing; Linguistics; Psychology","score_opus":0.02327235018734245,"score_gpt":0.24880301227091442,"score_spread":0.22553066208357198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327657264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010355655,0.0002757043,0.9951253,0.0023211872,0.0009895358,0.00043984363,0.00000840305,0.00026099195,0.00047549402],"genre_scores_gemma":[0.8083383,0.00020235126,0.18557175,0.0026886847,0.0011501486,0.00006227673,0.000050155977,0.00011190855,0.0018244454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695206,0.000037300604,0.00030110072,0.0013232231,0.0006961905,0.0006901107],"domain_scores_gemma":[0.99781203,0.0006826538,0.00020825461,0.00073468126,0.00037671308,0.00018564679],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057407,0.00044285486,0.00040080564,0.0005857195,0.00044356397,0.00069781387,0.001453764,0.00030110884,0.000004628008],"category_scores_gemma":[0.00008016922,0.00037396635,0.00005548631,0.0010040057,0.00078118587,0.00082371687,0.0007035322,0.0009030298,0.00001967077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017557075,0.000018233297,0.0001839393,0.000019519868,0.000021565189,0.0003098961,0.0008703503,0.46847674,0.000036648882,0.12969664,0.000064608466,0.4002843],"study_design_scores_gemma":[0.00011391992,0.0002164512,0.0004164951,0.00019675144,0.000008871008,0.00009474391,9.4285457e-7,0.9611377,0.00033114542,0.03675369,0.0002662727,0.00046302498],"about_ca_topic_score_codex":0.00003341132,"about_ca_topic_score_gemma":0.00048257996,"teacher_disagreement_score":0.80955356,"about_ca_system_score_codex":0.00020502153,"about_ca_system_score_gemma":0.0002227523,"threshold_uncertainty_score":0.99987125},"labels":[],"label_agreement":null},{"id":"W4360604687","doi":"10.1109/mcg.2023.3237286","title":"The Flow of Trust: A Visualization Framework to Externalize, Explore, and Explain Trust in ML Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Computer Graphics and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Bundesministerium für Bildung und Forschung; Academy of Finland","keywords":"Computer science; Rotation formalisms in three dimensions; Visualization; Workflow; Process (computing); Representation (politics); Pipeline (software); Human–computer interaction; Computational trust; Conceptual framework; Artificial intelligence; Programming language","score_opus":0.03326889931411739,"score_gpt":0.310875164864545,"score_spread":0.27760626555042756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360604687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027554717,0.00020450672,0.97008294,0.0009547108,0.000092877715,0.0009162552,0.0000086807,0.00013083358,0.00005450381],"genre_scores_gemma":[0.92186147,0.0030585006,0.06855729,0.0010420646,0.00039134818,0.004924043,0.000019804324,0.00004770683,0.00009774227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984723,0.00006161165,0.0004376869,0.0005026105,0.00022860897,0.0002972351],"domain_scores_gemma":[0.99840045,0.00049757055,0.00011516024,0.00070933776,0.00014003311,0.00013743734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004932547,0.00015797466,0.00017848462,0.00036429983,0.0004423622,0.00025299817,0.0007141317,0.000086142856,0.0000012102889],"category_scores_gemma":[0.000017642704,0.00014141832,0.000045192992,0.002563373,0.00015312924,0.00021623868,0.00025462848,0.00014929238,0.000023441058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031820368,0.00005365303,0.0010594596,0.000021460712,0.000008704964,0.0000010127707,0.0015998706,0.001055236,0.00015078984,0.9165663,0.0002659176,0.079214394],"study_design_scores_gemma":[0.0001188726,0.0000705305,0.004557333,0.00006100886,0.000007718303,0.0000061142664,0.00030292303,0.6458559,0.0012479131,0.31064373,0.036860086,0.00026784284],"about_ca_topic_score_codex":0.00004358822,"about_ca_topic_score_gemma":0.00006527836,"teacher_disagreement_score":0.9015256,"about_ca_system_score_codex":0.000015399626,"about_ca_system_score_gemma":0.000030776973,"threshold_uncertainty_score":0.57668716},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08080955537100197,"score_gpt":0.3440335552965247,"score_spread":0.2632239999255227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360991197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21306777,0.000035768786,0.78027517,0.0026291432,0.00043860803,0.0003338934,0.0000028137347,0.00040133976,0.002815505],"genre_scores_gemma":[0.991713,0.00004959046,0.0070833866,0.0008099368,0.000041289182,0.000022341384,0.0000031573143,0.000025769194,0.0002515537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969249,0.0001390151,0.00049072126,0.0010015231,0.0006381994,0.00080566254],"domain_scores_gemma":[0.9966094,0.0022590111,0.00008243786,0.0007558106,0.00012044613,0.0001729311],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001366526,0.0003187729,0.00036665192,0.00090344186,0.00045848315,0.0009538336,0.0010927927,0.00016800204,0.00008702184],"category_scores_gemma":[0.0008073782,0.00028606402,0.00010195369,0.0021044377,0.00017523674,0.0012434499,0.0009720835,0.00037822183,0.00010535547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018918572,0.000109347195,0.006817153,0.00004875041,0.000055380686,0.00083441706,0.019391503,0.10785406,0.0027100944,0.69695204,0.017701153,0.14733689],"study_design_scores_gemma":[0.00026346944,0.00013783941,0.0010095116,0.00051494746,0.000004905074,0.000020136664,0.011782846,0.6195501,0.00024596698,0.36556563,0.0004732272,0.00043139842],"about_ca_topic_score_codex":0.00038116632,"about_ca_topic_score_gemma":0.004557799,"teacher_disagreement_score":0.7786452,"about_ca_system_score_codex":0.0007297346,"about_ca_system_score_gemma":0.00009984837,"threshold_uncertainty_score":0.9999592},"labels":[],"label_agreement":null},{"id":"W4361768408","doi":"10.7202/1097750ar","title":"BERT, GPT-3, Timnit Gebru et nous","year":2023,"lang":"fr","type":"article","venue":"Sociologie et sociétés","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.5725789724907827,"score_gpt":0.5342138553928406,"score_spread":0.0383651170979421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361768408","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054357596,0.010329402,0.08655502,0.6921665,0.03970151,0.0018087775,0.0001896962,0.0052037435,0.10968774],"genre_scores_gemma":[0.8001288,0.016579527,0.011414442,0.022516767,0.0015088147,0.00032501126,0.00017444068,0.00021771615,0.14713445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936233,0.0015168396,0.0008116469,0.0013232676,0.0006817037,0.0020432011],"domain_scores_gemma":[0.9944798,0.0031360716,0.00031809704,0.0013329206,0.00040213543,0.0003309754],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00418235,0.0006097532,0.00071065064,0.00020829936,0.00075688545,0.00055189274,0.002269892,0.00097633165,0.0023074425],"category_scores_gemma":[0.0020640304,0.0005798013,0.0005477155,0.0015220507,0.0010915535,0.001448515,0.0017149802,0.001574418,0.025774281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020308853,0.0003448584,0.0009981067,0.00013346477,0.00023367739,0.0008013919,0.029123604,0.003111217,0.0009896772,0.6013344,0.25151715,0.11139215],"study_design_scores_gemma":[0.000433966,0.00060097274,0.0027212999,0.00017066214,0.000070149355,0.000043198917,0.0130768465,0.028173987,0.0033381917,0.82187176,0.1280892,0.0014097568],"about_ca_topic_score_codex":0.0007993867,"about_ca_topic_score_gemma":0.00008589981,"teacher_disagreement_score":0.7457712,"about_ca_system_score_codex":0.00044189682,"about_ca_system_score_gemma":0.00096536125,"threshold_uncertainty_score":0.9996653},"labels":[],"label_agreement":null},{"id":"W4362588244","doi":"10.3390/diagnostics13071315","title":"Error Consistency for Machine Learning Evaluation and Validation with Application to Biomedical Diagnostics","year":2023,"lang":"en","type":"article","venue":"Diagnostics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Nova Scotia Health Authority; St. Francis Xavier University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Research Foundation; St. Francis Xavier University","keywords":"Machine learning; Generalizability theory; Artificial intelligence; Computer science; Consistency (knowledge bases); Reliability (semiconductor); Software; Implementation; Variety (cybernetics); Software deployment; Sample (material); Data mining; Software engineering; Mathematics","score_opus":0.043832712958157376,"score_gpt":0.33322729223674336,"score_spread":0.289394579278586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362588244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083090425,0.00013309083,0.9112706,0.0035943305,0.00020986822,0.0013149048,0.000018794708,0.0002767037,0.000091250215],"genre_scores_gemma":[0.9688962,0.00034988442,0.028962675,0.00036616068,0.00012191745,0.0008791103,0.0003412784,0.000025953539,0.000056804925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984952,0.00008314568,0.00025870558,0.00041588244,0.00045110108,0.00029595112],"domain_scores_gemma":[0.99625397,0.002780176,0.00009701095,0.00030327227,0.0004073835,0.00015821625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009938052,0.00013270463,0.0001400431,0.00021075051,0.0002711263,0.00013843678,0.00026599885,0.00007564967,0.000005137443],"category_scores_gemma":[0.006914291,0.00012417698,0.000019502011,0.0008972072,0.0000670266,0.00020589153,0.00012993549,0.000108966815,0.00013557801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008162395,0.00050652813,0.050125152,0.00024586212,0.00009179006,0.000050737577,0.0090534985,0.052691076,0.0029114643,0.17789805,0.01445104,0.69189316],"study_design_scores_gemma":[0.00029349257,0.0005820374,0.0048412224,0.000053677195,0.000051960622,0.000006977898,0.00032253232,0.9614357,0.0052385773,0.008157091,0.018747047,0.00026972778],"about_ca_topic_score_codex":0.000050843093,"about_ca_topic_score_gemma":0.00004656275,"teacher_disagreement_score":0.9087446,"about_ca_system_score_codex":0.0000568684,"about_ca_system_score_gemma":0.00009904345,"threshold_uncertainty_score":0.82775515},"labels":[],"label_agreement":null},{"id":"W4362693528","doi":"10.1117/12.2654307","title":"Multi-scale local explanation approach for image analysis using model-agnostic Explainable Artificial Intelligence (XAI)","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Artificial intelligence; Computer science; Scale (ratio); Convolutional neural network; Weighting; Machine learning; Artificial neural network; Deep learning; Scheme (mathematics); Pattern recognition (psychology); Mathematics; Geography","score_opus":0.11670761443965559,"score_gpt":0.33941907855751097,"score_spread":0.22271146411785536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362693528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072627417,0.000023748884,0.99000514,0.0002393123,0.00021209999,0.0008268494,0.00001948828,0.0007972349,0.0006134159],"genre_scores_gemma":[0.48882547,0.000009965773,0.51031166,0.000100425044,0.00005963301,0.00017110952,0.000061058854,0.000027309974,0.00043333523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593955,0.00012095467,0.00089421973,0.001282298,0.0006373072,0.0011256869],"domain_scores_gemma":[0.9974724,0.00045886857,0.0002124067,0.0010610454,0.00053516676,0.00026010777],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014133374,0.00039299496,0.0005149978,0.0012268033,0.0006785172,0.0005533577,0.0014786181,0.00019370455,0.000036407197],"category_scores_gemma":[0.00031754244,0.0003971444,0.0003683968,0.005531595,0.00019078475,0.0018323177,0.00046099402,0.00021016883,0.00018731138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019399185,0.0002070284,0.000034874614,0.000047137768,0.000089631,0.000016208902,0.0015996443,0.95257646,0.006992319,0.026516393,0.00018061504,0.011720263],"study_design_scores_gemma":[0.000054041928,0.000057895293,0.000014569821,0.000010181926,0.00011851575,0.000004953905,0.0039270055,0.9096865,0.07200944,0.013647151,0.000016805503,0.00045293523],"about_ca_topic_score_codex":0.00041419093,"about_ca_topic_score_gemma":0.00030332166,"teacher_disagreement_score":0.48156273,"about_ca_system_score_codex":0.00026984315,"about_ca_system_score_gemma":0.00017653509,"threshold_uncertainty_score":0.99984807},"labels":[],"label_agreement":null},{"id":"W4363678929","doi":"10.1109/mc.2022.3233806","title":"A Trustworthy View on Explainable Artificial Intelligence Method Evaluation","year":2023,"lang":"en","type":"article","venue":"Computer","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Trustworthiness; Consistency (knowledge bases); Computer science; Process (computing); Artificial intelligence; Computer security","score_opus":0.12782758466331454,"score_gpt":0.3804678654842235,"score_spread":0.25264028082090895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4363678929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037462972,0.00007461691,0.98804003,0.0020422973,0.0016814993,0.00064164255,0.0000015000802,0.0008428849,0.0029292242],"genre_scores_gemma":[0.5411443,0.000117377946,0.4501028,0.0044920878,0.0019954669,0.00063888746,0.000046435245,0.00010666228,0.0013559586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99617267,0.00052483537,0.00059766526,0.0009939958,0.0009351396,0.000775679],"domain_scores_gemma":[0.9974417,0.000634579,0.00014982469,0.0012129904,0.00037615115,0.00018475983],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033088413,0.00030522817,0.0003250194,0.0005063887,0.00037740357,0.00046394634,0.001502551,0.00012369984,0.00021994504],"category_scores_gemma":[0.00014357724,0.00029576995,0.00015895987,0.0025503216,0.000058293794,0.00073914643,0.000559486,0.00028046194,0.008777548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009580733,0.00007246117,0.0000068246372,0.00001749985,0.00001445315,0.00004784274,0.0009912009,0.045112513,0.00013894349,0.21326695,0.0035958288,0.7367259],"study_design_scores_gemma":[0.000037377296,0.00021401588,0.00008407177,0.0000645122,0.000009364485,0.00001129719,0.00010669101,0.84530723,0.015112326,0.12747289,0.011274594,0.00030562712],"about_ca_topic_score_codex":0.00003946341,"about_ca_topic_score_gemma":0.000019703808,"teacher_disagreement_score":0.80019474,"about_ca_system_score_codex":0.00016909931,"about_ca_system_score_gemma":0.00015826408,"threshold_uncertainty_score":0.99994946},"labels":[],"label_agreement":null},{"id":"W4365452225","doi":"10.1016/j.patcog.2023.109610","title":"Learning Customised Decision Trees for Domain-knowledge Constraints","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Fonds De La Recherche Scientifique - FNRS","keywords":"Computer science; Machine learning; Decision tree; Binary decision diagram; Domain (mathematical analysis); Incremental decision tree; Artificial intelligence; Tree (set theory); Representation (politics); Domain knowledge; Discretization; Decision tree learning; Theoretical computer science; Mathematics","score_opus":0.0616607895682781,"score_gpt":0.31548476046536644,"score_spread":0.25382397089708836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365452225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2654022,0.000013148892,0.73134613,0.0003022173,0.0005357581,0.00039216076,0.000010408256,0.00047921186,0.0015187779],"genre_scores_gemma":[0.9888033,0.000025433015,0.0103416275,0.00013016432,0.00016744745,0.00021040777,0.000071556824,0.000022893752,0.00022711747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984911,0.00010194578,0.00031209047,0.00046725298,0.0001957935,0.0004317896],"domain_scores_gemma":[0.9985058,0.00081229943,0.00010607173,0.00024586034,0.00022762107,0.000102347585],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007323617,0.00015403128,0.00016222766,0.0002847251,0.0003032296,0.00019197326,0.00041314238,0.00008998954,0.0001021643],"category_scores_gemma":[0.00030995315,0.00015866166,0.00011009399,0.0005806359,0.00006512223,0.00043641333,0.00013149167,0.00013507594,0.004119652],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014063526,0.00003877658,0.00035028168,0.000019876954,0.000009311652,0.000012873363,0.0013885589,0.00007393962,0.0037981996,0.00032021402,0.00096804247,0.9930059],"study_design_scores_gemma":[0.0029016703,0.0011522598,0.008434589,0.0008400344,0.000046721474,0.00006884,0.00399666,0.55724484,0.1395592,0.25326502,0.03071782,0.0017723446],"about_ca_topic_score_codex":0.000009760718,"about_ca_topic_score_gemma":0.000071746465,"teacher_disagreement_score":0.9912335,"about_ca_system_score_codex":0.0000614251,"about_ca_system_score_gemma":0.00004589147,"threshold_uncertainty_score":0.99665576},"labels":[],"label_agreement":null},{"id":"W4366197471","doi":"10.48550/arxiv.2304.06879","title":"Performative Prediction with Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Lipschitz continuity; Resampling; Convexity; Computer science; Artificial neural network; Performative utterance; Minification; Focus (optics); Mathematics; Applied mathematics; Mathematical optimization; Artificial intelligence; Mathematical analysis","score_opus":0.10243080908172861,"score_gpt":0.19026809181263013,"score_spread":0.08783728273090152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366197471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1511078,0.000015771991,0.8455569,0.00015365791,0.00089620845,0.00032679026,0.000007668326,0.0007633517,0.0011718371],"genre_scores_gemma":[0.9976272,0.00008363633,0.000703818,0.00007357523,0.00013464926,0.0000031625582,0.000019261333,0.000025453835,0.0013292173],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797636,0.00018126908,0.00021775172,0.0010062642,0.00012575726,0.0004926053],"domain_scores_gemma":[0.99806666,0.00015209844,0.00023745987,0.0011251547,0.00024863041,0.00017001817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034703984,0.0003171634,0.00026811167,0.00027991203,0.00035604264,0.0002445044,0.001681596,0.00025149246,0.000016680744],"category_scores_gemma":[0.000030282246,0.00032510862,0.00012467177,0.0010593082,0.000115785755,0.0010949203,0.0016402602,0.0010169394,0.00018758226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031367475,0.00003071485,0.0022131593,0.000025339988,0.000054580374,0.00028228693,0.0006693762,0.9550089,0.0000028729753,0.040595237,0.00034782747,0.00073829025],"study_design_scores_gemma":[0.00010770469,0.000137058,0.0012707209,0.00007304276,0.00003409794,0.000007020641,0.0004277814,0.9869009,0.00014029516,0.010505588,0.000075272575,0.00032047418],"about_ca_topic_score_codex":0.00028169024,"about_ca_topic_score_gemma":0.00013861842,"teacher_disagreement_score":0.8465194,"about_ca_system_score_codex":0.00024465614,"about_ca_system_score_gemma":0.00012297963,"threshold_uncertainty_score":0.99992007},"labels":[],"label_agreement":null},{"id":"W4366595903","doi":"10.1145/3544549.3585727","title":"Something Borrowed: Exploring the Influence of AI-Generated Explanation Text on the Composition of Human Explanations","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Argumentative; Context (archaeology); Composition (language); Computer science; Epistemology; Argumentation theory; Empirical research; Cognitive science; Artificial intelligence; Natural language processing; Psychology; Linguistics; Philosophy","score_opus":0.10155839161521603,"score_gpt":0.3177451099028608,"score_spread":0.2161867182876448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366595903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556217,0.0000062162126,0.03756974,0.005034719,0.00014421584,0.00025430557,0.000003224969,0.0001652649,0.0012005912],"genre_scores_gemma":[0.99884564,0.000013580373,0.0004678118,0.00044814227,0.000028680712,0.00008654234,0.000009558847,0.000008400234,0.000091618895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983822,0.00020479124,0.00044705873,0.00024286973,0.0004985037,0.0002245464],"domain_scores_gemma":[0.9980578,0.00076315907,0.00018499568,0.0006209782,0.00034020524,0.0000328967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075771,0.00011762453,0.00013389568,0.00031088036,0.0005011768,0.000101463935,0.0009898029,0.000035901292,0.000020154352],"category_scores_gemma":[0.00017638646,0.000075181524,0.000056448334,0.0018654545,0.00010275744,0.00092563586,0.00016596368,0.0001922432,0.000074947166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031809486,0.000037526403,0.00013053238,0.000009046064,0.000013172283,0.0000017990429,0.0051100487,0.07277828,0.24433038,0.6758733,0.0004873507,0.0012254051],"study_design_scores_gemma":[0.00005622945,0.00010544824,0.0048158267,0.00007001327,0.000005925447,0.0000014037095,0.002418723,0.06553871,0.9124457,0.014328362,0.00008889187,0.00012471886],"about_ca_topic_score_codex":0.0003634821,"about_ca_topic_score_gemma":0.000094732146,"teacher_disagreement_score":0.6681154,"about_ca_system_score_codex":0.000041724998,"about_ca_system_score_gemma":0.000044240078,"threshold_uncertainty_score":0.38546976},"labels":[],"label_agreement":null},{"id":"W4366703926","doi":"10.2478/vjls-2022-0006","title":"Explainability of Artificial Intelligence Models: Technical Foundations and Legal Principles","year":2022,"lang":"en","type":"article","venue":"Vietnamese Journal of Legal Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Artificial intelligence; Key (lock); Computer science; Liability; Management science; Engineering ethics; Political science; Engineering; Law; Computer security","score_opus":0.08956895597000328,"score_gpt":0.3262964498248786,"score_spread":0.23672749385487532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366703926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34245384,0.00067682774,0.64516515,0.0075568063,0.0007566665,0.000297192,0.0000066169296,0.000051484767,0.0030354448],"genre_scores_gemma":[0.95195764,0.00004607377,0.047766037,0.0000914926,0.00006882648,0.000013673736,2.2496982e-7,0.000005749214,0.00005027911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962341,0.00034371513,0.0012089093,0.00043654445,0.001358055,0.00041866256],"domain_scores_gemma":[0.99787295,0.0003569951,0.0007603632,0.00039535397,0.00042617862,0.00018817067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050933897,0.00017677165,0.000373033,0.0004677499,0.0010501551,0.00039340282,0.002306937,0.000044494678,0.00006655541],"category_scores_gemma":[0.00067515933,0.00014887753,0.0001702821,0.0018841522,0.0010248384,0.0034153983,0.0010225838,0.0005040975,0.000002498233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033641907,0.00028616196,0.00021257548,0.000013787677,0.000010358777,0.00005237248,0.0013310323,0.052705202,0.0030769366,0.9164806,0.000046660778,0.025750656],"study_design_scores_gemma":[0.00009983992,0.002717997,0.00040525806,0.00006975541,0.000031717474,0.0013763617,0.013086216,0.5376022,0.015053461,0.41967663,0.009346214,0.0005343875],"about_ca_topic_score_codex":0.00016705248,"about_ca_topic_score_gemma":0.00012171471,"teacher_disagreement_score":0.6095038,"about_ca_system_score_codex":0.0001860373,"about_ca_system_score_gemma":0.00095090066,"threshold_uncertainty_score":0.8077051},"labels":[],"label_agreement":null},{"id":"W4367313097","doi":"10.2196/preprints.47995","title":"Reporting and Methodological Observations on Prognostic and Diagnostic Machine Learning Studies (Preprint)","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Preprint; Key (lock); Data science; Computer science; Artificial intelligence; Machine learning; Psychology; World Wide Web; Computer security","score_opus":0.5131537115510197,"score_gpt":0.43838889267874787,"score_spread":0.07476481887227188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367313097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5172436,0.0017101978,0.4698137,0.007435331,0.000765249,0.0011793856,0.0000024449178,0.0014188774,0.00043118952],"genre_scores_gemma":[0.80735976,0.0022418536,0.18848921,0.00032913242,0.000094657116,0.00036808275,0.0000093016,0.00003116889,0.0010768579],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960081,0.0005843268,0.0013025054,0.0013703181,0.00033699544,0.00039773565],"domain_scores_gemma":[0.979504,0.018178971,0.0011481476,0.00074067555,0.00028539036,0.000142828],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00522564,0.00033709712,0.00068213,0.00019227373,0.00041781663,0.00040847997,0.0005260014,0.00019624912,0.0000061914347],"category_scores_gemma":[0.15049899,0.00027538763,0.000080641585,0.00032858975,0.00016949528,0.00020323374,0.0051073865,0.0010367547,0.00003611953],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020559513,0.00021919156,0.54300183,0.0011016495,0.00048096062,0.0012115396,0.011674538,0.08540286,0.0005003108,0.2584422,0.00046335862,0.09748103],"study_design_scores_gemma":[0.0001015327,0.0004704003,0.23026331,0.0010810049,0.0000835219,0.00006800025,0.0017792549,0.3966103,0.0022045637,0.36608863,0.00032971692,0.00091976934],"about_ca_topic_score_codex":0.00040141592,"about_ca_topic_score_gemma":0.00018370758,"teacher_disagreement_score":0.3127385,"about_ca_system_score_codex":0.0000622147,"about_ca_system_score_gemma":0.00007510298,"threshold_uncertainty_score":0.99996984},"labels":[],"label_agreement":null},{"id":"W4367313592","doi":"10.1145/3594728","title":"Positioning Paradata: A Conceptual Frame for AI Processual Documentation in Archives and Recordkeeping Contexts","year":2023,"lang":"en","type":"article","venue":"Journal on Computing and Cultural Heritage","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; University of British Columbia","keywords":"Documentation; Computer science; Transparency (behavior); Process (computing); Accountability; Metadata; Agency (philosophy); Workflow; Scope (computer science); Scholarship; Data science; Sociology; World Wide Web; Political science; Database","score_opus":0.03338625850983379,"score_gpt":0.340418111546091,"score_spread":0.3070318530362572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367313592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92812514,0.00025188693,0.068871476,0.002082388,0.00026947324,0.00019555332,0.0000020051557,0.00008802573,0.00011406014],"genre_scores_gemma":[0.9909835,0.00008508307,0.008023314,0.00062608276,0.00016032445,0.000005955958,0.000004967305,0.000006503554,0.00010425628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890786,0.000082821214,0.00030665213,0.0002659835,0.00014015997,0.0002965299],"domain_scores_gemma":[0.9993146,0.00033680513,0.00013102009,0.00006702932,0.000058427402,0.0000921195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036339788,0.000118916745,0.00016584169,0.000107415224,0.0005002616,0.00073713734,0.00017992484,0.000038337363,0.0000015330802],"category_scores_gemma":[0.000098167104,0.00010112067,0.00003386663,0.00025028145,0.000074799405,0.0009865215,0.000088586865,0.0002673374,0.0000044821663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028714497,0.0001573199,0.005207957,0.00021819399,0.00008001738,0.00032575955,0.11577182,0.0064336914,0.016761167,0.19683988,0.0013764618,0.6565406],"study_design_scores_gemma":[0.002074377,0.0018866506,0.0145842135,0.0017944792,0.000017597808,0.00062198006,0.03591949,0.8649911,0.005754203,0.06866118,0.0027989363,0.00089574],"about_ca_topic_score_codex":0.000014942835,"about_ca_topic_score_gemma":0.00001551955,"teacher_disagreement_score":0.85855746,"about_ca_system_score_codex":0.00002699507,"about_ca_system_score_gemma":0.000028256993,"threshold_uncertainty_score":0.71082324},"labels":[],"label_agreement":null},{"id":"W4367319158","doi":"10.2196/47995","title":"Reporting and Methodological Observations on Prognostic and Diagnostic Machine Learning Studies","year":2023,"lang":"en","type":"article","venue":"JMIR AI","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Key (lock); Data science; Artificial intelligence; Computer science; Psychology; Machine learning","score_opus":0.3717432222961256,"score_gpt":0.4492624438026238,"score_spread":0.0775192215064982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367319158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9658263,0.0005823577,0.023484295,0.008806119,0.00017195787,0.0004112477,7.452184e-7,0.0005607274,0.00015625988],"genre_scores_gemma":[0.98787045,0.00024222407,0.010779967,0.00053526054,0.0000469613,0.00015344535,0.0000024571268,0.000008601677,0.0003606052],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99853015,0.00020962299,0.00044379482,0.00039204757,0.00016941459,0.0002549469],"domain_scores_gemma":[0.9936104,0.005778138,0.00025086268,0.00019672394,0.000094861185,0.00006902623],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016623009,0.00011182256,0.00021865759,0.00010227044,0.0003521902,0.00013333396,0.00015606028,0.000043506006,0.0000022983645],"category_scores_gemma":[0.03520812,0.00009009634,0.000024869369,0.0005713678,0.00008563543,0.00026595333,0.00036794384,0.00023024085,0.000032901364],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016724398,0.00014172247,0.6811616,0.00022079756,0.00009724705,0.0010118204,0.013511748,0.0051364223,0.0027348266,0.14817189,0.002231472,0.14556377],"study_design_scores_gemma":[0.00014677297,0.00080652133,0.67774457,0.00024239426,0.000022668204,0.000069782,0.0015150013,0.24268875,0.0022954468,0.070379786,0.0036419886,0.000446319],"about_ca_topic_score_codex":0.000023561293,"about_ca_topic_score_gemma":0.000019985966,"teacher_disagreement_score":0.23755233,"about_ca_system_score_codex":0.00001658872,"about_ca_system_score_gemma":0.000017965674,"threshold_uncertainty_score":0.97291875},"labels":[],"label_agreement":null},{"id":"W4367722415","doi":"10.2139/ssrn.4426783","title":"Recommender Algorithms Do No Harm ~90% But… An Exploratory Risk-Utility Meta-Analysis of Algorithmic Audits","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Audit; Computer science; Recommender system; Harm; Algorithm; Exploratory analysis; Data mining; Risk analysis (engineering); Information retrieval; Data science; Business; Accounting; Psychology","score_opus":0.08570767342731032,"score_gpt":0.3236915457612536,"score_spread":0.23798387233394325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367722415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056798693,0.0037342308,0.935563,0.0015801633,0.0009569834,0.00040206633,0.0000645721,0.0004362405,0.00046402926],"genre_scores_gemma":[0.98523456,0.005044342,0.007625715,0.00023955283,0.00037271396,0.00006602664,0.00002326601,0.00006089192,0.0013329256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99288386,0.0010948725,0.0011012984,0.00088805537,0.0010020568,0.0030298524],"domain_scores_gemma":[0.9963409,0.00034302863,0.00084009906,0.0013670437,0.00079052534,0.000318443],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010767657,0.00040769004,0.0011192722,0.0011467581,0.00057036284,0.00029101584,0.002336462,0.00016397997,0.000307719],"category_scores_gemma":[0.0003139603,0.0003547133,0.001292308,0.0043234457,0.00012288004,0.0018103276,0.0003595971,0.0021724303,0.00043057514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021361408,0.0021260162,0.002368965,0.000057980837,0.30362105,0.00024986526,0.0141252605,0.01872474,0.0028023531,0.1801337,0.0051820655,0.47039437],"study_design_scores_gemma":[0.0004934487,0.0012756736,0.0008309101,0.00000791867,0.033422474,0.00011404642,0.010401749,0.5701192,0.0070351507,0.37152514,0.0035320346,0.0012422472],"about_ca_topic_score_codex":0.0003810516,"about_ca_topic_score_gemma":0.0011950186,"teacher_disagreement_score":0.92843586,"about_ca_system_score_codex":0.00062917895,"about_ca_system_score_gemma":0.0016714262,"threshold_uncertainty_score":0.9998905},"labels":[],"label_agreement":null},{"id":"W4367841500","doi":"10.32920/22734320","title":"Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Cluster analysis; Classifier (UML); Popularity; Random forest; Stability (learning theory); Cluster (spacecraft); Pattern recognition (psychology)","score_opus":0.10118889623329573,"score_gpt":0.3379902339634696,"score_spread":0.23680133773017387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367841500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010072454,0.000051178915,0.99029243,0.0015529785,0.0017432573,0.0017952144,0.00013880616,0.0012940663,0.0021248246],"genre_scores_gemma":[0.83492595,0.00003154616,0.15535918,0.0003322319,0.000106174935,0.0023380534,0.000095702366,0.000076093274,0.0067350566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995503,0.00012610771,0.001004782,0.0017657886,0.00053829816,0.001062017],"domain_scores_gemma":[0.99441105,0.0018649433,0.00027725677,0.0024588562,0.0006946118,0.00029327525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011995297,0.0005552517,0.0006633389,0.00041088677,0.0004330981,0.000747649,0.0031653629,0.00041098057,0.00005605681],"category_scores_gemma":[0.0016023637,0.00057417154,0.0003316593,0.0004787213,0.00019066308,0.00075885287,0.003308214,0.0005916891,0.000337553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002158213,0.00016700393,0.000028981905,0.00042081662,0.000050953404,0.000026255726,0.001486139,0.8430837,0.000040767693,0.13942239,0.008059145,0.0071922657],"study_design_scores_gemma":[0.000065304055,0.00007615197,0.000009316189,0.000099992976,0.000026562573,0.0000032155924,0.00024279775,0.7185171,0.0018958566,0.2778498,0.0007611438,0.00045273796],"about_ca_topic_score_codex":0.00071070704,"about_ca_topic_score_gemma":0.0011289844,"teacher_disagreement_score":0.8349332,"about_ca_system_score_codex":0.00058980816,"about_ca_system_score_gemma":0.001023501,"threshold_uncertainty_score":0.999671},"labels":[],"label_agreement":null},{"id":"W4367841501","doi":"10.32920/22734320.v1","title":"Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Artificial intelligence; Computer science; Machine learning; Cluster analysis; Classifier (UML); Random forest; Stability (learning theory); Cluster (spacecraft); Popularity; Pattern recognition (psychology); Algorithm","score_opus":0.10118889623329573,"score_gpt":0.3379902339634696,"score_spread":0.23680133773017387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367841501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010072454,0.000051178915,0.99029243,0.0015529785,0.0017432573,0.0017952144,0.00013880616,0.0012940663,0.0021248246],"genre_scores_gemma":[0.83492595,0.00003154616,0.15535918,0.0003322319,0.000106174935,0.0023380534,0.000095702366,0.000076093274,0.0067350566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995503,0.00012610771,0.001004782,0.0017657886,0.00053829816,0.001062017],"domain_scores_gemma":[0.99441105,0.0018649433,0.00027725677,0.0024588562,0.0006946118,0.00029327525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011995297,0.0005552517,0.0006633389,0.00041088677,0.0004330981,0.000747649,0.0031653629,0.00041098057,0.00005605681],"category_scores_gemma":[0.0016023637,0.00057417154,0.0003316593,0.0004787213,0.00019066308,0.00075885287,0.003308214,0.0005916891,0.000337553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002158213,0.00016700393,0.000028981905,0.00042081662,0.000050953404,0.000026255726,0.001486139,0.8430837,0.000040767693,0.13942239,0.008059145,0.0071922657],"study_design_scores_gemma":[0.000065304055,0.00007615197,0.000009316189,0.000099992976,0.000026562573,0.0000032155924,0.00024279775,0.7185171,0.0018958566,0.2778498,0.0007611438,0.00045273796],"about_ca_topic_score_codex":0.00071070704,"about_ca_topic_score_gemma":0.0011289844,"teacher_disagreement_score":0.8349332,"about_ca_system_score_codex":0.00058980816,"about_ca_system_score_gemma":0.001023501,"threshold_uncertainty_score":0.999671},"labels":[],"label_agreement":null},{"id":"W4367849094","doi":"10.32920/22734389","title":"Locality Guided Neural Networks for Explainable Artificial Intelligence","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Locality; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Convolutional neural network; Layer (electronics); Topology (electrical circuits); Network topology; Pattern recognition (psychology); Mathematics; Computer network","score_opus":0.18465462804221094,"score_gpt":0.3587719475139085,"score_spread":0.17411731947169756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367849094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061889936,0.00013913377,0.9831587,0.004848748,0.0062633795,0.0019859977,0.00001913456,0.0019500887,0.0010158994],"genre_scores_gemma":[0.81173384,0.00014272732,0.17524636,0.0020549672,0.0023859735,0.0022451982,0.00017121369,0.00022576358,0.005793938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99351645,0.0002411859,0.0016545675,0.002275383,0.0006830158,0.0016294094],"domain_scores_gemma":[0.9943813,0.0009998233,0.000484267,0.002922412,0.00084229955,0.00036990165],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024931375,0.0007537087,0.0008314426,0.00038315088,0.00055066537,0.0014478721,0.0049302224,0.00071894063,0.000077257515],"category_scores_gemma":[0.00085283635,0.0007625112,0.000562637,0.0010637139,0.0002251707,0.00068745046,0.004941465,0.0010421913,0.0003835555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002462905,0.00009991977,0.000021485235,0.00016413283,0.000044789944,0.000049970808,0.000349902,0.5520633,0.000023960785,0.39119977,0.007973763,0.04798436],"study_design_scores_gemma":[0.000017088618,0.000073025745,0.000007372508,0.000057207115,0.000014335888,0.0000050028634,0.00023907899,0.65016115,0.0062194536,0.34193212,0.0007182136,0.00055595],"about_ca_topic_score_codex":0.0014227136,"about_ca_topic_score_gemma":0.00059660105,"teacher_disagreement_score":0.81111497,"about_ca_system_score_codex":0.00032744394,"about_ca_system_score_gemma":0.00034578764,"threshold_uncertainty_score":0.9995887},"labels":[],"label_agreement":null},{"id":"W4367849253","doi":"10.32920/22734389.v1","title":"Locality Guided Neural Networks for Explainable Artificial Intelligence","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Locality; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Convolutional neural network; Layer (electronics); Topology (electrical circuits); Network topology; Pattern recognition (psychology); Mathematics; Computer network","score_opus":0.18465462804221094,"score_gpt":0.3587719475139085,"score_spread":0.17411731947169756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367849253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061889936,0.00013913377,0.9831587,0.004848748,0.0062633795,0.0019859977,0.00001913456,0.0019500887,0.0010158994],"genre_scores_gemma":[0.81173384,0.00014272732,0.17524636,0.0020549672,0.0023859735,0.0022451982,0.00017121369,0.00022576358,0.005793938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99351645,0.0002411859,0.0016545675,0.002275383,0.0006830158,0.0016294094],"domain_scores_gemma":[0.9943813,0.0009998233,0.000484267,0.002922412,0.00084229955,0.00036990165],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024931375,0.0007537087,0.0008314426,0.00038315088,0.00055066537,0.0014478721,0.0049302224,0.00071894063,0.000077257515],"category_scores_gemma":[0.00085283635,0.0007625112,0.000562637,0.0010637139,0.0002251707,0.00068745046,0.004941465,0.0010421913,0.0003835555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002462905,0.00009991977,0.000021485235,0.00016413283,0.000044789944,0.000049970808,0.000349902,0.5520633,0.000023960785,0.39119977,0.007973763,0.04798436],"study_design_scores_gemma":[0.000017088618,0.000073025745,0.000007372508,0.000057207115,0.000014335888,0.0000050028634,0.00023907899,0.65016115,0.0062194536,0.34193212,0.0007182136,0.00055595],"about_ca_topic_score_codex":0.0014227136,"about_ca_topic_score_gemma":0.00059660105,"teacher_disagreement_score":0.81111497,"about_ca_system_score_codex":0.00032744394,"about_ca_system_score_gemma":0.00034578764,"threshold_uncertainty_score":0.9995887},"labels":[],"label_agreement":null},{"id":"W4376133361","doi":"10.1126/sciadv.abq0701","title":"Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data","year":2023,"lang":"en","type":"article","venue":"Science Advances","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Schwartz/Reisman Emergency Medicine Institute; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; Microsoft Research; University of Toronto; University of Southern California","keywords":"Normative; Computer science; Artificial intelligence; Object (grammar); Machine learning; Normative model of decision-making; Core (optical fiber); Psychology; Cognitive psychology; Epistemology","score_opus":0.25439494359505194,"score_gpt":0.357115698066272,"score_spread":0.10272075447122009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376133361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07012616,0.00028939996,0.92106414,0.0016093903,0.0006319886,0.00053914177,0.0000144091555,0.001179633,0.0045457347],"genre_scores_gemma":[0.86916775,0.00004611898,0.12939768,0.0007013685,0.000110086214,0.00007063526,0.000018055234,0.00003369341,0.00045459872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935908,0.00010394978,0.00064831146,0.0023199546,0.0014810242,0.0018560013],"domain_scores_gemma":[0.99674755,0.0002965694,0.0001902674,0.0019499804,0.00025582974,0.0005597852],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0047399867,0.00038426882,0.00042512626,0.0012749794,0.002184348,0.0012741237,0.0074078594,0.00005846654,0.000003930686],"category_scores_gemma":[0.0012871298,0.00036922246,0.00005928101,0.008020204,0.0003164703,0.010854902,0.003503838,0.00035981287,0.00023566857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006896636,0.00002851234,0.00009185137,0.000025449466,0.0000051909524,0.000015061724,0.020596303,0.821354,0.025272984,0.021259915,0.000043895176,0.11129997],"study_design_scores_gemma":[0.00007739698,0.00009094371,0.000033880086,0.000114982104,0.00000487958,0.0000072649223,0.0067354883,0.96974677,0.0109774675,0.009734775,0.0019323971,0.00054376834],"about_ca_topic_score_codex":0.00030752938,"about_ca_topic_score_gemma":0.000157706,"teacher_disagreement_score":0.7990416,"about_ca_system_score_codex":0.0001776569,"about_ca_system_score_gemma":0.00036370553,"threshold_uncertainty_score":0.99987596},"labels":[],"label_agreement":null},{"id":"W4377030819","doi":"10.1016/j.artint.2023.103945","title":"Human performance consequences of normative and contrastive explanations: An experiment in machine learning for reliability maintenance","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Mitacs","keywords":"Normative; Computer science; Artificial intelligence; Workload; Task (project management); Reliability (semiconductor); Machine learning; Automation; Advice (programming); Contrast (vision); Baseline (sea); Human–computer interaction; Psychology; Engineering","score_opus":0.07485535456500177,"score_gpt":0.3397358529433857,"score_spread":0.26488049837838396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377030819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7481307,0.00008633875,0.24987611,0.0006043201,0.0001686117,0.0007141696,0.000011714609,0.00016396427,0.0002440721],"genre_scores_gemma":[0.99398685,0.00009665569,0.005532967,0.000057557638,0.00002121837,0.00022418145,0.000012189609,0.000012113145,0.000056276327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757916,0.00019368286,0.0008374507,0.00060779543,0.00027980935,0.000502128],"domain_scores_gemma":[0.9983057,0.0005820574,0.0002573781,0.00038283714,0.00036351336,0.00010850979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016033412,0.00021231703,0.00032464837,0.0003276139,0.0003506011,0.00010565157,0.00065092125,0.00007938953,0.00001572653],"category_scores_gemma":[0.00070088153,0.00020816531,0.000052145715,0.0010113016,0.00054577034,0.0011881534,0.00017018407,0.00021635953,0.000029670924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016274407,0.00040924308,0.006768768,0.0001559073,0.00002656067,0.000022510589,0.035150923,0.07155619,0.07721231,0.72409594,0.000037617563,0.08440127],"study_design_scores_gemma":[0.000042292,0.00051074644,0.0010990277,0.00007331778,0.0000030249182,0.0000031797856,0.005259036,0.5349899,0.3945294,0.06321469,0.00006155797,0.00021383227],"about_ca_topic_score_codex":0.0006662033,"about_ca_topic_score_gemma":0.0005219117,"teacher_disagreement_score":0.6608813,"about_ca_system_score_codex":0.00009048202,"about_ca_system_score_gemma":0.000084533756,"threshold_uncertainty_score":0.8488735},"labels":[],"label_agreement":null},{"id":"W4378072741","doi":"10.48550/arxiv.2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Open Philanthropy Project","keywords":"Interpretability; Computer science; Transformer; Visualization; Generative grammar; Artificial intelligence; Vocabulary; Natural language processing","score_opus":0.07883463045535774,"score_gpt":0.21736684149058783,"score_spread":0.13853221103523009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378072741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18690403,0.000021893717,0.8112284,0.00026963418,0.00033800196,0.0002566123,0.0000055258297,0.0001473438,0.0008285365],"genre_scores_gemma":[0.998907,0.00018609849,0.0006984205,0.00008331203,0.000016337595,9.688231e-7,0.000005233032,0.000009488091,0.000093135175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998807,0.000107088745,0.00031078944,0.00039350576,0.00011072816,0.00027089549],"domain_scores_gemma":[0.9987553,0.00025305507,0.00025366506,0.00051886326,0.00015121448,0.00006792063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005958805,0.00019297823,0.00022640901,0.00029180388,0.00019154423,0.00017189868,0.0010918677,0.00014076284,0.0000059075796],"category_scores_gemma":[0.00009099732,0.0001818914,0.00012236173,0.0006444098,0.00014469308,0.0010653104,0.0010584919,0.00035961656,0.000054554424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007038737,0.000057296693,0.0021363907,0.0009348029,0.00024719248,0.00009876929,0.03535607,0.5534759,0.00030589927,0.3645356,0.00023447424,0.042547222],"study_design_scores_gemma":[0.000065055974,0.00003551595,0.0001951686,0.00022984161,0.00003099309,0.0000023327511,0.0023608678,0.9743525,0.0016981461,0.020654552,0.00017728555,0.00019775222],"about_ca_topic_score_codex":0.00044932344,"about_ca_topic_score_gemma":0.00009748897,"teacher_disagreement_score":0.81200296,"about_ca_system_score_codex":0.00007944796,"about_ca_system_score_gemma":0.00009130412,"threshold_uncertainty_score":0.74173164},"labels":[],"label_agreement":null},{"id":"W4378474033","doi":"10.48550/arxiv.2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Naval Information Warfare Center Pacific; Bar-Ilan University; Canadian Institute for Advanced Research","keywords":"Heuristics; Theory of mind; Adversarial system; Psychology; Benchmark (surveying); Cognitive psychology; Artificial intelligence; Cognitive science; Computer science; Cognition","score_opus":0.20581137279010794,"score_gpt":0.2491067126117638,"score_spread":0.04329533982165584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378474033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6449315,0.000020266469,0.35324594,0.000035892586,0.00027859389,0.00021711476,0.000045488185,0.0001600388,0.0010651583],"genre_scores_gemma":[0.99587125,0.000009777717,0.0023427748,0.000032364,0.000080173915,0.0000016603482,0.000010340422,0.000028878569,0.0016228025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763274,0.0003309858,0.00033695265,0.0009568754,0.00015128404,0.0005911699],"domain_scores_gemma":[0.9981143,0.0005402609,0.00032494185,0.0007500181,0.0001799645,0.00009055146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007854685,0.00028452178,0.0003981019,0.00042553595,0.00017454836,0.00009268773,0.001876223,0.00027401093,0.000026202453],"category_scores_gemma":[0.0002941322,0.00031589536,0.00015213591,0.0013591875,0.00011773026,0.000623966,0.002393392,0.0006488765,0.000035307075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009564178,0.00018384561,0.0066526853,0.00015380052,0.00005570435,0.002092854,0.013675044,0.6996599,0.0001944003,0.27443054,0.000035709727,0.0027698877],"study_design_scores_gemma":[0.00017858477,0.000034102904,0.0013516714,0.00022522509,0.0000229171,0.0000018765124,0.004646182,0.9437663,0.0012255546,0.04820426,0.0000029006444,0.00034044683],"about_ca_topic_score_codex":0.0009688034,"about_ca_topic_score_gemma":0.0014626805,"teacher_disagreement_score":0.35093972,"about_ca_system_score_codex":0.00018833888,"about_ca_system_score_gemma":0.00024930196,"threshold_uncertainty_score":0.9999293},"labels":[],"label_agreement":null},{"id":"W4379933269","doi":"10.48550/arxiv.2306.04025","title":"Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Introspection; Inference; Computer science; Artificial intelligence; Covert; Machine learning; Cognitive science; Psychology","score_opus":0.17602158513215585,"score_gpt":0.28160048348731026,"score_spread":0.10557889835515441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379933269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072853655,0.000032686865,0.9248998,0.00009649676,0.00064449303,0.00095106574,0.000016257487,0.000444027,0.00006149684],"genre_scores_gemma":[0.8352069,0.00014422918,0.16439703,0.000030561594,0.000112981776,0.000028234197,0.0000056050535,0.00004010172,0.00003433015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967223,0.00010308668,0.00042006915,0.0018304377,0.0002114234,0.00071271055],"domain_scores_gemma":[0.9957799,0.0022345914,0.00038908175,0.0009843417,0.00041451034,0.00019758372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005447944,0.0004903569,0.000513461,0.00055676856,0.0006505678,0.00053636305,0.0014171854,0.00043512255,0.00001629012],"category_scores_gemma":[0.00049243233,0.000530587,0.00015654767,0.0013300466,0.00022919454,0.0009022712,0.000930489,0.00087032403,0.000036997113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000328954,0.00007171558,0.00027738747,0.00009655177,0.00007754674,0.00015111222,0.0022773037,0.4082517,0.00003462601,0.5574005,0.000007245467,0.031025302],"study_design_scores_gemma":[0.000039958515,0.00019116735,0.00010651999,0.00070902903,0.000047303405,0.0000032765358,0.0019955079,0.39961302,0.00256374,0.59432834,0.0000070584247,0.00039507454],"about_ca_topic_score_codex":0.00014214648,"about_ca_topic_score_gemma":0.00036896416,"teacher_disagreement_score":0.7623533,"about_ca_system_score_codex":0.00044988195,"about_ca_system_score_gemma":0.0003254991,"threshold_uncertainty_score":0.99971455},"labels":[],"label_agreement":null},{"id":"W4380632342","doi":"10.1002/aaai.12095","title":"Evaluation and Design of Generalist Systems (EDGeS)","year":2023,"lang":"en","type":"article","venue":"AI Magazine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Scalability; Theme (computing); Machine learning; World Wide Web","score_opus":0.09645042184813814,"score_gpt":0.32365058205795927,"score_spread":0.22720016020982114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380632342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019448906,0.00061325997,0.9758244,0.0015899332,0.00057607493,0.00051549316,0.0000021413214,0.00020386314,0.0012258828],"genre_scores_gemma":[0.9942242,0.00008095192,0.004318541,0.00015248005,0.000079371,0.00005548767,0.0000046244127,0.000010247485,0.0010741211],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873537,0.00019259247,0.00022451846,0.00024394349,0.00041504807,0.00018855273],"domain_scores_gemma":[0.9990379,0.00011467514,0.00007086003,0.000367914,0.0003581557,0.00005046171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018835563,0.000080415404,0.00012333547,0.00014096094,0.00006266792,0.00009346247,0.00030412312,0.000037199658,0.00001212392],"category_scores_gemma":[0.0001910728,0.00007620847,0.00001784758,0.00068306865,0.00005806841,0.00035655068,0.00012958302,0.000047368016,0.0003845085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020637277,0.00011242106,0.0007869846,0.00017545372,0.00008212212,0.00006327089,0.002778907,0.21006633,0.16947557,0.30853817,0.094599016,0.21330112],"study_design_scores_gemma":[0.000086735934,0.0000813136,0.0007845182,0.00002019632,0.000011683224,0.000007312576,0.000029144803,0.9751069,0.014382073,0.0071687717,0.002224795,0.00009654873],"about_ca_topic_score_codex":0.00005096586,"about_ca_topic_score_gemma":0.000008324359,"teacher_disagreement_score":0.97477525,"about_ca_system_score_codex":0.00003044713,"about_ca_system_score_gemma":0.000070069946,"threshold_uncertainty_score":0.4942207},"labels":[],"label_agreement":null},{"id":"W4380875660","doi":"10.1145/3563359.3597383","title":"Ethical issues in explanations of personalized recommender systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recommender system; Transparency (behavior); Computer science; Ethical issues; Personalization; Data science; Engineering ethics; World Wide Web; Computer security; Engineering","score_opus":0.08764068147313261,"score_gpt":0.3639379450393281,"score_spread":0.27629726356619544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380875660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08187559,0.00057146617,0.73373437,0.122357756,0.0020506494,0.0009728115,0.000009281505,0.0014840995,0.056943968],"genre_scores_gemma":[0.9887017,0.00010828245,0.0054744747,0.00045502104,0.000035210316,0.000051290124,0.00000413379,0.000007760947,0.0051620984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883604,0.00015598806,0.00029878598,0.00022189671,0.00026353297,0.00022376227],"domain_scores_gemma":[0.99913394,0.00037618174,0.00004555465,0.00030045136,0.00009780795,0.000046053745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009076617,0.00007059768,0.00015413687,0.000274587,0.0000485155,0.000063709675,0.00050155644,0.00010377416,0.00007881559],"category_scores_gemma":[0.00020068957,0.000064385684,0.00003631362,0.0011818428,0.00004377326,0.00023590768,0.0001292605,0.00017971973,0.00032514025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023479186,0.000030464726,0.00043691605,0.000019475485,0.0000061488367,0.000011426222,0.0038426802,0.00088162784,0.0006222657,0.9774661,0.015477379,0.0012031408],"study_design_scores_gemma":[0.00029452375,0.000112654176,0.0014246778,0.00011574954,0.0000036517172,0.0000087483695,0.012709638,0.86636245,0.01753779,0.039960567,0.061079606,0.0003899242],"about_ca_topic_score_codex":0.0010078552,"about_ca_topic_score_gemma":0.00019613536,"teacher_disagreement_score":0.93750554,"about_ca_system_score_codex":0.000034632518,"about_ca_system_score_gemma":0.000044438657,"threshold_uncertainty_score":0.41791287},"labels":[],"label_agreement":null},{"id":"W4381135039","doi":"10.32920/22734359.v1","title":"DLIME: A Deterministic Local Interpretable Model - Agnostic Explanations Approach for Computer-Aided Diagnosis Systems","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Machine learning; Cluster analysis; Feature selection; Classifier (UML); Data mining; Stability (learning theory); Popularity; Pattern recognition (psychology)","score_opus":0.11104437799989604,"score_gpt":0.3149733058238708,"score_spread":0.20392892782397476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381135039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032671887,0.00014754952,0.9910414,0.00041271042,0.002613489,0.002767629,0.00016431273,0.001411254,0.0011148965],"genre_scores_gemma":[0.65062356,0.00006680853,0.33919606,0.00026538252,0.0002790885,0.0073884972,0.00022047093,0.00009763111,0.0018625135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950354,0.00017878696,0.0012142967,0.001935665,0.0006325104,0.0010033576],"domain_scores_gemma":[0.9944916,0.0021534525,0.0004139557,0.0020824005,0.00053536496,0.00032323075],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088672497,0.0006782426,0.0009208456,0.0006060708,0.00039344776,0.0014841054,0.0035977887,0.00049335737,0.0000074728523],"category_scores_gemma":[0.00041138678,0.00068435376,0.00038500497,0.0005701315,0.00016141353,0.0005446208,0.0033003837,0.00060034293,0.00020687758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076263645,0.00020961631,0.000026383825,0.00059470587,0.00009757384,0.000024349123,0.00082843046,0.9265634,0.000006890422,0.059341528,0.008731408,0.0035680837],"study_design_scores_gemma":[0.00012123376,0.00014315984,0.0000073803744,0.00035377417,0.00007602721,0.000015538915,0.00022129396,0.979257,0.00035023873,0.018545348,0.0001704101,0.00073861476],"about_ca_topic_score_codex":0.0009851569,"about_ca_topic_score_gemma":0.00011924922,"teacher_disagreement_score":0.6518454,"about_ca_system_score_codex":0.0004019861,"about_ca_system_score_gemma":0.00054919574,"threshold_uncertainty_score":0.9995608},"labels":[],"label_agreement":null},{"id":"W4382239166","doi":"10.1609/aaai.v37i6.25920","title":"Optimal Decision Diagrams for Classification","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Compute Canada","keywords":"Odds; Computer science; Perspective (graphical); Decision tree; Influence diagram; Integer programming; Stability (learning theory); Context (archaeology); Linear programming; Machine learning; Mathematical optimization; Artificial intelligence; Algorithm; Mathematics","score_opus":0.14460793450471177,"score_gpt":0.34340750509157486,"score_spread":0.1987995705868631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29336977,0.000022313608,0.6853404,0.010397216,0.0017230611,0.0018427848,0.000017456941,0.0006900842,0.006596903],"genre_scores_gemma":[0.98307353,0.00006538949,0.015758896,0.00017284842,0.00012912939,0.00022282946,0.0000024120175,0.000026992935,0.0005479455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996855,0.000021655327,0.0008635336,0.0008356633,0.00074776885,0.0006763698],"domain_scores_gemma":[0.9969512,0.00057567767,0.00047493007,0.0006109008,0.0012419434,0.00014532606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013059756,0.0003053209,0.00032967477,0.00033390216,0.00047375294,0.000475739,0.003349914,0.0001629949,0.00003495189],"category_scores_gemma":[0.0017074831,0.00024038677,0.00024740954,0.002229513,0.00030624922,0.00078758074,0.0005398923,0.0002769271,0.00059945526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007504644,0.00009933672,0.000080062055,0.000028669989,0.000010201563,4.307284e-7,0.00087670825,0.00048412342,0.047099207,0.79224443,0.0011434836,0.15785833],"study_design_scores_gemma":[0.000019252317,0.0001951922,0.00022844748,0.00011120441,0.000007655627,0.0000017578955,0.0008419583,0.3518049,0.3851126,0.26090518,0.0005676112,0.00020422191],"about_ca_topic_score_codex":0.000022657894,"about_ca_topic_score_gemma":0.00001538528,"teacher_disagreement_score":0.68970376,"about_ca_system_score_codex":0.0000875742,"about_ca_system_score_gemma":0.00013604051,"threshold_uncertainty_score":0.9802688},"labels":[],"label_agreement":null},{"id":"W4384665361","doi":"10.1007/s00521-023-08696-6","title":"Comparing explanations in RL","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Downstream (manufacturing); Context (archaeology); Artificial intelligence; Reinforcement; Test (biology); Machine learning; Human–computer interaction; Data science; Psychology; Social psychology","score_opus":0.0647685377314945,"score_gpt":0.32198655545966376,"score_spread":0.25721801772816927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384665361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5782162,0.00006713911,0.41408348,0.0026831422,0.00010205316,0.00032432514,0.0000011070423,0.0007621415,0.003760413],"genre_scores_gemma":[0.9972105,0.0000106119915,0.002463187,0.00013228398,0.000055830315,0.00004459765,0.0000052911264,0.000005009234,0.00007269214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915487,0.000030240002,0.0001929311,0.0002874357,0.00010072343,0.00023379702],"domain_scores_gemma":[0.99939895,0.00021034607,0.0000408408,0.00025849653,0.000034112876,0.00005723109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020153697,0.00007404923,0.00009288473,0.00018462249,0.0002873064,0.0001323463,0.00036886742,0.0000248048,0.0000011882148],"category_scores_gemma":[0.000021972628,0.000079463185,0.000018966117,0.001241015,0.000032286796,0.00017208967,0.0002263768,0.00012144459,0.00011786241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013454431,0.00007377043,0.024858393,0.000024844994,0.000005462145,0.000012253908,0.001999169,0.047466494,0.0016731506,0.7409658,0.0009692249,0.18195008],"study_design_scores_gemma":[0.00005270543,0.000008897327,0.01918885,0.000009888284,9.94159e-7,0.0000066136877,0.00019689728,0.96831715,0.0005196586,0.008853626,0.0027407422,0.00010400504],"about_ca_topic_score_codex":0.00007761217,"about_ca_topic_score_gemma":0.00006189291,"teacher_disagreement_score":0.92085063,"about_ca_system_score_codex":0.000017920396,"about_ca_system_score_gemma":0.000012939058,"threshold_uncertainty_score":0.32404146},"labels":[],"label_agreement":null},{"id":"W4385079050","doi":"10.1145/3597465.3605221","title":"A Human-in-the-loop Workflow for Multi-Factorial Sensitivity Analysis of Algorithmic Rankers","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Computer science; Leverage (statistics); Workflow; Data exploration; Data mining; Machine learning; Sensitivity (control systems); Visualization; Artificial intelligence; Database","score_opus":0.09679615228762019,"score_gpt":0.35970038801354165,"score_spread":0.2629042357259215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385079050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13578595,0.0000060770567,0.8625309,0.0004155315,0.00044886046,0.00045930865,0.000009163573,0.00015494348,0.00018927405],"genre_scores_gemma":[0.96971375,0.0000032555054,0.02946484,0.00013497079,0.00010693116,0.0000566291,0.000010904148,0.000009173032,0.00049952895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982307,0.00019140114,0.00038812243,0.00042878813,0.00034034142,0.0004206715],"domain_scores_gemma":[0.9983345,0.0007089192,0.00010207063,0.00065647834,0.00014870867,0.00004932393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019162871,0.00014048038,0.00033786552,0.00062998134,0.0001489467,0.0001033624,0.0006678312,0.000075001546,0.000017227752],"category_scores_gemma":[0.00021362516,0.00011272198,0.00027911965,0.0046008206,0.000064735395,0.0003101587,0.00012618638,0.00010598792,0.00004122443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022143433,0.0022356866,0.017379334,0.00020126475,0.0032836862,0.00066193356,0.049785808,0.2178934,0.11632321,0.33923903,0.013049296,0.23972592],"study_design_scores_gemma":[0.00025545192,0.000056187135,0.0043772548,0.000006915584,0.000077576355,7.377881e-7,0.0005489605,0.9822116,0.010481276,0.0016242521,0.00019521234,0.00016460955],"about_ca_topic_score_codex":0.0009396141,"about_ca_topic_score_gemma":0.0028771595,"teacher_disagreement_score":0.8339278,"about_ca_system_score_codex":0.00004631812,"about_ca_system_score_gemma":0.00004529555,"threshold_uncertainty_score":0.4596669},"labels":[],"label_agreement":null},{"id":"W4385434321","doi":"10.1007/978-1-4842-9579-3_12","title":"Use Cases","year":2023,"lang":"en","type":"book-chapter","venue":"Design Thinking","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generative grammar; Computer science; Workflow; Point (geometry); Process (computing); Artificial intelligence; Generative model; Human–computer interaction; Programming language; Database","score_opus":0.23287284559146162,"score_gpt":0.2910375391046953,"score_spread":0.058164693513233695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385434321","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000058827454,0.0002052214,0.90561056,0.00033483823,0.0014627156,0.00044162653,0.0000058792893,0.0015323559,0.0904009],"genre_scores_gemma":[0.001677106,0.0002447377,0.09299194,0.0010620771,0.00042970153,0.0000264403,0.000012889887,0.0001758009,0.9033793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997686,0.000060743918,0.00040915055,0.0007422745,0.00063998695,0.00046181033],"domain_scores_gemma":[0.9964172,0.001960233,0.00023642127,0.0011067368,0.00016637654,0.00011301778],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007524111,0.0003743266,0.0003419913,0.00035324827,0.00034407258,0.0008821057,0.0016954774,0.00031546413,0.00007085723],"category_scores_gemma":[0.00037245802,0.00038648956,0.0001615808,0.00014647782,0.00007247591,0.00086138415,0.00058987463,0.00047798394,0.0036917746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036149356,0.0000050663834,0.000001754637,0.0000140991315,0.00003495002,0.0019773124,0.0008444862,0.0003515353,0.000056999907,0.97815126,0.0055917874,0.012967121],"study_design_scores_gemma":[0.000030358902,0.00012131815,0.0000033211504,0.00042784464,0.000028839186,0.0001249333,0.000018833995,0.009523381,0.0028696836,0.92187184,0.06422303,0.0007565932],"about_ca_topic_score_codex":0.000115622344,"about_ca_topic_score_gemma":0.0000401231,"teacher_disagreement_score":0.8129784,"about_ca_system_score_codex":0.00012509653,"about_ca_system_score_gemma":0.00016035623,"threshold_uncertainty_score":0.9998587},"labels":[],"label_agreement":null},{"id":"W4385434398","doi":"10.1007/978-1-4842-9579-3_8","title":"The Art of the Prompt","year":2023,"lang":"en","type":"book-chapter","venue":"Design Thinking","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generative grammar; Computer science; Image (mathematics); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.06969338833698943,"score_gpt":0.24956683293835352,"score_spread":0.1798734446013641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385434398","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026596988,0.00037168025,0.6296891,0.0030700732,0.0022502088,0.00097562745,0.0000023465495,0.00037139098,0.36326692],"genre_scores_gemma":[0.0019394017,0.00017750022,0.01121795,0.0004836255,0.00025977346,0.000041244482,0.0000015218185,0.00009219859,0.9857868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801856,0.00009407934,0.00042000916,0.0003882335,0.0007541743,0.00032491598],"domain_scores_gemma":[0.9971042,0.0009041582,0.00038784987,0.001400909,0.00016570449,0.00003716717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016374884,0.00023000386,0.00022265276,0.00007872604,0.00061904953,0.00028290058,0.003502418,0.0001720804,0.0000153052],"category_scores_gemma":[0.00016473194,0.00013520614,0.00018652277,0.00016284072,0.00019108586,0.00017057246,0.0008129209,0.00047112137,0.0007506609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024918716,0.0000031741838,0.0000010722773,0.000011490553,0.00003040897,0.000013414597,0.0010989005,0.0002507451,0.000104157065,0.9813919,0.0069775544,0.010114678],"study_design_scores_gemma":[0.00001698394,0.000036697467,0.000004398532,0.00026760722,0.000013691247,0.000007015258,0.000023189281,0.005980515,0.005916189,0.9103272,0.07722331,0.00018320039],"about_ca_topic_score_codex":0.0000116358215,"about_ca_topic_score_gemma":0.000026443791,"teacher_disagreement_score":0.62251985,"about_ca_system_score_codex":0.000060484326,"about_ca_system_score_gemma":0.00019608298,"threshold_uncertainty_score":0.96484774},"labels":[],"label_agreement":null},{"id":"W4385478085","doi":"10.1109/compsac57700.2023.00185","title":"Linking Team-level and Organization-level Governance in Machine Learning Operations through Explainable AI and Responsible AI Connector","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Corporate governance; Cable gland; Knowledge management; Computer science; Artificial intelligence; Process management; Learning organization; Engineering management; Engineering; Business; Telecommunications","score_opus":0.04899054021991848,"score_gpt":0.2921494805999299,"score_spread":0.24315894038001143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385478085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21837725,0.00037169497,0.76344883,0.014832559,0.0002503517,0.00045826298,0.00001542168,0.00059054303,0.0016551012],"genre_scores_gemma":[0.96496224,0.00039229702,0.026408888,0.0014995631,0.00004097121,0.00002335131,0.000015511207,0.000028297722,0.006628894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982204,0.00013875675,0.00035497232,0.00058776105,0.0002542972,0.0004438057],"domain_scores_gemma":[0.9989456,0.0003449,0.000055930228,0.00033565407,0.000235341,0.0000825666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006551774,0.00018871571,0.00021350499,0.00016262254,0.00062059436,0.0005610982,0.00039863307,0.00009344179,0.000079890364],"category_scores_gemma":[0.0011256683,0.0001880035,0.000015968597,0.0022130376,0.00007327842,0.0020903077,0.00055180397,0.00032291032,0.00011804239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015253984,0.000068982394,0.073129125,0.00005611515,0.000015812167,0.00007745532,0.0115572745,0.028385649,0.008287332,0.8697035,0.0013687316,0.0073348028],"study_design_scores_gemma":[0.00040406265,0.00012428232,0.01939635,0.00012004675,0.0000049911487,0.00003461236,0.0010442849,0.91234213,0.04227864,0.01898224,0.00475619,0.0005121453],"about_ca_topic_score_codex":0.0017345668,"about_ca_topic_score_gemma":0.0033088455,"teacher_disagreement_score":0.8839565,"about_ca_system_score_codex":0.00008204099,"about_ca_system_score_gemma":0.00021207455,"threshold_uncertainty_score":0.766656},"labels":[],"label_agreement":null},{"id":"W4385482308","doi":"10.1109/ecai58194.2023.10193964","title":"Impact of Feature Encoding on Malware Classification Explainability","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Malware; Encoding (memory); Computer science; Feature (linguistics); Feature extraction; Pattern recognition (psychology); Artificial intelligence; Computer security","score_opus":0.07726922416953384,"score_gpt":0.356794254277948,"score_spread":0.2795250301084141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385482308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8931491,0.000010787757,0.084925406,0.002654916,0.00027834618,0.00033810353,0.0000052575842,0.00069408305,0.017944042],"genre_scores_gemma":[0.9966058,0.000009169558,0.0022592396,0.00004753375,0.000033296415,0.00001953872,0.0000050427507,0.0000076035353,0.0010127737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986492,0.00008054305,0.00022573257,0.00041039762,0.00030720563,0.00032695697],"domain_scores_gemma":[0.99853325,0.00025576502,0.00009546129,0.00084343826,0.0001850228,0.00008708165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052524847,0.00013075187,0.00015318973,0.00022706673,0.000120778124,0.00007733087,0.00073772896,0.000084588,0.00006524753],"category_scores_gemma":[0.0003110262,0.00010395025,0.00013907414,0.0014362641,0.00004854562,0.00050172245,0.00015063262,0.00013905899,0.00038377132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007210488,0.00040311244,0.061108727,0.00009306521,0.000058689082,0.000046478734,0.0051999576,0.0068987743,0.08627257,0.70648104,0.030906592,0.10245886],"study_design_scores_gemma":[0.00016553844,0.00088243675,0.50027907,0.00006747354,0.0000061610845,0.000007942051,0.0016912163,0.32513744,0.1401097,0.030221255,0.0009269026,0.000504842],"about_ca_topic_score_codex":0.00011823125,"about_ca_topic_score_gemma":0.000018058417,"teacher_disagreement_score":0.6762598,"about_ca_system_score_codex":0.00017149493,"about_ca_system_score_gemma":0.000097668184,"threshold_uncertainty_score":0.49327317},"labels":[],"label_agreement":null},{"id":"W4385483623","doi":"10.31234/osf.io/4cbuv","title":"Reclaiming AI as a theoretical tool for cognitive science","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Simons Institute for the Theory of Computing, University of California Berkeley; Lorentz Center; Natural Sciences and Engineering Research Council of Canada; Koninklijke Nederlandse Akademie van Wetenschappen","keywords":"Cognitive science; Cognition; Context (archaeology); Field (mathematics); Computer science; Rotation formalisms in three dimensions; Cognitive architecture; Realisation; Artificial intelligence; Multidisciplinary approach; Computational model; Comparative cognition; Psychology; Epistemology; Sociology; Mathematics","score_opus":0.06988998295052878,"score_gpt":0.3785062093367649,"score_spread":0.3086162263862361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385483623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008703462,0.000018028413,0.9699917,0.006516579,0.001760715,0.001257806,0.000012530238,0.0007754012,0.010963772],"genre_scores_gemma":[0.92053205,0.00002033365,0.073705256,0.0026009637,0.00023436289,0.00059054984,0.000008623212,0.00004195598,0.0022658876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960918,0.000075945114,0.00048949156,0.0016493091,0.00078507554,0.00090838975],"domain_scores_gemma":[0.9960888,0.0014076342,0.00014056305,0.0010824292,0.0010824786,0.00019811474],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002601897,0.0003241753,0.0003431537,0.00042774738,0.00062853703,0.0014199659,0.0032553962,0.00023559255,0.000102864615],"category_scores_gemma":[0.0041931984,0.00029825862,0.00019699728,0.00097196223,0.001224712,0.000678662,0.004673887,0.0005935993,0.0011303547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015336864,0.000036086636,0.0000217814,0.00004299565,0.0000142629115,0.00002366631,0.000953747,0.0001653468,0.0003611744,0.97846603,0.0003862786,0.019513309],"study_design_scores_gemma":[0.000052377694,0.000103899365,0.000029769935,0.00018783506,0.00001267609,0.0000075738576,0.00030817732,0.19870885,0.07175244,0.7282691,0.00019602025,0.00037126333],"about_ca_topic_score_codex":0.000113392816,"about_ca_topic_score_gemma":0.000017208435,"teacher_disagreement_score":0.9118286,"about_ca_system_score_codex":0.00018340681,"about_ca_system_score_gemma":0.0014270653,"threshold_uncertainty_score":0.99994695},"labels":[],"label_agreement":null},{"id":"W4385564898","doi":"10.18653/v1/2023.acl-demo.21","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Python (programming language); Debiasing; Artificial intelligence; Domain (mathematical analysis); Natural language processing; Adaptation (eye); Programming language; Cognitive science","score_opus":0.055215519934208465,"score_gpt":0.28085303581281396,"score_spread":0.22563751587860548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385564898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032118976,0.000018807594,0.9598182,0.0015445767,0.00016594227,0.00018521307,0.0000062188496,0.0005540258,0.0055880304],"genre_scores_gemma":[0.9714031,0.000032720927,0.025397269,0.00083753554,0.000030279973,0.00003616233,0.000015813242,0.000019472109,0.0022276146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987778,0.00004228048,0.00029608957,0.0003807479,0.0001985908,0.00030449318],"domain_scores_gemma":[0.9988152,0.00033858677,0.000072861316,0.0006333666,0.000062840045,0.00007714433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016776897,0.00010033251,0.00021523863,0.00059492583,0.00007272262,0.00010393488,0.00096361723,0.000037897138,0.000053909287],"category_scores_gemma":[0.000047329526,0.000092869246,0.00020059006,0.0041050804,0.000029234854,0.001302847,0.00032252495,0.000049591006,0.0000614703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001163055,0.00006141358,0.00038609176,0.000021046359,0.00013118553,0.000015208161,0.00077606965,0.3484355,0.0017457487,0.6190398,0.0036719772,0.025704348],"study_design_scores_gemma":[0.000025200088,0.00006827087,0.00042537285,0.0000013167843,0.00004275796,2.8823285e-7,0.000060273687,0.9434105,0.01726027,0.03790188,0.00071338034,0.00009048666],"about_ca_topic_score_codex":0.000034456607,"about_ca_topic_score_gemma":0.000028055585,"teacher_disagreement_score":0.93928415,"about_ca_system_score_codex":0.000005488478,"about_ca_system_score_gemma":0.000028896187,"threshold_uncertainty_score":0.3787098},"labels":[],"label_agreement":null},{"id":"W4385570917","doi":"10.18653/v1/2023.findings-acl.867","title":"Model Interpretability and Rationale Extraction by Input Mask Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Artificial neural network; Masking (illustration); Modalities; Task (project management); Pattern recognition (psychology)","score_opus":0.03587866272525021,"score_gpt":0.2899735662333752,"score_spread":0.254094903508125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385570917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02447769,0.000017069884,0.9699167,0.0018799792,0.0001083669,0.0001538873,0.0000018738735,0.00033788517,0.0031065466],"genre_scores_gemma":[0.9125348,0.00004581884,0.084607005,0.00030161472,0.000016159507,0.000031888692,0.000013863798,0.0000065410018,0.002442347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914575,0.000037046226,0.00018090427,0.00031468435,0.00016485268,0.00015673919],"domain_scores_gemma":[0.99946475,0.00010231082,0.000038949966,0.00025803494,0.00007918701,0.00005678548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032905213,0.00007612021,0.000068843256,0.000080374295,0.0001180122,0.00016603543,0.00021378536,0.000045987563,0.00004844866],"category_scores_gemma":[0.00009735385,0.000074557225,0.000019699404,0.0004021152,0.000034752396,0.0012594796,0.0001405158,0.00006499171,0.00009604562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006810744,0.000049650753,0.00031922708,0.0000110820465,0.0000054995103,0.0000015755116,0.0013277767,0.9081273,0.007315967,0.055792738,0.0061163986,0.020925963],"study_design_scores_gemma":[0.000026997215,0.000016110196,0.000038680948,0.00000270508,0.0000011371499,0.0000018479546,0.00010181986,0.9721113,0.008845802,0.018566394,0.0002048934,0.0000823083],"about_ca_topic_score_codex":0.00003814803,"about_ca_topic_score_gemma":0.000022412158,"teacher_disagreement_score":0.88805705,"about_ca_system_score_codex":0.000039955416,"about_ca_system_score_gemma":0.000034454944,"threshold_uncertainty_score":0.30403554},"labels":[],"label_agreement":null},{"id":"W4385571067","doi":"10.18653/v1/2023.acl-long.483","title":"Efficient Shapley Values Estimation by Amortization for Text Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Institute for Catastrophic Loss Reduction; Cisco Systems","keywords":"Shapley value; Interpretability; Computer science; Stability (learning theory); Amortized analysis; Feature (linguistics); Theoretical computer science; Algorithm; Artificial intelligence; Machine learning; Mathematics; Data structure; Mathematical economics; Game theory","score_opus":0.0499369776387494,"score_gpt":0.31947818509686315,"score_spread":0.2695412074581138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028473321,0.000013977563,0.96617466,0.0024550627,0.0002791849,0.00047442314,0.0000040588875,0.0007789958,0.0013463203],"genre_scores_gemma":[0.95653534,0.0000071157815,0.040746324,0.00021145251,0.00003986582,0.00016982183,0.00008210639,0.000013990494,0.0021939888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871194,0.00003629099,0.0002958062,0.0003957814,0.0002736572,0.000286524],"domain_scores_gemma":[0.99904996,0.00020307525,0.00010088131,0.00038659875,0.00019542474,0.00006406472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053480006,0.00010485212,0.00009281796,0.00016557857,0.00024881557,0.00021839746,0.00044726187,0.000057723893,0.000022334643],"category_scores_gemma":[0.00029261064,0.00010034569,0.000045874647,0.0010253701,0.000032437383,0.00030491746,0.0000763568,0.000040534545,0.0007556063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008660464,0.00012261611,0.00016665865,0.00003557561,0.000010553337,9.10017e-7,0.0015326975,0.16795537,0.02988374,0.58525246,0.05959957,0.15543117],"study_design_scores_gemma":[0.00005322333,0.000045600787,0.0006640841,0.0000071411414,0.000003060148,5.292262e-7,0.00016988165,0.950043,0.034201067,0.01352782,0.0011631667,0.000121377336],"about_ca_topic_score_codex":0.000030644373,"about_ca_topic_score_gemma":0.0000068855147,"teacher_disagreement_score":0.928062,"about_ca_system_score_codex":0.0000747386,"about_ca_system_score_gemma":0.000041224543,"threshold_uncertainty_score":0.9712042},"labels":[],"label_agreement":null},{"id":"W4385573178","doi":"10.18653/v1/2022.blackboxnlp-1.10","title":"How (Un)Faithful is Attention?","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Metric (unit); Artificial intelligence; Binary number; Encoder; Simple (philosophy); Measure (data warehouse); Machine learning; Data mining; Mathematics; Arithmetic","score_opus":0.021813937023083166,"score_gpt":0.23589322400456864,"score_spread":0.21407928698148548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03881933,0.00009702373,0.8826005,0.05355895,0.00085842394,0.0002241497,0.0000038125595,0.000482231,0.023355564],"genre_scores_gemma":[0.94720113,0.0000035907533,0.016099194,0.0031787972,0.00004649827,0.00005935313,0.0000016603776,0.000008803194,0.03340097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986834,0.00007450187,0.00013068641,0.00038770915,0.00042144032,0.00030225457],"domain_scores_gemma":[0.9991429,0.000040568037,0.000052316966,0.0006226567,0.00006618861,0.000075396536],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029206806,0.00009423265,0.00008984752,0.00010530245,0.00052401377,0.00034294094,0.0011961667,0.000018151626,0.0013953702],"category_scores_gemma":[0.00001934218,0.00009449626,0.00007731962,0.00069859787,0.000026473712,0.0006917381,0.0008332622,0.00014334386,0.00036121128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034391012,0.00015943512,0.0010658877,0.0000049016576,0.000022411334,0.00007112453,0.0015422113,0.00010197086,0.0033384599,0.8581803,0.040270325,0.09523955],"study_design_scores_gemma":[0.00025836832,0.00047335014,0.0017366094,0.0000046867735,0.000011510747,0.00013453262,0.0062689665,0.20978732,0.08223373,0.13035952,0.5678537,0.00087773177],"about_ca_topic_score_codex":0.00007188321,"about_ca_topic_score_gemma":0.000010066087,"teacher_disagreement_score":0.9083818,"about_ca_system_score_codex":0.00006492569,"about_ca_system_score_gemma":0.000037941154,"threshold_uncertainty_score":0.9995175},"labels":[],"label_agreement":null},{"id":"W4385638922","doi":"10.1038/s41598-023-39301-4","title":"New drugs and stock market: a machine learning framework for predicting pharma market reaction to clinical trial announcements","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Event study; Portfolio; Computer science; Stock market; Artificial intelligence; Machine learning; Market capitalization; Econometrics; Business; Actuarial science; Economics; Finance","score_opus":0.07418405740963437,"score_gpt":0.3820984849342864,"score_spread":0.30791442752465203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385638922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32515445,0.000089370165,0.62050647,0.002145873,0.045038033,0.0032714626,0.00000780805,0.0010315663,0.0027549698],"genre_scores_gemma":[0.6369577,0.00008666151,0.21055512,0.0006229402,0.0036994976,0.0007002815,0.00012695864,0.00014084118,0.14711],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99550366,0.00023341706,0.0011405769,0.0015776439,0.00085447717,0.0006902203],"domain_scores_gemma":[0.997,0.00082888186,0.00053989526,0.0009459635,0.00024712223,0.00043815613],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011856564,0.00021635657,0.00030961994,0.00038337143,0.00089172623,0.0011022168,0.00048972666,0.00013343294,0.00008555873],"category_scores_gemma":[0.00465058,0.00021576455,0.00014520923,0.0018169216,0.000086987035,0.0007983271,0.00053696084,0.00036495292,0.00006521706],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004139525,0.00027468364,0.02381027,0.00010731255,0.00012673358,0.00042444887,0.0063892878,0.00042117824,0.0034775843,0.0013746715,0.41490993,0.5445444],"study_design_scores_gemma":[0.003119843,0.0010613211,0.0017870988,0.00024903883,0.00005497719,0.000108328924,0.00061198144,0.31707585,0.0027513758,0.0761293,0.5962659,0.0007849524],"about_ca_topic_score_codex":0.00007538938,"about_ca_topic_score_gemma":0.000018560775,"teacher_disagreement_score":0.5437594,"about_ca_system_score_codex":0.00008242509,"about_ca_system_score_gemma":0.00028049562,"threshold_uncertainty_score":0.99993473},"labels":[],"label_agreement":null},{"id":"W4385791603","doi":"10.1017/9781009258227.003","title":"Artificial Intelligence and Agents","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.08894281395247638,"score_gpt":0.24532443812226384,"score_spread":0.15638162416978746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791603","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004930496,0.00005254652,0.09864787,0.000089571615,0.0007739213,0.0003564311,0.00004860379,0.00052805967,0.8994537],"genre_scores_gemma":[0.001884196,0.00020979851,0.00091763405,0.000082397775,0.00013153188,0.000001198622,0.000010290994,0.00004949989,0.99671346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779665,0.000046531153,0.00032230653,0.0009583617,0.00041054102,0.00046560913],"domain_scores_gemma":[0.9981398,0.0002281502,0.00021783641,0.0009530947,0.00019245868,0.0002686493],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022989152,0.00041137025,0.00038069184,0.0003576096,0.00033634173,0.00023898468,0.0015809145,0.00035056684,0.0000042278944],"category_scores_gemma":[0.000043380962,0.0005128155,0.0001542796,0.0000405331,0.00033965672,0.0003139169,0.0016742474,0.0004951878,0.00028426928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014739806,0.0000073868714,4.5952024e-7,0.00003767705,0.000050432587,0.0006994579,0.00014956816,0.00002013889,0.000023730561,0.9649929,0.0055988245,0.028404677],"study_design_scores_gemma":[0.000059995968,0.00017759234,0.000010823126,0.00030710112,0.00012012845,0.000044433767,0.00017488521,0.017562686,0.0073077246,0.007762304,0.9650583,0.0014140243],"about_ca_topic_score_codex":0.00018236987,"about_ca_topic_score_gemma":0.000012339272,"teacher_disagreement_score":0.9594595,"about_ca_system_score_codex":0.00014999247,"about_ca_system_score_gemma":0.00011603352,"threshold_uncertainty_score":0.9997323},"labels":[],"label_agreement":null},{"id":"W4385791641","doi":"10.1017/9781009258227.030","title":"Index of Algorithms","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Implementation; Code (set theory); Generative grammar; Artificial intelligence; Index (typography); Data science; Software engineering; Programming language","score_opus":0.04425272690565705,"score_gpt":0.2245832415651888,"score_spread":0.18033051465953176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791641","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015878706,0.000034578665,0.090858445,0.000026020225,0.0005861154,0.00024370482,0.00006379057,0.00033096966,0.9078405],"genre_scores_gemma":[0.0009084471,0.000065893066,0.00089348125,0.000027853313,0.00007924372,5.796735e-7,0.000008423382,0.000038661023,0.99797744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982669,0.000034060675,0.00027756323,0.0006311446,0.0004476636,0.00034269656],"domain_scores_gemma":[0.9979451,0.0001798759,0.00030542893,0.001098871,0.00031330102,0.00015743874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017473736,0.00031010405,0.00041587584,0.0003770291,0.00013435347,0.00005820027,0.0020081254,0.00033973192,0.0000027059064],"category_scores_gemma":[0.00002309883,0.00038520675,0.00022944687,0.000038043454,0.00025654916,0.00022552458,0.0013075863,0.0004010446,0.00009846249],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011480454,0.0000070709875,0.0000011994885,0.000049968112,0.00006992588,0.00040510087,0.00009410101,0.000027695021,0.000042311858,0.9829278,0.008855566,0.00750781],"study_design_scores_gemma":[0.00022156739,0.00012137908,0.000016962049,0.00026558893,0.0000699439,0.000015078415,0.000069292575,0.010185319,0.0073040426,0.0008014191,0.980171,0.00075837836],"about_ca_topic_score_codex":0.00037427086,"about_ca_topic_score_gemma":0.0000061059072,"teacher_disagreement_score":0.98212636,"about_ca_system_score_codex":0.00013586144,"about_ca_system_score_gemma":0.00017563479,"threshold_uncertainty_score":0.99986},"labels":[],"label_agreement":null},{"id":"W4385791642","doi":"10.1017/9781009258227.007","title":"Reasoning with Constraints","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Implementation; Code (set theory); Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.034389066425831324,"score_gpt":0.21052726863256194,"score_spread":0.1761382022067306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791642","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002576739,0.000019242141,0.07236554,0.000033278753,0.00031085545,0.00028270294,0.000041351712,0.0006640331,0.92625725],"genre_scores_gemma":[0.00096952944,0.000033349726,0.0024912658,0.00005587464,0.00007513306,9.257609e-7,0.000011143059,0.000051227333,0.99631155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809885,0.00003587854,0.00018677903,0.0008061087,0.00041700737,0.00045536563],"domain_scores_gemma":[0.99811023,0.0001751692,0.00022618359,0.0010057054,0.00025885657,0.00022384399],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016497175,0.00037902148,0.0003600242,0.0002624275,0.00029104803,0.0001716032,0.0015584698,0.00027097494,0.000004225881],"category_scores_gemma":[0.000023607654,0.00042034176,0.00013224299,0.000032922304,0.0005114924,0.0002803112,0.0007884709,0.0005060968,0.00019369615],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019720324,0.0000041336475,0.0000013016449,0.000028025837,0.00008363017,0.0019599898,0.00010524934,0.000020145346,0.00001691078,0.985989,0.0068930844,0.0048788246],"study_design_scores_gemma":[0.00030687533,0.00016786183,0.000011941463,0.00071278657,0.000109845554,0.0001145424,0.00015314513,0.0022555888,0.0022749316,0.00020806293,0.99255335,0.0011310792],"about_ca_topic_score_codex":0.0001462679,"about_ca_topic_score_gemma":0.000010396905,"teacher_disagreement_score":0.9857809,"about_ca_system_score_codex":0.00018824355,"about_ca_system_score_gemma":0.0002569601,"threshold_uncertainty_score":0.9998248},"labels":[],"label_agreement":null},{"id":"W4385791643","doi":"10.1017/9781009258227.026","title":"Retrospect and Prospect","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Implementation; Code (set theory); Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.03442814937263706,"score_gpt":0.20983717176416514,"score_spread":0.17540902239152809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791643","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000055446173,0.00008616335,0.00962343,0.000069028065,0.00049108284,0.00039135866,0.000043723012,0.00070634694,0.98853344],"genre_scores_gemma":[0.00092050026,0.00017708882,0.0007455219,0.000046533656,0.00011219259,9.843632e-7,0.000006411484,0.000047108522,0.99794364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810743,0.000028629407,0.00020263359,0.0009001184,0.0003564285,0.00040477604],"domain_scores_gemma":[0.9983171,0.00013623902,0.00018300429,0.0009857619,0.00017107709,0.00020681131],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018246585,0.00036445097,0.000380708,0.0002638296,0.0002924963,0.00021339764,0.00124508,0.0002954546,0.0000020881419],"category_scores_gemma":[0.00003102579,0.0004378669,0.0001428912,0.000030751646,0.00026362808,0.00027892148,0.0013708002,0.0004815657,0.00012797175],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011424548,0.0000036745548,0.000003666604,0.000040847797,0.000047471705,0.00075510825,0.00008344896,0.0000017363125,0.00004596935,0.9833867,0.013752918,0.0018670453],"study_design_scores_gemma":[0.00021951798,0.0001642122,0.000057421857,0.00021520104,0.00007523323,0.0000463624,0.000037135585,0.00198005,0.0027073557,0.0015183865,0.9920588,0.0009203027],"about_ca_topic_score_codex":0.000154687,"about_ca_topic_score_gemma":0.000009239445,"teacher_disagreement_score":0.9818683,"about_ca_system_score_codex":0.00020199546,"about_ca_system_score_gemma":0.00010446498,"threshold_uncertainty_score":0.9998073},"labels":[],"label_agreement":null},{"id":"W4385791648","doi":"10.1017/9781009258227","title":"Artificial Intelligence","year":2023,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Artificial intelligence; Implementation; Code (set theory); Software engineering; Programming language","score_opus":0.05907902442046043,"score_gpt":0.24352777471447176,"score_spread":0.18444875029401134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791648","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009109741,0.000042432115,0.24885224,0.00007487767,0.0013368502,0.00036479416,0.000053140437,0.0009760272,0.74829054],"genre_scores_gemma":[0.00017902811,0.00006902446,0.0013599639,0.00008599987,0.0003369657,0.0000028769834,0.000029749483,0.00006511913,0.9978713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968431,0.00013274243,0.00044795065,0.0011984741,0.00061996497,0.0007577978],"domain_scores_gemma":[0.99692446,0.00045561334,0.00031187947,0.0016683546,0.00032937588,0.0003103242],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036004273,0.00051806157,0.00051124475,0.0005171344,0.00040629588,0.0003206914,0.0037918994,0.00050663116,0.0000035667858],"category_scores_gemma":[0.00009682485,0.00065376994,0.00031837233,0.00013832313,0.00034497454,0.00042409584,0.0019906356,0.0007987161,0.0010572823],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015754307,0.000016038188,1.4089547e-7,0.000051743045,0.000053361084,0.0009075106,0.00013857476,0.000058093046,0.000037101156,0.8774254,0.10342906,0.017867247],"study_design_scores_gemma":[0.000029944518,0.000106664265,0.0000014902577,0.00019357963,0.000068759255,0.000020370977,0.00012252186,0.0108665405,0.010196063,0.0028953343,0.9745019,0.0009968083],"about_ca_topic_score_codex":0.00018344256,"about_ca_topic_score_gemma":0.000014319296,"teacher_disagreement_score":0.8745301,"about_ca_system_score_codex":0.00060788076,"about_ca_system_score_gemma":0.0007105942,"threshold_uncertainty_score":0.9997205},"labels":[],"label_agreement":null},{"id":"W4385791653","doi":"10.1017/9781009258227.014","title":"Learning with Uncertainty","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.032340753673934554,"score_gpt":0.20781409689649188,"score_spread":0.17547334322255734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791653","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006436536,0.000018752718,0.035063688,0.000046656718,0.00028943917,0.0002787304,0.000017175955,0.00089091645,0.96333027],"genre_scores_gemma":[0.0012265329,0.000051122024,0.00064665574,0.00004412482,0.000086217886,0.0000010784657,0.000015483696,0.000056295423,0.9978725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801034,0.000055757944,0.00018528604,0.0008294939,0.00045115565,0.00046799748],"domain_scores_gemma":[0.99816877,0.00022599241,0.0002345274,0.0008812926,0.00028422388,0.00020517418],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018205366,0.00039283698,0.00036763801,0.00028294316,0.00039327546,0.00017324662,0.0016045424,0.00027570484,0.000002805835],"category_scores_gemma":[0.000025996009,0.0004234461,0.00014931062,0.0000399707,0.00024199166,0.00026648585,0.0009363055,0.00077054347,0.00021456018],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032126718,0.000004252212,0.000001492256,0.00003403426,0.00007983951,0.0011751483,0.0001689214,0.00077693537,0.000021406144,0.98847085,0.0054420363,0.003792937],"study_design_scores_gemma":[0.00017640003,0.00023014063,0.0000037615082,0.00023039135,0.00006290862,0.000024684097,0.00013418566,0.0073341797,0.00077050197,0.000121139026,0.990215,0.00069669937],"about_ca_topic_score_codex":0.00038577055,"about_ca_topic_score_gemma":0.000020656133,"teacher_disagreement_score":0.98834974,"about_ca_system_score_codex":0.0002450638,"about_ca_system_score_gemma":0.00021046122,"threshold_uncertainty_score":0.9998217},"labels":[],"label_agreement":null},{"id":"W4385791654","doi":"10.1017/9781009258227.010","title":"Learning and Reasoning with Uncertainty","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Artificial intelligence; Implementation; Deep learning; Space (punctuation); Data science; Software engineering; Programming language","score_opus":0.023536105104067135,"score_gpt":0.21033904857240002,"score_spread":0.18680294346833287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791654","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024673602,0.00004937686,0.020578306,0.000033055047,0.0001504411,0.00022551148,0.000010497619,0.0005807072,0.9781254],"genre_scores_gemma":[0.0018422093,0.000119726275,0.0012101195,0.000024852534,0.0000561931,7.898249e-7,0.000008214637,0.000043187414,0.9966947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983903,0.000048097423,0.000143658,0.00073854375,0.00030877243,0.00037061892],"domain_scores_gemma":[0.998736,0.00021170033,0.00019106123,0.00048683048,0.00018825731,0.00018611283],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018399456,0.0003230945,0.0003146779,0.00021869692,0.00041066922,0.00018630504,0.00074153446,0.00021616352,0.0000011682396],"category_scores_gemma":[0.00003271267,0.00035023608,0.00007393346,0.000029359502,0.00024624393,0.00023812497,0.00087399944,0.0006145495,0.000033827604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027804408,0.000002192547,0.0000068495024,0.000036165296,0.000060763698,0.00078595,0.00021508633,0.00015361533,0.00001906035,0.99226743,0.0011453243,0.005279777],"study_design_scores_gemma":[0.00022521091,0.00024261305,0.000013773957,0.0005118729,0.00008298357,0.000057893783,0.0002889288,0.01197628,0.00055072387,0.00011661274,0.9851389,0.0007941853],"about_ca_topic_score_codex":0.00034600668,"about_ca_topic_score_gemma":0.000017828044,"teacher_disagreement_score":0.9921508,"about_ca_system_score_codex":0.00013996936,"about_ca_system_score_gemma":0.00012295488,"threshold_uncertainty_score":0.999895},"labels":[],"label_agreement":null},{"id":"W4385791658","doi":"10.1017/9781009258227.011","title":"Supervised Machine Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Artificial intelligence; Implementation; Code (set theory); Data science; Software engineering; Programming language","score_opus":0.0449768148350184,"score_gpt":0.21434104986240404,"score_spread":0.16936423502738565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791658","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028054861,0.000081314654,0.029733302,0.00006377678,0.00058879465,0.0002816591,0.000042920223,0.0010759205,0.96810424],"genre_scores_gemma":[0.00059303135,0.00014913433,0.0006981249,0.00006221049,0.000107822365,8.610632e-7,0.000033910484,0.00006603883,0.99828887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979037,0.00007341055,0.00024656326,0.0008496098,0.00043656232,0.00049012003],"domain_scores_gemma":[0.99813944,0.00023968273,0.00019285249,0.000974211,0.00022235491,0.00023145627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022677681,0.00041749925,0.00040962323,0.0003653923,0.00041018263,0.00018140281,0.0020463343,0.00034110714,0.0000075788225],"category_scores_gemma":[0.000045575092,0.00051777775,0.0002542487,0.00003802483,0.00016617689,0.00029867238,0.0015678138,0.00084507733,0.0004615328],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015727594,0.0000055406913,0.0000021529468,0.00004114616,0.00006500276,0.00096102577,0.00013732142,0.00006953244,0.00007863949,0.98747057,0.0064014997,0.004751829],"study_design_scores_gemma":[0.00017068544,0.00008434523,0.0000033753422,0.00012277083,0.00005071026,0.000014840354,0.00003756126,0.02249708,0.0014876255,0.00014661359,0.9747466,0.0006378032],"about_ca_topic_score_codex":0.0004606784,"about_ca_topic_score_gemma":0.000014158472,"teacher_disagreement_score":0.98732394,"about_ca_system_score_codex":0.00020128216,"about_ca_system_score_gemma":0.00013425117,"threshold_uncertainty_score":0.99972737},"labels":[],"label_agreement":null},{"id":"W4385791660","doi":"10.1017/9781009258227.013","title":"Reasoning with Uncertainty","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.03267971374999882,"score_gpt":0.21110117240173262,"score_spread":0.1784214586517338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791660","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043832348,0.000027732078,0.04725334,0.00004699534,0.00033979266,0.00030558178,0.000037655,0.00078264636,0.9511624],"genre_scores_gemma":[0.0005811083,0.000046026234,0.0016685331,0.00006281701,0.00009742558,0.0000012805191,0.000015631244,0.000057735477,0.9974694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979162,0.000041884512,0.00019459894,0.00088649645,0.00046848154,0.0004923422],"domain_scores_gemma":[0.9978367,0.0001905936,0.00023884964,0.00121028,0.0002957731,0.00022776879],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001831368,0.00041391054,0.00038559627,0.00027654567,0.0003424529,0.00018288287,0.0018171566,0.0002841308,0.0000024225126],"category_scores_gemma":[0.00002471345,0.00044391805,0.00015286887,0.000042543055,0.00025126486,0.0002973086,0.0009585076,0.00054455845,0.0001634725],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033790653,0.0000044793496,0.0000010545147,0.00003136229,0.000082981285,0.0013704504,0.00011816492,0.00018692274,0.000014876156,0.98568326,0.010017215,0.002455441],"study_design_scores_gemma":[0.00019640345,0.00013787152,0.0000062636605,0.00043314177,0.000080887425,0.00003865192,0.00009228427,0.005983313,0.0010396912,0.00018314892,0.99098676,0.00082158623],"about_ca_topic_score_codex":0.00053471007,"about_ca_topic_score_gemma":0.000031773667,"teacher_disagreement_score":0.9855001,"about_ca_system_score_codex":0.00028354366,"about_ca_system_score_gemma":0.00024888295,"threshold_uncertainty_score":0.9998013},"labels":[],"label_agreement":null},{"id":"W4385791664","doi":"10.1017/9781009258227.008","title":"Propositions and Inference","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Inference; Code (set theory); Implementation; Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.04513973933741957,"score_gpt":0.23166319506447763,"score_spread":0.18652345572705806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791664","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031691525,0.00003797226,0.049179833,0.000085618616,0.0002806141,0.00029803117,0.000052853535,0.00047655305,0.9495568],"genre_scores_gemma":[0.0013568568,0.00012882105,0.0009854675,0.00005002154,0.000052407835,0.0000012378057,0.000009809596,0.000025932944,0.99738944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866515,0.000029181698,0.00015829707,0.00061383646,0.0002433122,0.0002901945],"domain_scores_gemma":[0.99860436,0.00019094645,0.00012839623,0.0007039561,0.00019467434,0.0001776605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009984793,0.00026476092,0.00024568717,0.00024029627,0.0003161694,0.00017522494,0.0009705324,0.00022975812,0.0000015635803],"category_scores_gemma":[0.000027053451,0.00032014036,0.000087467444,0.00002398984,0.00026393408,0.0002946976,0.0011663085,0.0003647022,0.00011196927],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049283003,0.000004117426,8.009381e-7,0.000034003795,0.000031692227,0.0003411283,0.00009746532,0.0000049211517,0.000046508023,0.9913056,0.005095227,0.0030336333],"study_design_scores_gemma":[0.00017766799,0.00014459073,0.000023732991,0.00034276824,0.00009558913,0.000036045196,0.00006650147,0.0045977402,0.002311664,0.0021310146,0.98912156,0.0009511026],"about_ca_topic_score_codex":0.00017684349,"about_ca_topic_score_gemma":0.000010150471,"teacher_disagreement_score":0.98917454,"about_ca_system_score_codex":0.000102698636,"about_ca_system_score_gemma":0.00013848458,"threshold_uncertainty_score":0.9999251},"labels":[],"label_agreement":null},{"id":"W4385791668","doi":"10.1017/9781009258227.012","title":"Neural Networks and Deep Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Deep learning; Artificial intelligence; Code (set theory); Implementation; Artificial neural network; Data science; Software engineering; Programming language","score_opus":0.02987037628919012,"score_gpt":0.20667738438848268,"score_spread":0.17680700809929256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791668","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061252686,0.00021186397,0.10814958,0.000035317425,0.00056736637,0.00022710595,0.0000047561425,0.0006226855,0.8901201],"genre_scores_gemma":[0.004136224,0.00024983948,0.00025958632,0.000056682893,0.00013637987,6.297561e-7,0.000008814895,0.00004503662,0.9951068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836904,0.000059495414,0.00018253097,0.00071524986,0.0002472482,0.0004264378],"domain_scores_gemma":[0.99866724,0.00024461627,0.00017811063,0.0005655555,0.00013678076,0.000207673],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016212328,0.00032836528,0.00031724092,0.00021326228,0.0003953451,0.00020862115,0.0010247723,0.00030950943,0.0000013931484],"category_scores_gemma":[0.000026155483,0.00040891318,0.00012566698,0.000026288471,0.00021068435,0.0002743271,0.0014228426,0.00076575624,0.000032813216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011930431,0.0000021947549,0.0000035237592,0.000022530598,0.00004086369,0.0006958054,0.00009913579,0.0014701925,0.000005729683,0.97519064,0.0013572057,0.02110025],"study_design_scores_gemma":[0.0001457561,0.00010243582,0.00001978299,0.00009420677,0.00006234305,0.00003575343,0.00007468638,0.44804752,0.00009548669,0.000108292224,0.55052936,0.00068436767],"about_ca_topic_score_codex":0.00013785623,"about_ca_topic_score_gemma":0.000010161531,"teacher_disagreement_score":0.97508234,"about_ca_system_score_codex":0.000094977055,"about_ca_system_score_gemma":0.000031739033,"threshold_uncertainty_score":0.99983627},"labels":[],"label_agreement":null},{"id":"W4385791673","doi":"10.1017/9781009258227.020","title":"Representing Individuals and Relations","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Artificial intelligence; Space (punctuation); Data science; Software engineering; Programming language","score_opus":0.048957491137067,"score_gpt":0.2287306926827909,"score_spread":0.1797732015457239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791673","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000099681114,0.00006184821,0.018351695,0.0001069625,0.00031606865,0.0002766061,0.00004341517,0.00049527973,0.98024845],"genre_scores_gemma":[0.00081283716,0.00006756045,0.0013439744,0.00003540232,0.00007222335,8.606163e-7,0.000011916985,0.0000327094,0.9976225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983703,0.00004558132,0.00022488627,0.00072785607,0.0003123182,0.0003190461],"domain_scores_gemma":[0.9982469,0.0003520748,0.00022545659,0.0008590931,0.00015505213,0.0001614039],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002512529,0.0002570448,0.00026895202,0.00032952207,0.00041571425,0.0002065046,0.0009826288,0.0002790608,0.0000022298625],"category_scores_gemma":[0.00007490833,0.00032999393,0.00011168018,0.00003252209,0.00019389275,0.0003635112,0.0017187799,0.00043758226,0.00012496443],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002048223,0.0000026718703,0.000014424961,0.000019053894,0.000053436812,0.00022640574,0.00017885059,0.000012780783,0.000016769382,0.98170096,0.01571894,0.0020536326],"study_design_scores_gemma":[0.00013335847,0.00003366405,0.00008405299,0.00019335061,0.00008404786,0.000022119306,0.00009027231,0.002873314,0.0006542995,0.0013434968,0.99390024,0.0005877692],"about_ca_topic_score_codex":0.00017189473,"about_ca_topic_score_gemma":0.0000049059113,"teacher_disagreement_score":0.98035747,"about_ca_system_score_codex":0.00008995874,"about_ca_system_score_gemma":0.00009019271,"threshold_uncertainty_score":0.9999152},"labels":[],"label_agreement":null},{"id":"W4385830333","doi":"10.3138/utlj-2023-0003","title":"Explainability and the Epistemic Division of Labour in Adjudication","year":2023,"lang":"en","type":"article","venue":"University of Toronto Law Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Adjudication; Transparency (behavior); Perspective (graphical); Epistemology; Quality (philosophy); Division of labour; Sociology; Law; Law and economics; Positive economics; Political science; Philosophy; Economics; Computer science; Artificial intelligence","score_opus":0.010235642338196089,"score_gpt":0.2192349413401937,"score_spread":0.2089992990019976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385830333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9505436,0.00050551567,0.04086953,0.0034739054,0.00014387559,0.00016962418,0.0000025094723,0.000028615117,0.004262822],"genre_scores_gemma":[0.99835277,0.00038515247,0.0011176943,0.000014501584,0.000007708359,7.5413375e-8,2.1787845e-7,0.0000014835629,0.00012042723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992162,0.000187398,0.00016647774,0.00011654171,0.00018886793,0.00012449309],"domain_scores_gemma":[0.99924093,0.00019436484,0.00016566322,0.00021862159,0.00013612337,0.000044321336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012350848,0.000047904072,0.00013211457,0.00003519282,0.0002156952,0.000019921838,0.00055052317,0.00003255556,0.000037421443],"category_scores_gemma":[0.00007764046,0.00004112949,0.000045622895,0.00013506238,0.0002495813,0.0007153566,0.00022545528,0.00008909251,0.000003811437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009686512,0.00005491916,0.0052319984,0.000037607337,0.0000140155025,0.000024211677,0.0149010485,0.00047890982,0.0008152099,0.9557381,0.000120424935,0.022486692],"study_design_scores_gemma":[0.004521091,0.00055870373,0.4533634,0.00045328235,0.00003471177,0.00008469679,0.059330206,0.10732238,0.008276329,0.3525944,0.012916723,0.0005440852],"about_ca_topic_score_codex":0.026812155,"about_ca_topic_score_gemma":0.021175977,"teacher_disagreement_score":0.6031437,"about_ca_system_score_codex":0.00012851006,"about_ca_system_score_gemma":0.000035364887,"threshold_uncertainty_score":0.996685},"labels":[],"label_agreement":null},{"id":"W4385832544","doi":"10.1007/978-3-031-39821-6_6","title":"Explaining Decisions of Black-Box Models Using BARBE","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Debugging; Black box; Artificial intelligence; Inference; Machine learning; Classifier (UML); Programming language","score_opus":0.09758068534050314,"score_gpt":0.3086712252729021,"score_spread":0.21109053993239896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385832544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004382742,0.00015249437,0.9935304,0.0002271454,0.0017161488,0.0003758382,0.0000072185444,0.00024038464,0.0033120865],"genre_scores_gemma":[0.30610198,0.00010692345,0.6924583,0.00048486065,0.00033253487,0.0000073847377,0.0000031790617,0.00008631589,0.0004185312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946174,0.000054093474,0.001043982,0.0017966751,0.0015046685,0.0009831664],"domain_scores_gemma":[0.99475276,0.0018188745,0.00049243495,0.0021186452,0.00057002064,0.00024725831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015842513,0.0005924,0.0007727483,0.001704231,0.00036383566,0.00044854905,0.005052792,0.00039274307,0.000020159154],"category_scores_gemma":[0.00043881484,0.00058366754,0.00022724348,0.0018055453,0.0011577087,0.0013950383,0.002811837,0.0008226008,0.00009811613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045002275,0.000018823237,0.000006509983,0.00001915619,0.000010650906,0.00011504133,0.0022148213,0.733806,0.0007014671,0.13126987,0.000010640877,0.13182253],"study_design_scores_gemma":[0.00005252841,0.000067807094,0.0000027432252,0.000535708,0.0000057048214,0.000019253284,0.0000019674367,0.6301944,0.0056934026,0.36301994,0.000034163284,0.00037238223],"about_ca_topic_score_codex":0.00010501826,"about_ca_topic_score_gemma":0.00012497736,"teacher_disagreement_score":0.3056637,"about_ca_system_score_codex":0.00033414926,"about_ca_system_score_gemma":0.00092877087,"threshold_uncertainty_score":0.99966145},"labels":[],"label_agreement":null},{"id":"W4385895994","doi":"10.1017/9781009258227.031","title":"Index","year":2023,"lang":"en","type":"paratext","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Implementation; Code (set theory); Generative grammar; Artificial intelligence; Index (typography); Space (punctuation); Data science; Software engineering; Programming language","score_opus":0.03818936267099429,"score_gpt":0.24394467771592204,"score_spread":0.20575531504492775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385895994","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008804913,0.0000823024,0.1584788,0.000061400824,0.0037685963,0.00029852858,0.00008510376,0.0004426642,0.83669454],"genre_scores_gemma":[0.0014060969,0.00013444584,0.00039113313,0.00010265816,0.0002640511,0.0000028875565,0.000036674704,0.00004429687,0.9976178],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753076,0.00016996296,0.00024233798,0.0009442325,0.0004404695,0.00067224057],"domain_scores_gemma":[0.9976406,0.00022639413,0.0002224793,0.0014152469,0.000249281,0.00024596317],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001905772,0.00039170182,0.0004206454,0.0004324288,0.00034081616,0.00028839547,0.0034070446,0.0004389371,0.00001205616],"category_scores_gemma":[0.000040727013,0.0004829485,0.0002156435,0.00018580563,0.00017504011,0.00037007808,0.0019551697,0.0006499523,0.007733764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011035887,0.000012802472,6.5054735e-7,0.000056962373,0.000049297985,0.0003480037,0.00009282359,0.00013861214,0.00004280262,0.22701275,0.7705757,0.0016585671],"study_design_scores_gemma":[0.00011943426,0.000039440587,0.000009845592,0.000091855894,0.000019945099,0.00000818203,0.00009480958,0.006200149,0.0040861513,0.0000046283735,0.9888064,0.00051910256],"about_ca_topic_score_codex":0.0015770971,"about_ca_topic_score_gemma":0.0000093624685,"teacher_disagreement_score":0.22700812,"about_ca_system_score_codex":0.0002873036,"about_ca_system_score_gemma":0.00033039539,"threshold_uncertainty_score":0.99976224},"labels":[],"label_agreement":null},{"id":"W4385989212","doi":"10.1016/j.mlwa.2023.100491","title":"A novel application of XAI in squinting models: A position paper","year":2023,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Mistake; Process (computing); Automation; Field (mathematics); Risk analysis (engineering); Data science; Operations research; Machine learning; Engineering; Business","score_opus":0.019033226905915607,"score_gpt":0.264956386830006,"score_spread":0.2459231599240904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385989212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012990356,0.000036569538,0.98269755,0.0015986422,0.000009573721,0.0005395039,0.0000027899189,0.00037366338,0.0017513674],"genre_scores_gemma":[0.9512717,0.000011708499,0.047540706,0.000105422325,0.00002428894,0.0008541086,0.00004129184,0.000019146713,0.00013161544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869084,0.000044279146,0.00032531298,0.00042396208,0.00024214304,0.00027348875],"domain_scores_gemma":[0.9989852,0.00015218044,0.00018277117,0.0005009842,0.00012570487,0.000053162163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045552469,0.0001246518,0.00015039385,0.00030980373,0.00018714876,0.000058987433,0.00051508675,0.000053271422,0.000004645012],"category_scores_gemma":[0.000037242535,0.00012090557,0.00003503486,0.002385104,0.000047821348,0.000493432,0.00014938533,0.00025725574,0.000105792635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011640289,0.00016347472,0.0042420058,0.00004138443,0.000010518123,0.0000016876857,0.0016776164,0.4833764,0.04838508,0.410948,0.000014683533,0.0511275],"study_design_scores_gemma":[0.00013485522,0.000051061048,0.0022265434,0.000026034531,0.0000048593165,0.000008109327,0.0001586357,0.98126364,0.002315531,0.011983036,0.0016848611,0.00014283469],"about_ca_topic_score_codex":0.00096279685,"about_ca_topic_score_gemma":0.00030223737,"teacher_disagreement_score":0.93828136,"about_ca_system_score_codex":0.000053078802,"about_ca_system_score_gemma":0.000045307846,"threshold_uncertainty_score":0.49303862},"labels":[],"label_agreement":null},{"id":"W4386128184","doi":"10.14778/3611479.3611518","title":"POEM: Pattern-Oriented Explanations of Convolutional Neural Networks","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Poetry; Computer science; Artificial intelligence; Modular design; Classifier (UML); Image (mathematics); Meaning (existential); Pattern recognition (psychology); Deep learning; Artificial neural network; Machine learning; Psychology; Art; Literature","score_opus":0.023780839036322252,"score_gpt":0.24839148151546825,"score_spread":0.224610642479146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386128184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8711274,0.00019797316,0.10632136,0.011544553,0.0024604485,0.0013249279,0.000030036454,0.00051498774,0.006478276],"genre_scores_gemma":[0.99879414,0.00001982221,0.00064500724,0.00014051145,0.000058412374,0.00005100702,0.0000025641789,0.000007901973,0.00028065286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985599,0.000010486564,0.00038179703,0.00025581525,0.00048199864,0.00031001694],"domain_scores_gemma":[0.999042,0.00008548014,0.00025893605,0.00019167301,0.00036416634,0.000057788082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035097077,0.00011782238,0.00015503251,0.0001464782,0.0001437958,0.00003819859,0.0010292347,0.00004063396,0.000017262024],"category_scores_gemma":[0.00011009485,0.00009186282,0.00010559919,0.0011322688,0.00010221143,0.00035864324,0.0005516915,0.00011638079,0.000016115402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032432115,0.00037403195,0.03971645,0.00014964998,0.00013886412,0.0000039361375,0.0045387703,0.02076241,0.04004866,0.8507329,0.024949282,0.01855257],"study_design_scores_gemma":[0.00026198485,0.00013635527,0.012665882,0.00009023737,0.00001953987,0.0000114575,0.00090593996,0.8085448,0.16612725,0.009753057,0.0012645267,0.00021895856],"about_ca_topic_score_codex":0.00010542218,"about_ca_topic_score_gemma":0.000007408744,"teacher_disagreement_score":0.8409799,"about_ca_system_score_codex":0.000057438345,"about_ca_system_score_gemma":0.000026677393,"threshold_uncertainty_score":0.37460572},"labels":[],"label_agreement":null},{"id":"W4386189630","doi":"10.1007/978-3-030-95060-6_37-1","title":"Artificial Intelligence Techniques in Software Design for Mathematics Education","year":2023,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Focus (optics); Artificial intelligence; Software; State (computer science); Mathematics education; Programming language; Mathematics","score_opus":0.09821439107169437,"score_gpt":0.34249808439512225,"score_spread":0.24428369332342786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386189630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000417959,0.0001908653,0.9593769,0.0006214703,0.0036808006,0.001415421,0.000020124038,0.00022408072,0.034428563],"genre_scores_gemma":[0.005770263,0.00032909142,0.78604233,0.00023797904,0.001069632,0.0010742808,0.00013108696,0.00014989839,0.20519544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975562,0.00001755924,0.0010588912,0.000611772,0.000501667,0.0002539144],"domain_scores_gemma":[0.99713844,0.0004633269,0.00066611473,0.0006329344,0.0010255259,0.00007368357],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007405744,0.0003241179,0.00033498055,0.0011111137,0.00007376238,0.00016118301,0.0014625962,0.00028640218,0.000051899402],"category_scores_gemma":[0.00048725645,0.00037489223,0.00017021626,0.00012772798,0.00009590241,0.00043561734,0.00022172468,0.00025827982,0.00011039071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011497486,0.00018370616,0.000009892108,0.000101915364,0.000025321791,6.3348284e-7,0.00062983605,0.00007418686,0.00027963528,0.7065958,0.0008237428,0.29126382],"study_design_scores_gemma":[0.000013293377,0.000077873454,0.000012164114,0.0013924304,0.000017072207,0.00000432404,0.00015972804,0.002968916,0.08673368,0.90032566,0.00793975,0.00035513483],"about_ca_topic_score_codex":0.000081998594,"about_ca_topic_score_gemma":0.00008746092,"teacher_disagreement_score":0.2909087,"about_ca_system_score_codex":0.0004182247,"about_ca_system_score_gemma":0.0015072422,"threshold_uncertainty_score":0.9998703},"labels":[],"label_agreement":null},{"id":"W4386204668","doi":"10.1145/3603719.3603725","title":"InfoMoD: Information-theoretic Model Diagnostics","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Debugging; Data modeling; Data mining; Machine learning; Artificial intelligence; Software engineering; Programming language","score_opus":0.02157812953750826,"score_gpt":0.2580000841401901,"score_spread":0.23642195460268184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386204668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061158547,0.0000066040966,0.94745743,0.0018284188,0.00021484443,0.00013005744,0.0000020216164,0.0008573246,0.04338744],"genre_scores_gemma":[0.9611219,0.0001655494,0.03420551,0.0025057702,0.000037206286,0.00005324607,0.000011701625,0.000009348308,0.0018897312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894404,0.00001729677,0.0002699195,0.00014301894,0.00028632476,0.00033937924],"domain_scores_gemma":[0.9989187,0.0002691903,0.00004726875,0.0005249596,0.00014186601,0.00009800986],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003046401,0.00009978049,0.0000870113,0.00022141807,0.00013391425,0.00027615053,0.0008452993,0.000050695075,0.000044596218],"category_scores_gemma":[0.00045137477,0.00009112405,0.000039227587,0.0010081901,0.000051688192,0.0020454698,0.00035708104,0.00008727406,0.008488199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6365163e-7,0.0000074295667,0.000052987183,0.00000669141,0.0000023520051,0.000004224207,0.0014697133,0.049963225,0.000020912234,0.92505765,0.014844104,0.008570031],"study_design_scores_gemma":[0.000026640355,0.000017051465,0.00003786002,0.000004376487,0.0000011377563,0.0000016833885,0.0001497199,0.803579,0.004843209,0.18824875,0.002981529,0.0001090636],"about_ca_topic_score_codex":0.000027154509,"about_ca_topic_score_gemma":0.0000092625405,"teacher_disagreement_score":0.95500606,"about_ca_system_score_codex":0.000030089928,"about_ca_system_score_gemma":0.000087264845,"threshold_uncertainty_score":0.9922838},"labels":[],"label_agreement":null},{"id":"W4386391608","doi":"10.31235/osf.io/z3nqd","title":"Insights from the Folk Theories of Recommender System Users","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Recommender system; Folk psychology; Computer science; World Wide Web; Psychology; Cognitive science","score_opus":0.07106718127527077,"score_gpt":0.2860065383958087,"score_spread":0.2149393571205379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386391608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013826428,0.00039071872,0.9539108,0.005356125,0.005646215,0.00068130693,0.000027424452,0.0010141657,0.019146807],"genre_scores_gemma":[0.9883681,0.00004929793,0.0100674415,0.00029944305,0.00018398368,0.00008007895,0.000012856103,0.000027802118,0.0009110286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768174,0.0003252685,0.00059374527,0.0006940149,0.00044021424,0.0002650069],"domain_scores_gemma":[0.9958138,0.0013640666,0.00031645762,0.002216111,0.00022463012,0.0000649248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042439395,0.00026944128,0.00038815045,0.0001031976,0.00017184927,0.00033083116,0.0035132424,0.00022056914,0.000024750281],"category_scores_gemma":[0.0001421536,0.00017175224,0.00018511275,0.00039506835,0.00012208676,0.0002471838,0.0033394757,0.00043431896,0.00034568677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004455557,0.000017700562,0.000116180185,0.00005982136,0.000100631245,0.000012364407,0.00528911,0.0011299014,0.00008201681,0.9877313,0.004139338,0.0013172274],"study_design_scores_gemma":[0.000056529865,0.000039019684,0.00040072302,0.00047707683,0.000032569616,0.0000014290486,0.01418066,0.06781603,0.028946111,0.884998,0.0025906481,0.00046116507],"about_ca_topic_score_codex":0.0060883313,"about_ca_topic_score_gemma":0.0011124759,"teacher_disagreement_score":0.97454166,"about_ca_system_score_codex":0.00010971568,"about_ca_system_score_gemma":0.00017710116,"threshold_uncertainty_score":0.9203777},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02013936258471615,"score_gpt":0.31039423981865355,"score_spread":0.2902548772339374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386541762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047162406,0.00040952538,0.9491691,0.0007431004,0.00034859154,0.00009754326,2.2125964e-7,0.0005028075,0.0015667006],"genre_scores_gemma":[0.9882717,0.00007421849,0.011231184,0.00022073608,0.00009474174,0.000014667437,0.0000013017204,0.0000119805645,0.00007945375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988548,0.00005516624,0.00019818859,0.0003685712,0.0001493629,0.0003738688],"domain_scores_gemma":[0.9985998,0.00084994937,0.000059576254,0.00034267042,0.000063308165,0.000084639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036931637,0.00010131262,0.00010696737,0.0002108854,0.00039991774,0.0002488281,0.0004847988,0.000056084693,0.000011746691],"category_scores_gemma":[0.0004338955,0.00010131491,0.000039370887,0.0016849762,0.0000427525,0.00040535597,0.00046055287,0.00020139733,0.00014551099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020017383,0.0000090105605,0.011235342,0.000004146911,0.000006529651,0.000018179962,0.00031160284,0.018506655,0.000078007586,0.077201515,0.00038240603,0.8922446],"study_design_scores_gemma":[0.000024286956,0.000025463225,0.010938281,0.00001788339,0.0000024634937,0.000017036875,0.0002487126,0.9584803,0.00005779664,0.02897436,0.0010877586,0.00012563825],"about_ca_topic_score_codex":0.000011178736,"about_ca_topic_score_gemma":0.00001767981,"teacher_disagreement_score":0.9411093,"about_ca_system_score_codex":0.00002635011,"about_ca_system_score_gemma":0.000011948777,"threshold_uncertainty_score":0.4131502},"labels":[],"label_agreement":null},{"id":"W4386995089","doi":"10.1007/s10515-023-00399-5","title":"$$AI^{2}$$: the next leap toward native language-based and explainable machine learning framework","year":2023,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Process (computing); Chatbot; Interface (matter); Preprocessor; Natural language processing; Programming language","score_opus":0.02200965276098119,"score_gpt":0.2670099074727578,"score_spread":0.24500025471177664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386995089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08130719,0.0008383729,0.9038219,0.0018695915,0.00042777706,0.00027042167,0.000003572308,0.011432928,0.000028237546],"genre_scores_gemma":[0.9668425,0.00003857067,0.032302316,0.00046421876,0.000067180925,0.00007920248,0.000013036469,0.00005207521,0.00014094748],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982243,0.00008521937,0.00026364898,0.00044703015,0.00033485336,0.00064494635],"domain_scores_gemma":[0.99789697,0.0013463784,0.00007086161,0.00046755618,0.00009738434,0.00012082058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057663594,0.0002666114,0.00022362993,0.00027831018,0.00038144932,0.0004559091,0.0007351389,0.00013129372,0.000020424804],"category_scores_gemma":[0.0019366664,0.00022650238,0.000064719236,0.0017373575,0.000051748262,0.00066258886,0.00034055536,0.00061875535,0.00017257396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010460105,0.000037173682,0.0015808279,0.0002189021,0.000089794084,0.00045969427,0.021749167,0.9299604,0.0019449675,0.023056293,0.0010448459,0.019847441],"study_design_scores_gemma":[0.000081029786,0.000055628792,0.0007602031,0.00011095843,0.0000066120524,0.000011870427,0.0007174578,0.98688847,0.008443825,0.00046251735,0.0021780329,0.00028341118],"about_ca_topic_score_codex":0.00016713375,"about_ca_topic_score_gemma":0.00000573351,"teacher_disagreement_score":0.88553524,"about_ca_system_score_codex":0.00008125641,"about_ca_system_score_gemma":0.00006132987,"threshold_uncertainty_score":0.9236499},"labels":[],"label_agreement":null},{"id":"W4387100407","doi":"10.58190/icat.2023.28","title":"A Framework for Detecting AI-Generated Text in Research Publications","year":2023,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Advanced Technologies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Classifier (UML); Generative grammar; Artificial intelligence; Generative model; Source code; Cloud computing; Data science; Information retrieval; Natural language processing","score_opus":0.24824387876751006,"score_gpt":0.4371898901063391,"score_spread":0.18894601133882902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387100407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63529843,0.00006648282,0.08229165,0.26084238,0.0011105002,0.0021682624,0.000022654136,0.0040649287,0.014134712],"genre_scores_gemma":[0.95167464,0.00006734744,0.0472123,0.000074027856,0.000013241829,0.00052824325,9.404496e-7,0.000010293128,0.00041896573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982939,0.000008094477,0.00033258263,0.00045203877,0.00052315695,0.00039023196],"domain_scores_gemma":[0.9972809,0.0004492052,0.00018529894,0.00031258794,0.0017523834,0.000019643145],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00089015294,0.00012006597,0.00013896362,0.0009377829,0.00021807363,0.00027838553,0.0037533408,0.00013568228,0.0000053125523],"category_scores_gemma":[0.009724996,0.00009764535,0.000054505825,0.0031688975,0.00020866618,0.00069441885,0.0009597557,0.0005536667,0.000025862313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015247749,0.00003070065,0.00042309755,0.000010905263,0.000006498174,2.1050379e-7,0.00019208019,0.0001916836,0.066138975,0.8986082,0.0002885811,0.034093805],"study_design_scores_gemma":[0.000050673774,0.00005542602,0.00016482265,0.00013065929,4.6728584e-7,8.478009e-7,0.0023416711,0.045596577,0.37387234,0.5770101,0.00070587377,0.00007054873],"about_ca_topic_score_codex":0.000012941375,"about_ca_topic_score_gemma":0.000022695362,"teacher_disagreement_score":0.32159814,"about_ca_system_score_codex":0.00015440861,"about_ca_system_score_gemma":0.00009280488,"threshold_uncertainty_score":0.9986165},"labels":[],"label_agreement":null},{"id":"W4387211034","doi":"10.1007/978-3-031-43895-0_46","title":"A Flexible Framework for Simulating and Evaluating Biases in Deep Learning-Based Medical Image Analysis","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Computer science; Flexibility (engineering); Deep learning; Artificial intelligence; Machine learning; Modular design; Convolutional neural network; Generalization; Inductive bias; Data science; Multi-task learning","score_opus":0.07095669370079277,"score_gpt":0.37068318070971723,"score_spread":0.29972648700892446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387211034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092116813,0.00020571376,0.9965487,0.0009635888,0.0004480711,0.0005111293,0.0000022578968,0.0002760016,0.00012334986],"genre_scores_gemma":[0.2321415,0.000019884015,0.7665534,0.0008543171,0.00024210285,0.000041429168,0.000008741193,0.000048927806,0.00008970532],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99462384,0.00012267557,0.0008409175,0.0018468298,0.0015710176,0.0009946984],"domain_scores_gemma":[0.98698914,0.011140322,0.00036983064,0.0008809036,0.00036324267,0.00025657433],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004670706,0.00047843167,0.0007636704,0.0022218802,0.0004327795,0.00077498215,0.0022173405,0.0004700581,0.000034543402],"category_scores_gemma":[0.00991434,0.00047057765,0.00020629262,0.0032890013,0.0007081854,0.0005051556,0.0010949062,0.0012182916,0.000020110505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006791698,0.000014677119,0.00033389797,0.00003933702,0.000017778724,0.000061200946,0.00071379245,0.6928622,0.000024856918,0.008312373,3.6336218e-7,0.29761276],"study_design_scores_gemma":[0.00011623426,0.00019494935,0.00010976906,0.00061058206,0.000026248927,0.0000033465174,0.000001986006,0.8033789,0.000793763,0.19435315,0.000013072836,0.00039801837],"about_ca_topic_score_codex":0.00011219304,"about_ca_topic_score_gemma":0.0009344465,"teacher_disagreement_score":0.29721472,"about_ca_system_score_codex":0.000255956,"about_ca_system_score_gemma":0.0008036808,"threshold_uncertainty_score":0.9997746},"labels":[],"label_agreement":null},{"id":"W4387344795","doi":"10.1145/3610206","title":"Selective Explanations: Leveraging Human Input to Align Explainable AI","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":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"Universitas Brawijaya; National Science Foundation","keywords":"Task (project management); Computer science; Space (punctuation); Perception; Artificial intelligence; Property (philosophy); Ask price; Machine learning; Data science; Psychology; Epistemology; Management","score_opus":0.08774926588927132,"score_gpt":0.3596719010079191,"score_spread":0.2719226351186478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387344795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520858,0.0000064492656,0.028112093,0.010333915,0.0019023967,0.0010918011,0.0000026692232,0.00097549363,0.005489381],"genre_scores_gemma":[0.99060243,0.000002682652,0.006146828,0.0016550925,0.00038839845,0.00015962883,0.0000035806333,0.000035674064,0.0010057007],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99732053,0.000038747872,0.00060934975,0.00080824684,0.0006540682,0.0005690298],"domain_scores_gemma":[0.9976461,0.00019795915,0.000380404,0.00087076,0.0007881636,0.000116606076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074103585,0.00030885593,0.00030306733,0.0009010208,0.0008769627,0.0005903839,0.003858783,0.00009459078,0.000018683242],"category_scores_gemma":[0.00041356313,0.00027474022,0.0001719258,0.0020507602,0.000050714003,0.0021481088,0.0019812225,0.00044222592,0.00032462738],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010093765,0.0006450389,0.0025286668,0.00027839435,0.00024835634,0.000014844136,0.040613253,0.013166274,0.33294502,0.29846498,0.28251722,0.028476996],"study_design_scores_gemma":[0.00028477443,0.000718366,0.004122139,0.00059539103,0.000019150955,0.000028042637,0.0016496483,0.034839157,0.82003385,0.13047044,0.0066055264,0.00063351955],"about_ca_topic_score_codex":0.00018765638,"about_ca_topic_score_gemma":0.000022316717,"teacher_disagreement_score":0.48708883,"about_ca_system_score_codex":0.00038246077,"about_ca_system_score_gemma":0.000034730278,"threshold_uncertainty_score":0.9999705},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10995152306595299,"score_gpt":0.36186354424247574,"score_spread":0.2519120211765228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387344906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649375,0.0000061819765,0.028677985,0.0016695004,0.00046396008,0.00054091495,0.0000018215388,0.00018275918,0.0035193858],"genre_scores_gemma":[0.9981757,0.00000382307,0.0013803061,0.00021756781,0.00012081358,0.00004489831,0.0000016924348,0.000021847596,0.000033362365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794406,0.000034153898,0.00058762106,0.00049147627,0.0006370809,0.00030561019],"domain_scores_gemma":[0.99790245,0.00049429544,0.0005735767,0.00071527745,0.00028310335,0.000031272008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006918367,0.0002136259,0.00023519646,0.0006921429,0.0006167041,0.00025927558,0.002475822,0.0000755352,0.000011565045],"category_scores_gemma":[0.00022864573,0.00014716617,0.0001052547,0.0014457153,0.00011455869,0.0011312788,0.00068817264,0.00046572427,0.000020943207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012473224,0.0003395282,0.002780783,0.00007424364,0.000055308094,0.0000041438193,0.011721855,0.015634058,0.0721806,0.8816594,0.0033673237,0.012058023],"study_design_scores_gemma":[0.00030063238,0.0009948004,0.0064091412,0.00310122,0.00001588563,0.000014018984,0.0041084667,0.06990027,0.1677325,0.74691427,0.00017217577,0.000336596],"about_ca_topic_score_codex":0.00006293996,"about_ca_topic_score_gemma":0.00009274853,"teacher_disagreement_score":0.1347451,"about_ca_system_score_codex":0.0003738685,"about_ca_system_score_gemma":0.000019854837,"threshold_uncertainty_score":0.6001262},"labels":[],"label_agreement":null},{"id":"W4387415063","doi":"10.1109/mnet.2023.3321539","title":"A Unified Framework for Integrating Semantic Communication and AI-Generated Content in Metaverse","year":2023,"lang":"en","type":"article","venue":"IEEE Network","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Metaverse; World Wide Web; Human–computer interaction; Virtual reality","score_opus":0.09721548394303664,"score_gpt":0.3207714402264902,"score_spread":0.22355595628345354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387415063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18486017,0.00037654754,0.8080555,0.0033322228,0.0019168598,0.00079143554,0.0000020727405,0.0003977261,0.00026743693],"genre_scores_gemma":[0.9478908,0.00012656221,0.05033781,0.0010092934,0.00028533192,0.00012605664,0.000009113374,0.000016895541,0.00019814965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862576,0.00017641859,0.00033822912,0.00031920377,0.0001280562,0.00041236545],"domain_scores_gemma":[0.9983854,0.0007758339,0.00008423778,0.0005567962,0.00013129185,0.000066417226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010138382,0.00013363795,0.0002092423,0.00011539036,0.00022821568,0.00020059089,0.00054810586,0.00010240716,0.0000023141708],"category_scores_gemma":[0.00025654692,0.0001292186,0.000043738415,0.0012880006,0.00005705242,0.00025580186,0.00014438106,0.00024809712,0.000046397065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008899344,0.00008686343,0.0019049882,0.000061774794,0.00007254564,0.000039954135,0.0066097947,0.14483832,0.002553939,0.8042055,0.0171108,0.022426521],"study_design_scores_gemma":[0.00017123636,0.00007746338,0.00059648376,0.00023317468,0.000009648821,0.0000029724195,0.00068311905,0.7895406,0.004498096,0.20143901,0.0025198536,0.00022836028],"about_ca_topic_score_codex":0.00038480593,"about_ca_topic_score_gemma":0.0011083008,"teacher_disagreement_score":0.76303065,"about_ca_system_score_codex":0.00004647722,"about_ca_system_score_gemma":0.00004027732,"threshold_uncertainty_score":0.5269382},"labels":[],"label_agreement":null},{"id":"W4387435262","doi":"10.1007/978-3-031-45249-9_20","title":"Studying the Effects of Sex-Related Differences on Brain Age Prediction Using Brain MR Imaging","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Interpretability; Generalizability theory; Machine learning; Artificial intelligence; Computer science; Neuroimaging; Demographics; Generalization; Context (archaeology); Affect (linguistics); Psychology; Developmental psychology; Demography; Neuroscience","score_opus":0.031474972007579836,"score_gpt":0.2700527544772534,"score_spread":0.23857778246967357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387435262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009447853,0.00018899262,0.9828943,0.0019425142,0.0037425954,0.000881625,0.0000038527974,0.00030999992,0.00058826036],"genre_scores_gemma":[0.97803897,0.000032847285,0.018305616,0.0022740576,0.00042243197,0.00002267529,0.0000038894736,0.00008089337,0.0008186271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952884,0.00020232308,0.0007939441,0.0015215186,0.0014110447,0.00078280416],"domain_scores_gemma":[0.99080735,0.0069531077,0.00048153507,0.0014529526,0.00018779794,0.00011727814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020504347,0.00056575116,0.00060395553,0.0010158282,0.0006099915,0.00060178956,0.0036496285,0.00022789996,0.0000047019466],"category_scores_gemma":[0.0011141042,0.00043266412,0.00016910385,0.0014582915,0.0010754579,0.0006097405,0.0014494039,0.0010343299,0.000026471134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013828603,0.000114234754,0.0009025146,0.000266134,0.000079422076,0.000689177,0.019945223,0.12090427,0.013167831,0.044509094,0.000084364256,0.7993239],"study_design_scores_gemma":[0.00015210346,0.00031629455,0.00052671495,0.0014489415,0.00001434789,0.000031018662,0.00000744667,0.843465,0.011067812,0.1424344,0.000054747543,0.00048119016],"about_ca_topic_score_codex":0.00013434282,"about_ca_topic_score_gemma":0.00006829414,"teacher_disagreement_score":0.9685911,"about_ca_system_score_codex":0.00030390074,"about_ca_system_score_gemma":0.00030763113,"threshold_uncertainty_score":0.99981254},"labels":[],"label_agreement":null},{"id":"W4387538577","doi":"10.20378/irb-89771","title":"Human-centered Interactions with Text Classifiers : Fusing Concept-based Knowledge with Local Surrogate Explanation Models","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Artificial intelligence; Action (physics); Comprehension; Context (archaeology); TRACE (psycholinguistics); Domain (mathematical analysis); Audit; Black box; Domain knowledge; Order (exchange); Machine learning; Data science; Knowledge management","score_opus":0.07759488985227153,"score_gpt":0.33039934263024634,"score_spread":0.2528044527779748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387538577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020487728,0.000048941,0.94440454,0.00023888522,0.0010759664,0.00069679366,0.0000102907325,0.0009376788,0.032099184],"genre_scores_gemma":[0.9735637,0.000005055427,0.0047813696,0.00009618373,0.00008094774,0.00016621454,0.00069579965,0.00009904853,0.020511717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970887,0.00014212441,0.0005709807,0.0010223904,0.0005760154,0.00059982593],"domain_scores_gemma":[0.9976434,0.0002030502,0.00040393928,0.00076619134,0.00079360174,0.00018982132],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023024534,0.0005185829,0.00043735307,0.0006910488,0.00055873685,0.00052846735,0.00092168833,0.00021501056,0.000102887374],"category_scores_gemma":[0.000018798306,0.00043384335,0.0001128691,0.0012819308,0.00014596414,0.0014344681,0.00006090488,0.0005514848,0.00026011968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009855541,0.0016517577,0.00011675683,0.00080427073,0.0008226307,0.0005853294,0.05555864,0.4216374,0.0037033735,0.36058763,0.013324995,0.14022166],"study_design_scores_gemma":[0.0006460562,0.00047676993,0.000121729616,0.0010970774,0.000077112185,0.0000113284095,0.025208741,0.9419043,0.026949042,0.0018075057,0.00067501655,0.0010253204],"about_ca_topic_score_codex":0.0009829077,"about_ca_topic_score_gemma":0.039220117,"teacher_disagreement_score":0.95307595,"about_ca_system_score_codex":0.00042919477,"about_ca_system_score_gemma":0.0006392491,"threshold_uncertainty_score":0.99981135},"labels":[],"label_agreement":null},{"id":"W4387592307","doi":"10.1017/9781316718636.021","title":"Evaluating Models","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Figuring; Harm; Computer science; Psychology; Social psychology; Physics","score_opus":0.15642113633639307,"score_gpt":0.28386412098006913,"score_spread":0.12744298464367607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387592307","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020147669,0.0000431894,0.11779259,0.000036769077,0.000603991,0.00033813354,0.000035228655,0.0007288105,0.88040113],"genre_scores_gemma":[0.00037286317,0.000056123095,0.0031782063,0.00006587321,0.00011831281,0.0000014240798,0.000011473206,0.000057836784,0.9961379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764407,0.000063732856,0.00027619474,0.00091970444,0.0006134326,0.00048287294],"domain_scores_gemma":[0.9976228,0.0002651526,0.00025645562,0.0012975824,0.0003526111,0.00020538688],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037816245,0.0003899773,0.00038074853,0.00032100664,0.0003441991,0.00018186335,0.0022023295,0.00033810726,0.0000025131123],"category_scores_gemma":[0.000037573347,0.000493056,0.00023807655,0.00003228296,0.00015658913,0.00048623106,0.0016649521,0.0005222971,0.0002676639],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010639095,0.00000430169,5.4713762e-8,0.000034091183,0.000054519278,0.00040220286,0.00013971892,0.0009423413,0.00005640125,0.98173386,0.008749619,0.007872282],"study_design_scores_gemma":[0.00032230798,0.00020603147,0.000001153992,0.00043858806,0.00015432085,0.000027308739,0.00009350455,0.42524046,0.0027046483,0.007494173,0.5618094,0.0015080523],"about_ca_topic_score_codex":0.00022262508,"about_ca_topic_score_gemma":0.0000051310712,"teacher_disagreement_score":0.97423965,"about_ca_system_score_codex":0.00026520755,"about_ca_system_score_gemma":0.0002351054,"threshold_uncertainty_score":0.9997521},"labels":[],"label_agreement":null},{"id":"W4387640553","doi":"10.1007/978-3-031-45676-3_23","title":"Is Visual Explanation with Grad-CAM More Reliable for Deeper Neural Networks? A Case Study with Automatic Pneumothorax Diagnosis","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning; Robustness (evolution); SAFER; Artificial neural network; Popularity; Convolutional neural network; Flexibility (engineering)","score_opus":0.034408357935175236,"score_gpt":0.302627817131459,"score_spread":0.26821945919628376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387640553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020571243,0.00007775681,0.9744664,0.0011206521,0.0008636715,0.0023759913,0.000005741285,0.00047765693,0.000040877014],"genre_scores_gemma":[0.8142014,0.000018603476,0.1825216,0.001834517,0.00038541257,0.0006112688,0.000010124474,0.00014723597,0.0002698586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945468,0.00005823584,0.00071937597,0.0022249706,0.0013512014,0.0010994598],"domain_scores_gemma":[0.99596167,0.0012674374,0.00044855403,0.0014540191,0.0006107881,0.00025756186],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011035276,0.0007929938,0.0007339209,0.0010135095,0.0007409193,0.0012736195,0.0022379414,0.0002536689,0.0000097796155],"category_scores_gemma":[0.0000898045,0.0006197572,0.00012069943,0.0018759554,0.0005383537,0.0013804396,0.0007341072,0.00069010357,0.000020130341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048781778,0.00027964142,0.0030173822,0.00011211856,0.000081091675,0.005167395,0.008943087,0.6283563,0.0000042818756,0.0020485753,0.000094176394,0.35184717],"study_design_scores_gemma":[0.00030503012,0.0023599712,0.0001004648,0.00037390427,0.000044679873,0.0008825938,0.00003878083,0.98688024,0.00026808056,0.007851768,0.000059952854,0.0008345219],"about_ca_topic_score_codex":0.00039035495,"about_ca_topic_score_gemma":0.002183184,"teacher_disagreement_score":0.7936301,"about_ca_system_score_codex":0.00033510136,"about_ca_system_score_gemma":0.00038398115,"threshold_uncertainty_score":0.99976313},"labels":[],"label_agreement":null},{"id":"W4387680963","doi":"10.1007/978-3-031-23265-7","title":"Stewards of the Grasslands","year":2023,"lang":"en","type":"book","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Liber Ero Foundation; Alberta Conservation Association","keywords":"Environmental science","score_opus":0.02933717939951166,"score_gpt":0.2506820931133792,"score_spread":0.22134491371386752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387680963","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016593018,0.00005309427,0.048442226,0.00071647833,0.0014988976,0.00021227532,0.000006094874,0.0002431937,0.9488112],"genre_scores_gemma":[0.000987807,0.000024234527,0.00074765045,0.00014898596,0.000103238235,0.000008216917,0.0000020399011,0.000020703023,0.9979571],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985817,0.000037935126,0.00031424442,0.00032605673,0.00050680997,0.00023327582],"domain_scores_gemma":[0.99818796,0.00017634727,0.00016970577,0.0012797052,0.00014341864,0.00004286358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003234065,0.00016334098,0.00022999739,0.00010880636,0.000076192766,0.00006771238,0.002583076,0.00016442737,0.00006708316],"category_scores_gemma":[0.00006763707,0.00010406408,0.00018757241,0.00035331133,0.00009506272,0.00012484982,0.00090768945,0.00023254327,0.0007034862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.834899e-7,0.000010806153,0.000016664506,0.000039664443,0.000025446207,0.000009038659,0.00025574805,0.000056787463,0.000049910435,0.7429647,0.2486564,0.007914074],"study_design_scores_gemma":[0.000054435124,0.00010704472,0.00011140323,0.0002440916,0.000022408267,0.000007420821,0.000056425568,0.00686829,0.022862526,0.5694235,0.39977255,0.00046992055],"about_ca_topic_score_codex":0.00006105283,"about_ca_topic_score_gemma":0.00015420989,"teacher_disagreement_score":0.17354119,"about_ca_system_score_codex":0.00007821796,"about_ca_system_score_gemma":0.0005062623,"threshold_uncertainty_score":0.9042127},"labels":[],"label_agreement":null},{"id":"W4387838655","doi":"10.48550/arxiv.2310.12568","title":"Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Deutsche Forschungsgemeinschaft; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Python (programming language); Computer science; Pipeline (software); Generalization; Artificial intelligence; Open source; Machine learning; Software engineering; Data science; Data mining; Software; Programming language","score_opus":0.2567715085980189,"score_gpt":0.24974215428597896,"score_spread":0.007029354312039937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387838655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28015292,0.000015623977,0.7175551,0.00018452387,0.00037612257,0.00081027474,0.00003146279,0.00049390865,0.00038007327],"genre_scores_gemma":[0.9863548,0.000102188715,0.012135147,0.00006997949,0.00006296511,0.000008477361,0.000033979675,0.000040284696,0.0011921251],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979803,0.00019900293,0.0002580948,0.0011057964,0.00016953736,0.00028724363],"domain_scores_gemma":[0.99755657,0.00021084421,0.00022646473,0.0014651757,0.00035940766,0.00018151228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005893502,0.00022753938,0.00027038204,0.0005482161,0.00018031117,0.00022524576,0.0014728494,0.00022535535,0.0000083701125],"category_scores_gemma":[0.0002106594,0.00028601324,0.000110626075,0.00081052753,0.00008723947,0.0028340535,0.0020056572,0.0002497287,0.000024994828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006563578,0.00007062444,0.0005147119,0.00007256067,0.000035744797,0.000015999281,0.00080218236,0.70253843,0.00014061737,0.29351127,0.0005637215,0.0016684945],"study_design_scores_gemma":[0.00013269513,0.00012452216,0.000573065,0.00004964391,0.000034509056,6.3194295e-7,0.00016676389,0.6675481,0.0014600985,0.32963142,0.00008477969,0.00019378887],"about_ca_topic_score_codex":0.00043523664,"about_ca_topic_score_gemma":0.00020067704,"teacher_disagreement_score":0.706202,"about_ca_system_score_codex":0.00012195942,"about_ca_system_score_gemma":0.00023633953,"threshold_uncertainty_score":0.99995923},"labels":[],"label_agreement":null},{"id":"W4387839040","doi":"10.48550/arxiv.2310.12805","title":"Detection and Evaluation of bias-inducing Features in Machine learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Computer science; Identification (biology); Machine learning; Artificial intelligence; Context (archaeology); Harm; Feature (linguistics); Outcome (game theory); Psychology; Social psychology; Mathematics","score_opus":0.2072066899680573,"score_gpt":0.24888457049334442,"score_spread":0.04167788052528712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387839040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8735677,0.000108426735,0.1252911,0.00005042571,0.0002870443,0.00025391503,0.0000013741776,0.000119707875,0.0003203033],"genre_scores_gemma":[0.9992417,0.00014415458,0.00029218802,0.000007672643,0.000021518126,0.0000013803127,0.0000036358438,0.000011489482,0.00027623662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983107,0.0004267837,0.00019437615,0.0006976232,0.00016561693,0.0002049008],"domain_scores_gemma":[0.99882716,0.00020293838,0.0002380882,0.00044765844,0.00023229163,0.000051836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016889531,0.00016033977,0.00021138233,0.00058458175,0.000102089005,0.00006750453,0.0005079503,0.00018771869,0.0000056841877],"category_scores_gemma":[0.00039875548,0.00019414522,0.00006238904,0.0008795535,0.000051566152,0.0003335591,0.0009169592,0.00057224993,0.000014531088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149490925,0.000026469908,0.0092659015,0.000062226696,0.000021826094,0.00004301604,0.0011123965,0.9674413,0.0010919917,0.007908217,0.0000035699475,0.013008101],"study_design_scores_gemma":[0.0001289165,0.000039794457,0.01153976,0.000113503884,0.000029909175,0.0000019319523,0.00031695658,0.94960845,0.007603354,0.030438017,0.000009469341,0.00016992578],"about_ca_topic_score_codex":0.0033478863,"about_ca_topic_score_gemma":0.0034901253,"teacher_disagreement_score":0.12567401,"about_ca_system_score_codex":0.00022791198,"about_ca_system_score_gemma":0.00011546635,"threshold_uncertainty_score":0.79170126},"labels":[],"label_agreement":null},{"id":"W4387918213","doi":"10.1007/978-3-031-44505-7_8","title":"Explaining the Behavior of Reinforcement Learning Agents Using Association Rules","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Association rule learning; Lift (data mining); Artificial intelligence; Learning classifier system; Process (computing); Machine learning; Association (psychology); Reinforcement","score_opus":0.061392412825267466,"score_gpt":0.3017173438229634,"score_spread":0.24032493099769592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387918213","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024597826,0.00006168049,0.99380034,0.00020099067,0.0016217255,0.0005156033,0.0000014451666,0.00014191968,0.001196511],"genre_scores_gemma":[0.86041445,0.000107386455,0.13528991,0.0006288311,0.00057997403,0.00006459368,0.000010746014,0.000091524984,0.0028125634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960647,0.000077636556,0.00074128667,0.00088826177,0.0015413637,0.00068672816],"domain_scores_gemma":[0.9968283,0.0009694513,0.0008196232,0.0009034905,0.00039298713,0.00008612705],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023771652,0.0003638296,0.00041488753,0.0006393096,0.00055069855,0.00044711807,0.0027750067,0.00025243592,0.00001981711],"category_scores_gemma":[0.00047234417,0.0003065933,0.00014638495,0.00078703207,0.0003111484,0.0006357455,0.0015492648,0.00082871766,0.00007163629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030875383,0.000016677024,0.0006984904,0.000027330316,0.000020341535,0.000053760672,0.0035670083,0.7786071,0.00074367743,0.024944182,0.000009256164,0.19130912],"study_design_scores_gemma":[0.00007142195,0.00011712795,0.0002159552,0.00037676844,0.000019795469,0.000010361429,0.000005220057,0.97045255,0.007383419,0.020650903,0.00030345455,0.0003930068],"about_ca_topic_score_codex":0.00013964598,"about_ca_topic_score_gemma":0.000060463164,"teacher_disagreement_score":0.85851043,"about_ca_system_score_codex":0.00073270826,"about_ca_system_score_gemma":0.00038646447,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W4387966050","doi":"10.1038/s42003-023-05456-z","title":"Biological age estimation using circulating blood biomarkers","year":2023,"lang":"en","type":"article","venue":"Communications Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"Medical Research Council; Foreign, Commonwealth and Development Office; Public Health England; Imperial College London; National Institute for Health and Care Research; National Institute for Health Research Health Protection Research Unit","keywords":"Biological age; Biobank; Biomarker; Population; Medicine; Frailty Index; Statistics; Internal medicine; Bioinformatics; Biology; Gerontology; Mathematics","score_opus":0.24715111388321376,"score_gpt":0.3979638015888823,"score_spread":0.15081268770566852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387966050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.364071,0.00042620228,0.6284008,0.002654788,0.0002814792,0.0003114471,0.0000055863366,0.0010455053,0.0028031452],"genre_scores_gemma":[0.8381024,0.00011266154,0.16153684,0.00011766019,0.000016172273,0.000029915253,0.00006460616,0.00000652316,0.000013221854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985596,0.00039421045,0.00033711654,0.00031178215,0.000061043414,0.0003362383],"domain_scores_gemma":[0.997131,0.00064272963,0.00012403086,0.0019577013,0.000085415624,0.000059112932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006849368,0.00011452761,0.00014994774,0.00025598484,0.00055250246,0.00008324245,0.002296129,0.0001328441,0.000010381119],"category_scores_gemma":[0.0005363294,0.0001093418,0.00006082593,0.0014628858,0.00033698964,0.00022763936,0.0013739106,0.00015331703,0.00026879006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030827755,0.00015996619,0.008709965,0.000009967635,0.00009500597,0.000028285165,0.0012713898,0.0030158334,0.17782255,0.7180587,0.00013781522,0.09068743],"study_design_scores_gemma":[0.00006974306,0.000049792714,0.0015741162,0.00001475206,0.0000083069635,0.000029093011,0.00016577943,0.93375814,0.0031728724,0.05988435,0.001091995,0.00018107062],"about_ca_topic_score_codex":0.00011955203,"about_ca_topic_score_gemma":0.000023276145,"teacher_disagreement_score":0.9307423,"about_ca_system_score_codex":0.000043359032,"about_ca_system_score_gemma":0.00005224222,"threshold_uncertainty_score":0.44588292},"labels":[],"label_agreement":null},{"id":"W4388039953","doi":"10.1109/imeta59369.2023.10294907","title":"Explainable AI for the Metaverse: A Short Survey","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Metaverse; Computer science; Context (archaeology); Transparency (behavior); Possible world; Human–computer interaction; Data science; Key (lock); Virtual reality; World Wide Web; Epistemology","score_opus":0.12200148415486552,"score_gpt":0.3502298249992334,"score_spread":0.22822834084436788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388039953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026814481,0.000044108405,0.98691714,0.004940661,0.0007005294,0.00058835844,0.0000064179344,0.00059406727,0.0035272518],"genre_scores_gemma":[0.95777375,0.0000628128,0.008719663,0.0026162579,0.00013149908,0.00043836108,0.000015018548,0.000029838946,0.030212784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838287,0.000098487144,0.0002369825,0.00041184286,0.000292788,0.00057703274],"domain_scores_gemma":[0.9971686,0.0015903794,0.000027060692,0.0008835763,0.0002479417,0.000082432576],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025733905,0.00013562576,0.0001496512,0.0001197814,0.00047072725,0.00034657138,0.0015037287,0.000050149283,0.00007919266],"category_scores_gemma":[0.00049724494,0.00009107544,0.0001041302,0.0015285196,0.000057349276,0.00066890346,0.00037198747,0.000101478945,0.001111041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027704476,0.000068926136,0.0016494697,0.000022615133,0.00010207427,0.0000341576,0.0015263043,0.0061547654,0.0006461806,0.6184428,0.31953257,0.05179248],"study_design_scores_gemma":[0.00009016216,0.00011727314,0.0039735264,0.0000056020417,0.0000125564675,0.000006188898,0.0010391802,0.7354407,0.037089217,0.021552563,0.20032819,0.00034489445],"about_ca_topic_score_codex":0.0009522195,"about_ca_topic_score_gemma":0.0010617126,"teacher_disagreement_score":0.9781975,"about_ca_system_score_codex":0.000038422084,"about_ca_system_score_gemma":0.00009309985,"threshold_uncertainty_score":0.9996667},"labels":[],"label_agreement":null},{"id":"W4388134641","doi":"10.1007/978-981-99-3814-8_16","title":"Evolutionary Approaches to Explainable Machine Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; XML; Artificial intelligence; Field (mathematics); Trustworthiness; Machine learning; Data science; World Wide Web; Computer security","score_opus":0.09228201504910044,"score_gpt":0.23841051330053953,"score_spread":0.1461284982514391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388134641","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003167916,0.0040073316,0.9279321,0.0019614638,0.0007555415,0.0008145651,0.00002381102,0.0007802411,0.06340818],"genre_scores_gemma":[0.070482455,0.0011885259,0.2793613,0.0004610626,0.00088089885,0.00019350972,0.00058435457,0.00022817928,0.64661974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973726,0.000075851276,0.00052065944,0.0009920264,0.0005617731,0.00047709123],"domain_scores_gemma":[0.99880165,0.00021307188,0.00019929797,0.0003713077,0.00017512038,0.0002395381],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026656513,0.0004142937,0.00034395442,0.0005426314,0.000645455,0.00014188503,0.0004972226,0.00026223547,0.00004052214],"category_scores_gemma":[0.000052179734,0.0004745688,0.00010665452,0.00027145114,0.00011078891,0.00032121214,0.0006741413,0.00038916935,0.0012885974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028295735,0.000042064912,0.00015890964,0.00010859827,0.000094298324,0.0001000733,0.0010052379,0.3936256,0.00001700801,0.5121374,0.009520234,0.0831623],"study_design_scores_gemma":[0.00009951234,0.0002669432,0.002014631,0.000097031254,0.000026418882,0.00009178629,0.000070744216,0.65210927,0.00000943472,0.30500957,0.039610952,0.0005936906],"about_ca_topic_score_codex":0.00007712299,"about_ca_topic_score_gemma":0.000014718956,"teacher_disagreement_score":0.6485708,"about_ca_system_score_codex":0.00023464588,"about_ca_system_score_gemma":0.00018683886,"threshold_uncertainty_score":0.9997706},"labels":[],"label_agreement":null},{"id":"W4388446603","doi":"10.5206/cjils-rcsib.v46i2.15723","title":"Using folk theories of recommender systems to inform human-centered explainable AI (HCXAI)","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Recommender system; Computer science; Folk psychology; Psychology; Cognitive science; World Wide Web","score_opus":0.05464557464243531,"score_gpt":0.29073572040931617,"score_spread":0.23609014576688087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388446603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7672893,0.00019020127,0.19854057,0.00909723,0.0028223637,0.0006020525,0.000031757543,0.00011022445,0.021316292],"genre_scores_gemma":[0.99546343,0.000012379745,0.0032896816,0.0010535173,0.000029195216,0.00000159247,0.0000017490621,0.0000035553317,0.00014489895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852294,0.00002690693,0.0006473293,0.000089386835,0.00032938315,0.00038404673],"domain_scores_gemma":[0.99850845,0.000044609224,0.0003240519,0.00020955187,0.00031403435,0.0005992996],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0010398238,0.000094518364,0.00015971008,0.0015704986,0.0005917456,0.0011497029,0.0010625708,0.00003531316,0.000031498763],"category_scores_gemma":[0.00016845646,0.00008314769,0.000034865523,0.00276902,0.0001990148,0.02041671,0.00013783517,0.00011433658,0.00002393513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010046436,0.0000062463173,0.0031251232,0.00008664082,0.000011358976,0.000020441044,0.022379566,0.009374191,0.0007154502,0.94291896,0.0064306906,0.014921315],"study_design_scores_gemma":[0.0010432408,0.0015255907,0.013474893,0.0013978955,0.000020128857,0.00068752054,0.08596666,0.39967167,0.062164497,0.057396933,0.3751854,0.0014655718],"about_ca_topic_score_codex":0.00085792056,"about_ca_topic_score_gemma":0.00011284958,"teacher_disagreement_score":0.885522,"about_ca_system_score_codex":0.000076994766,"about_ca_system_score_gemma":0.0015946052,"threshold_uncertainty_score":0.9998872},"labels":[],"label_agreement":null},{"id":"W4388694426","doi":"10.1007/978-3-031-47958-8_9","title":"Designing Explainable Artificial Intelligence with Active Inference: A Framework for Transparent Introspection and Decision-Making","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; HEC Montréal","funders":"","keywords":"Introspection; Computer science; Inference; Artificial intelligence; Covert; Machine learning; Cognitive science; Psychology","score_opus":0.10643249706039275,"score_gpt":0.364949812949029,"score_spread":0.25851731588863625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388694426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000106157815,0.00008279967,0.9946224,0.0003605007,0.00026526817,0.0007833878,0.000010335321,0.00014880874,0.003620322],"genre_scores_gemma":[0.1730718,0.0011640298,0.82528895,0.00019094284,0.000044861965,0.00016281675,0.000011686504,0.00001670012,0.000048220583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997782,0.000026300535,0.0007941258,0.00050639646,0.00050159934,0.00038957485],"domain_scores_gemma":[0.99527735,0.002258,0.00039800946,0.0013388612,0.00061421975,0.00011357677],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012763735,0.0002917181,0.00032406766,0.0011711972,0.0010880496,0.001246446,0.0021124335,0.00017915624,0.000004207164],"category_scores_gemma":[0.00032711655,0.0002812919,0.000041267347,0.0009257035,0.0008852325,0.00673065,0.0011063673,0.0005379262,0.000022579785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014515218,0.00000804847,0.000006022107,0.000020455116,0.000004230347,4.4895427e-7,0.0035674768,0.0022769577,0.0000020755913,0.57615906,0.0000026681012,0.41793802],"study_design_scores_gemma":[0.000036569716,0.00015030056,0.00009205118,0.0008579226,0.0000064776827,0.000009678047,0.00041819422,0.44912812,0.00016012724,0.5483702,0.00049934536,0.00027101955],"about_ca_topic_score_codex":0.000012995903,"about_ca_topic_score_gemma":0.000065919994,"teacher_disagreement_score":0.44685116,"about_ca_system_score_codex":0.00023077788,"about_ca_system_score_gemma":0.00033943148,"threshold_uncertainty_score":0.99996394},"labels":[],"label_agreement":null},{"id":"W4388976300","doi":"10.21203/rs.3.rs-3528413/v1","title":"Improving Explainable AI Interpretability: Mathematical Models for Evaluating Explanation Methods.","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Transparency (behavior); Computer science; Accountability; Artificial intelligence; Correctness; Management science; Machine learning; Algorithm; Computer security","score_opus":0.39214911705601807,"score_gpt":0.5530217707892984,"score_spread":0.1608726537332803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388976300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001349974,0.0002643589,0.98927325,0.0028344945,0.00063384866,0.004062642,0.000034176253,0.0007051985,0.0008420512],"genre_scores_gemma":[0.16470426,0.00004800224,0.826868,0.0000966197,0.00030755528,0.0063656494,0.00007631377,0.0001427631,0.0013908178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906226,0.0023504135,0.0011419258,0.0020292846,0.0021758638,0.0016799307],"domain_scores_gemma":[0.9862423,0.007314233,0.00028661825,0.0026618564,0.0031634853,0.0003315057],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030686073,0.0004518781,0.00070861203,0.001091253,0.0007733828,0.0017686314,0.0033713074,0.00052911654,0.000048549256],"category_scores_gemma":[0.015239232,0.0004505285,0.00038390333,0.0011751684,0.00018945662,0.0014352651,0.006572414,0.001995968,0.0002331448],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010849513,0.00033594295,0.000022650467,0.0084356675,0.00012372644,0.00004237694,0.016328005,0.09239598,0.0031907808,0.53063947,0.0018108422,0.34656605],"study_design_scores_gemma":[0.000060189315,0.00016639738,0.0000019137026,0.00043839868,0.000007380968,0.0000018744541,0.001323117,0.52967906,0.0073363087,0.46068496,0.00007515935,0.00022522283],"about_ca_topic_score_codex":0.00062754966,"about_ca_topic_score_gemma":0.000067353714,"teacher_disagreement_score":0.4372831,"about_ca_system_score_codex":0.0010623005,"about_ca_system_score_gemma":0.0012686934,"threshold_uncertainty_score":0.99979466},"labels":[],"label_agreement":null},{"id":"W4389040816","doi":"10.1109/access.2023.3337117","title":"Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Lakehead University","funders":"King Saud University","keywords":"Survivability; Computer science; Context (archaeology); Machine learning; Process (computing); Artificial intelligence; Inference; Radiation treatment planning; Predictive modelling; Decision support system; Risk analysis (engineering); Medicine","score_opus":0.36592380060243573,"score_gpt":0.3912223805439937,"score_spread":0.025298579941557986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389040816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2631547,0.00015788134,0.7337081,0.00022052195,0.0008443692,0.00020073852,0.0000055065416,0.0007284705,0.0009797598],"genre_scores_gemma":[0.99498796,0.000064251144,0.0039000227,0.00008735069,0.00014390954,0.00003133489,0.0000117405325,0.00003877013,0.00073467335],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977459,0.00017788837,0.00034463208,0.0006422714,0.00043823858,0.0006510858],"domain_scores_gemma":[0.9986127,0.00032951526,0.00014767204,0.00066250615,0.00010744382,0.00014018125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005174518,0.00025874467,0.0002713645,0.0003849731,0.0004992401,0.00079437334,0.0013574491,0.000075251504,0.00003754862],"category_scores_gemma":[0.000026497919,0.00024350398,0.0000996087,0.0015098694,0.000047034588,0.0016372431,0.0002214909,0.00018344416,0.00018138134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013807373,0.000045688936,0.0020153935,0.000011469817,0.000015387119,0.0002013867,0.00080231886,0.98335385,0.0028027014,0.0034294527,0.000066878194,0.0072416603],"study_design_scores_gemma":[0.00017024112,0.00007499646,0.00012035573,0.00003457706,0.0000045561587,0.0000018155247,0.00010887557,0.94313693,0.051128063,0.0015988128,0.0033554912,0.00026528048],"about_ca_topic_score_codex":0.00096394686,"about_ca_topic_score_gemma":0.00006199045,"teacher_disagreement_score":0.7318333,"about_ca_system_score_codex":0.00023289782,"about_ca_system_score_gemma":0.00012097429,"threshold_uncertainty_score":0.99298036},"labels":[],"label_agreement":null},{"id":"W4389138268","doi":"10.1007/s11943-023-00331-z","title":"Exploring quality dimensions in trustworthy Machine Learning in the context of official statistics: model explainability and uncertainty quantification","year":2023,"lang":"en","type":"article","venue":"AStA Wirtschafts- und Sozialstatistisches Archiv","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Computer science; Quality (philosophy); Context (archaeology); Data science; Trustworthiness; Data collection; Coding (social sciences); Data quality; Quality management; Process management; Artificial intelligence; Machine learning; Data mining; Engineering; Operations management; Statistics; Computer security","score_opus":0.1553770748700975,"score_gpt":0.34805547126080294,"score_spread":0.19267839639070544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389138268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57484466,0.00009631069,0.42321888,0.00090167613,0.000099516,0.0005047978,0.00015945264,0.00009469497,0.00008004744],"genre_scores_gemma":[0.9797059,0.00032608342,0.019566955,0.00007730317,0.000024723038,0.00014213624,0.00009707806,0.000023276989,0.000036487425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953058,0.0014348913,0.0011990719,0.0007914133,0.00060476456,0.00066408527],"domain_scores_gemma":[0.9947779,0.0038385214,0.00035467584,0.0007657322,0.00014576958,0.00011740611],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004575845,0.000300884,0.0005391778,0.0004759877,0.0003678218,0.00015133554,0.0007890617,0.00006362095,0.0000050824183],"category_scores_gemma":[0.0020921628,0.00026944952,0.00006241443,0.001227813,0.000397872,0.0007638962,0.00040112511,0.00057018537,0.000017033912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012508917,0.00018737892,0.0086426325,0.00012114021,0.000019734302,0.000045919627,0.042033035,0.111927696,0.0013479511,0.7553568,0.00005456014,0.080138095],"study_design_scores_gemma":[0.0003445813,0.0001332445,0.034624327,0.00007196086,0.000010902413,0.0000028965878,0.008327157,0.8932171,0.00073632965,0.061970457,0.0002350585,0.00032597483],"about_ca_topic_score_codex":0.008809096,"about_ca_topic_score_gemma":0.017204829,"teacher_disagreement_score":0.7812894,"about_ca_system_score_codex":0.00007982065,"about_ca_system_score_gemma":0.00024899573,"threshold_uncertainty_score":0.99997574},"labels":[],"label_agreement":null},{"id":"W4389160999","doi":"10.1109/qce57702.2023.00024","title":"Quantum Algorithms for Shapley Value Calculation","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Shapley value; Computer science; Context (archaeology); Algorithm; Voting; Cooperative game theory; Quantum; Game theory; Polynomial; Interval (graph theory); Value (mathematics); Theoretical computer science; Mathematical economics; Mathematics; Combinatorics; Machine learning","score_opus":0.08758635475548701,"score_gpt":0.34244434541363716,"score_spread":0.2548579906581502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389160999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069399504,0.000011591566,0.98714894,0.0026135491,0.0005133765,0.00029676457,0.0000022380357,0.0007438426,0.0017297557],"genre_scores_gemma":[0.83129084,0.000018241333,0.15781525,0.0011265324,0.00034775562,0.0002100476,0.000029511382,0.00003475032,0.009127086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988307,0.000027446324,0.00021207743,0.00034830088,0.0002175481,0.00036393417],"domain_scores_gemma":[0.9991668,0.00020867317,0.000040284922,0.00038788756,0.00012073425,0.00007566215],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00050228095,0.000094406685,0.000100556164,0.0001427678,0.00018134828,0.00015049386,0.0005488362,0.000052656487,0.000020441827],"category_scores_gemma":[0.00013462268,0.00008686902,0.000072354946,0.00082204625,0.000022030632,0.0005221235,0.00014622498,0.000047531146,0.0009565819],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020654325,0.000016330827,0.00004839865,0.000007904006,0.00000575139,0.0000053364006,0.00040710444,0.004963044,0.0014738648,0.9541775,0.008645079,0.030247621],"study_design_scores_gemma":[0.000047445108,0.00005281063,0.0003056723,0.0000043078358,0.0000016686815,0.0000016306349,0.0000644616,0.8897831,0.018115342,0.0832609,0.00824653,0.000116128016],"about_ca_topic_score_codex":0.00018114853,"about_ca_topic_score_gemma":0.000026139054,"teacher_disagreement_score":0.88482004,"about_ca_system_score_codex":0.00003797311,"about_ca_system_score_gemma":0.00004645526,"threshold_uncertainty_score":0.9998213},"labels":[],"label_agreement":null},{"id":"W4389203808","doi":"10.3390/make5040089","title":"Analysing Semi-Supervised ConvNet Model Performance with Computation Processes","year":2023,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Preprocessor; Machine learning; Computation; Classifier (UML); Artificial neural network; Supervised learning; Training set; Data pre-processing; Algorithm","score_opus":0.02850362207233759,"score_gpt":0.3039833642872269,"score_spread":0.2754797422148893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389203808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45012382,0.00023174185,0.5465813,0.00019644314,0.00007457156,0.00008887908,4.0956337e-7,0.0005258148,0.0021770257],"genre_scores_gemma":[0.99325955,0.00019664009,0.0046275374,0.00001708147,0.00005492564,0.0000150550895,0.000023628802,0.00001626446,0.0017893037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988962,0.00008675885,0.00019509689,0.00038539077,0.00017505084,0.00026153304],"domain_scores_gemma":[0.99931335,0.00016639984,0.000103724466,0.00011993039,0.00022418583,0.00007239341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044809165,0.00015258334,0.00015128806,0.0002672771,0.0005414367,0.00023545888,0.00014600539,0.000054353,0.00000498799],"category_scores_gemma":[0.000096071315,0.00013460037,0.000021087215,0.0013032602,0.00004094403,0.0009181714,0.00007326652,0.0003012508,0.000117008596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043871096,0.00008054573,0.019402152,0.00027394498,0.000028841676,0.000011349629,0.005944073,0.7300737,0.0038375687,0.00051143725,0.00010599685,0.23968652],"study_design_scores_gemma":[0.00012761039,0.00012974131,0.0012941038,0.0000637211,0.000012997111,0.000022219838,0.00025397236,0.9940101,0.0028321291,0.00023855493,0.0008350673,0.00017979491],"about_ca_topic_score_codex":0.00005040513,"about_ca_topic_score_gemma":0.000096029005,"teacher_disagreement_score":0.54313576,"about_ca_system_score_codex":0.000038380673,"about_ca_system_score_gemma":0.00009862882,"threshold_uncertainty_score":0.5488844},"labels":[],"label_agreement":null},{"id":"W4389205280","doi":"10.17986/blm.1661","title":"Yapay Zeka ve Adli Bilimler: Yayınların Bibliyometrik Analizi","year":2023,"lang":"en","type":"article","venue":"The Bulletin of Legal Medicine","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Forensic science; Data science; Computer science; History; Archaeology","score_opus":0.0381693571336104,"score_gpt":0.29239634375667284,"score_spread":0.2542269866230624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389205280","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14160976,0.0049585537,0.06065209,0.6663434,0.005540688,0.001835703,0.000018523107,0.0020864618,0.116954826],"genre_scores_gemma":[0.9825557,0.0005702065,0.001636741,0.0033097118,0.00067418284,0.000041727293,0.0000071271447,0.000036188914,0.01116841],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701154,0.00023924073,0.00066732883,0.0004867629,0.0009824246,0.0006126756],"domain_scores_gemma":[0.99668723,0.0012706632,0.00023977985,0.0013418641,0.00028032935,0.0001801209],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028632316,0.00024054217,0.00044018117,0.0012859008,0.00022605664,0.000064796186,0.0022721274,0.00008528195,0.0009955246],"category_scores_gemma":[0.0015960501,0.00015172876,0.00011302189,0.0071800575,0.0005635911,0.00012627216,0.00053217553,0.00034408804,0.0021719956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007347293,0.00013939796,0.0003696708,0.00011109678,0.0000959381,0.00022767867,0.0044494406,0.0004957406,0.007429742,0.16620454,0.7814279,0.038975365],"study_design_scores_gemma":[0.00038347518,0.0008271502,0.0011166802,0.00021883841,0.000033095894,0.00004062949,0.0013602003,0.004210783,0.021130253,0.005330396,0.96506494,0.00028357186],"about_ca_topic_score_codex":0.0017143625,"about_ca_topic_score_gemma":0.00002791819,"teacher_disagreement_score":0.84094596,"about_ca_system_score_codex":0.000042685046,"about_ca_system_score_gemma":0.00008120842,"threshold_uncertainty_score":0.9999177},"labels":[],"label_agreement":null},{"id":"W4389261129","doi":"10.48550/arxiv.2311.18503","title":"End-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Information retrieval; Implementation; Encoder; Software; Similarity (geometry); Artificial neural network; Artificial intelligence; Data mining; Programming language","score_opus":0.22762425124588948,"score_gpt":0.25986799749423023,"score_spread":0.032243746248340754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389261129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5600832,0.000020604477,0.43828523,0.00035174793,0.00030654925,0.00032757482,0.000009555083,0.00026433737,0.0003512018],"genre_scores_gemma":[0.9889435,0.00008756943,0.007707516,0.000076660646,0.000055567518,9.121765e-7,0.000009983629,0.000035133242,0.0030831143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997318,0.00018614468,0.00024375481,0.0015696386,0.00017423509,0.00050819386],"domain_scores_gemma":[0.9975179,0.00025520404,0.00021254773,0.0014451633,0.00029453033,0.00027466522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004115103,0.0003195498,0.00032887392,0.00054577366,0.00036072574,0.00032448786,0.001190494,0.00019965782,0.000032046784],"category_scores_gemma":[0.00017411415,0.00036726016,0.0000934414,0.0017463657,0.00020667759,0.00056270376,0.0024328583,0.000514474,0.00022230722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020239124,0.00009471481,0.005985045,0.0000686779,0.00016887,0.0024110966,0.0019091492,0.90332395,0.0016340698,0.0833251,0.00021946862,0.00065747206],"study_design_scores_gemma":[0.0004543595,0.00021840032,0.0040558116,0.00029406574,0.00019872072,0.000058472233,0.001596681,0.93381435,0.014144306,0.043509647,0.0004650883,0.0011900933],"about_ca_topic_score_codex":0.001580066,"about_ca_topic_score_gemma":0.00045450663,"teacher_disagreement_score":0.43057773,"about_ca_system_score_codex":0.00023953257,"about_ca_system_score_gemma":0.0003380829,"threshold_uncertainty_score":0.9998779},"labels":[],"label_agreement":null},{"id":"W4389685461","doi":"10.1007/s10664-023-10409-5","title":"Detection and evaluation of bias-inducing features in machine learning","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Computer science; Machine learning; Identification (biology); Context (archaeology); Artificial intelligence; Harm; Feature (linguistics); Outcome (game theory); Data mining; Psychology","score_opus":0.06541519331576667,"score_gpt":0.314828704639924,"score_spread":0.24941351132415734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389685461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78428334,0.00021157162,0.21483956,0.00010348933,0.00014057015,0.00009767535,2.657974e-7,0.00031073717,0.000012788109],"genre_scores_gemma":[0.9958068,0.00001339494,0.004091706,0.00001451201,0.00002826056,0.000016656688,0.0000014386138,0.000010397866,0.000016804044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998922,0.000080674356,0.0001990834,0.00024083417,0.0003398687,0.00021757573],"domain_scores_gemma":[0.9992569,0.00043229994,0.00004235404,0.00014629854,0.00007379539,0.000048352944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012762022,0.00009475324,0.00012626483,0.00031322066,0.00005351029,0.00004360809,0.000153604,0.000063221334,0.0000039722468],"category_scores_gemma":[0.00265992,0.000096444186,0.000026988058,0.0011786816,0.000010168757,0.0002744215,0.00012773807,0.00022849758,0.000010107464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003612331,0.000016423093,0.06790005,0.00005118032,0.000008666393,0.000011186441,0.0023198707,0.78294444,0.007442107,0.00012337632,0.000018718743,0.13916038],"study_design_scores_gemma":[0.00007785369,0.000035553807,0.13414863,0.000040690196,0.0000034747582,0.0000049575715,0.00004046899,0.84376657,0.021332059,0.0002966005,0.00015134625,0.00010179097],"about_ca_topic_score_codex":0.00013640411,"about_ca_topic_score_gemma":0.00006239272,"teacher_disagreement_score":0.21152349,"about_ca_system_score_codex":0.00008251705,"about_ca_system_score_gemma":0.000023409735,"threshold_uncertainty_score":0.393288},"labels":[],"label_agreement":null},{"id":"W4390151798","doi":"10.48550/arxiv.2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"","keywords":"Interpretability; Computer science; Audit; Pairwise comparison; Key (lock); Artificial intelligence; Data science; Machine learning; Computer security; Business","score_opus":0.15318685338188803,"score_gpt":0.22531732621700656,"score_spread":0.07213047283511853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390151798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7273369,0.000051764,0.26860693,0.0020352767,0.00036153974,0.00059321383,0.000008285808,0.00023876374,0.0007673569],"genre_scores_gemma":[0.9989238,0.000090550544,0.00010015192,0.00009911607,0.0000629991,0.00000525576,0.000006255857,0.000023907874,0.0006879949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970212,0.0008287578,0.00037011306,0.0011721362,0.00014297767,0.00046480607],"domain_scores_gemma":[0.99583685,0.0022231676,0.0002827341,0.0014806394,0.000083655905,0.000092937065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002028083,0.0003459013,0.00041225678,0.0002812633,0.00039950537,0.00033376456,0.0030947062,0.00020719095,0.000017644612],"category_scores_gemma":[0.0008958544,0.00025758895,0.00017521434,0.0009432403,0.00029159972,0.00037566756,0.0050609917,0.0017427221,0.00011270673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016115706,0.00020652932,0.28690222,0.00020849558,0.00024367757,0.00049618026,0.020302474,0.18607429,0.00007000447,0.48922864,0.00018317306,0.015923183],"study_design_scores_gemma":[0.00018928204,0.00011202567,0.0126345875,0.00032781082,0.00003820835,0.0000021069595,0.0015190757,0.8610131,0.0005713928,0.12255743,0.00057823386,0.0004567598],"about_ca_topic_score_codex":0.0014759625,"about_ca_topic_score_gemma":0.0006970072,"teacher_disagreement_score":0.6749388,"about_ca_system_score_codex":0.00027910623,"about_ca_system_score_gemma":0.000115014154,"threshold_uncertainty_score":0.99998766},"labels":[],"label_agreement":null},{"id":"W4390338706","doi":"10.1038/s41598-023-49854-z","title":"On the interpretability of part-prototype based classifiers: a human centric analysis","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Computer science; Perspective (graphical); Representation (politics); Machine learning; Artificial intelligence; Set (abstract data type); Reliability (semiconductor); Black box; Task (project management); Limit (mathematics); Data mining; Systems engineering; Mathematics","score_opus":0.0491905525721428,"score_gpt":0.3001583060939814,"score_spread":0.25096775352183864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390338706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9250005,0.000024021452,0.061832048,0.0017038047,0.0047233463,0.001209493,0.0000042241527,0.0004605795,0.005041993],"genre_scores_gemma":[0.99868643,4.3932565e-7,0.00027949503,0.00007801215,0.000018662138,0.00008351951,0.000013838555,0.0000075210573,0.0008321021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996439,0.00026134154,0.00079005264,0.0010744671,0.00096094585,0.0004742272],"domain_scores_gemma":[0.99548364,0.00040882468,0.00045181386,0.003184934,0.00035126987,0.000119524375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053321556,0.00016233712,0.00027979797,0.00078247406,0.00055727403,0.00047523942,0.001057376,0.000062241925,0.00032939564],"category_scores_gemma":[0.0010605557,0.0001145146,0.00033016995,0.009750494,0.00045284422,0.00028789093,0.00027649294,0.00016515267,0.00015408295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015407936,0.0026826817,0.13207538,0.00038633312,0.0014338593,0.0027735208,0.015811926,0.089211375,0.068141304,0.49958238,0.15543593,0.032311223],"study_design_scores_gemma":[0.00008843781,0.00029656567,0.007076608,0.00010319945,0.00015914309,0.000009162797,0.0006010031,0.47183967,0.24562086,0.2591508,0.0144860055,0.000568531],"about_ca_topic_score_codex":0.000079230434,"about_ca_topic_score_gemma":0.00009056994,"teacher_disagreement_score":0.3826283,"about_ca_system_score_codex":0.00007908371,"about_ca_system_score_gemma":0.00019305457,"threshold_uncertainty_score":0.4684789},"labels":[],"label_agreement":null},{"id":"W4390356179","doi":"10.2139/ssrn.4678045","title":"A Data-Driven Accident Model (Dam): Holistic Risk Simulation Using Explainable Artificial Intelligence","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Accident (philosophy); Computer science; Artificial intelligence; Philosophy; Epistemology","score_opus":0.2302192832857171,"score_gpt":0.3909140503123218,"score_spread":0.16069476702660468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390356179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031132706,0.00082083844,0.96466047,0.0004260388,0.0018147996,0.0006393035,0.000057357658,0.00040865122,0.000039835737],"genre_scores_gemma":[0.967124,0.003320682,0.027867999,0.000058427562,0.0010496728,0.000029857129,0.00006164844,0.00012488224,0.00036286467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98998934,0.00053019205,0.0016733715,0.0018633527,0.0013388564,0.0046049054],"domain_scores_gemma":[0.99387795,0.0005064757,0.001518565,0.0031063491,0.0006750997,0.00031555234],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006715834,0.0007383559,0.0007474082,0.00085294945,0.0011658714,0.0017693592,0.007498543,0.0005005997,0.00001449889],"category_scores_gemma":[0.0014250773,0.0007827652,0.0003265768,0.0010199308,0.00013130551,0.0021228483,0.005780129,0.0073585194,0.0003301261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000032133765,0.00009173115,0.000062938685,0.000025663006,0.00015713695,0.000046752386,0.00064042315,0.85688895,0.000043534634,0.12129216,0.000025718366,0.020692868],"study_design_scores_gemma":[0.00002656709,0.00006319722,0.000005064728,0.00010126413,0.000076843244,0.000055705063,0.00070200337,0.5221705,0.00011639898,0.47625825,0.000020858788,0.0004033568],"about_ca_topic_score_codex":0.00127196,"about_ca_topic_score_gemma":0.0043149777,"teacher_disagreement_score":0.9367925,"about_ca_system_score_codex":0.003941764,"about_ca_system_score_gemma":0.009202773,"threshold_uncertainty_score":0.9998819},"labels":[],"label_agreement":null},{"id":"W4390452853","doi":"10.1016/j.cjca.2023.12.028","title":"Artificial Intelligence in Cardiology Research: How to Upskill","year":2023,"lang":"en","type":"editorial","venue":"Canadian Journal of Cardiology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital; University of British Columbia Hospital","funders":"","keywords":"Medicine; Cardiology; Internal medicine; Medical physics","score_opus":0.11534033931750737,"score_gpt":0.35909493863568454,"score_spread":0.24375459931817717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390452853","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001350107,0.00041403197,0.16921033,0.0062057027,0.8218071,0.00033585093,0.00006722537,0.000032789252,0.0017919856],"genre_scores_gemma":[0.067673996,0.0003748391,0.002106095,0.000106104686,0.9290998,0.00005560868,0.000020955717,0.00010606974,0.00045651192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923617,0.0020841183,0.0013157851,0.00095549366,0.0010511205,0.0022317714],"domain_scores_gemma":[0.98875475,0.005236774,0.0003888012,0.001255515,0.0027841364,0.0015799961],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009429543,0.00045169797,0.0018062495,0.0048977025,0.0002835792,0.00042572443,0.0052445084,0.0015692369,0.000007679023],"category_scores_gemma":[0.026962057,0.00046723412,0.00045784353,0.0029641893,0.00058634864,0.00041016145,0.00042352563,0.003918935,0.0006048048],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024453915,0.0000016478173,0.000064946566,0.000018565841,0.0000938181,0.0053732684,0.000666085,0.014892248,0.000026964151,0.0075821653,0.9524486,0.01880721],"study_design_scores_gemma":[0.000032784057,0.0006219267,0.00005875374,0.00014670445,0.000015294145,0.00011071436,0.00060717657,0.00018586464,0.0001490434,0.029894333,0.9677583,0.00041910383],"about_ca_topic_score_codex":0.0050802426,"about_ca_topic_score_gemma":0.04828407,"teacher_disagreement_score":0.16710423,"about_ca_system_score_codex":0.0016135747,"about_ca_system_score_gemma":0.010124761,"threshold_uncertainty_score":0.9997779},"labels":[],"label_agreement":null},{"id":"W4390491648","doi":"10.17705/1jais.00869","title":"Should We Collaborate with AI to Conduct Literature Reviews? Changing Epistemic Values in a Flattening World","year":2024,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Transparency (behavior); Scope (computer science); Computer science; Context (archaeology); Generative grammar; Process (computing); Artificial intelligence; Compromise; Quality (philosophy); Epistemology; Data science; Management science; Sociology; Engineering; Philosophy","score_opus":0.04314033247248466,"score_gpt":0.31966404047514946,"score_spread":0.2765237080026648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390491648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029780678,0.015908007,0.7901204,0.13041836,0.02061217,0.007260911,0.00008903553,0.00031754287,0.005492864],"genre_scores_gemma":[0.9875688,0.00013616974,0.0028021024,0.001674581,0.00046033078,0.000103489656,0.000004144546,0.00001546647,0.0072348947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99786067,0.00019317486,0.001031356,0.000094332594,0.0005647781,0.00025569834],"domain_scores_gemma":[0.9974275,0.0002681699,0.0010327791,0.00019739741,0.0010150631,0.00005908495],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0047536395,0.00012562056,0.00030291564,0.0009078023,0.0001530773,0.0017254855,0.00054308755,0.000069206646,7.5382695e-7],"category_scores_gemma":[0.0005120694,0.000078060584,0.00011419159,0.0037369519,0.0000059773324,0.0046461867,0.00006106545,0.0002947216,0.00004287336],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001820623,0.00006344153,0.006657634,0.0034853884,0.00046767428,0.00002710912,0.2697691,0.16102064,0.002337587,0.38002712,0.1498943,0.026067944],"study_design_scores_gemma":[0.00045352182,0.00019895443,0.00022344419,0.013399486,0.000049604536,0.00012764105,0.00453221,0.14757207,0.003223787,0.002284523,0.8275394,0.00039535086],"about_ca_topic_score_codex":0.0000060338757,"about_ca_topic_score_gemma":0.00001928878,"teacher_disagreement_score":0.95778817,"about_ca_system_score_codex":0.00088464184,"about_ca_system_score_gemma":0.0001725174,"threshold_uncertainty_score":0.9993108},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06421974591361419,"score_gpt":0.3520020040083907,"score_spread":0.28778225809477653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390604658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8700366,0.0021049292,0.025154108,0.08651837,0.0006255317,0.0019608354,0.00014600788,0.00035294335,0.013100646],"genre_scores_gemma":[0.98895115,0.000009255269,0.010568614,0.0001670399,0.00009277371,0.000017459426,1.1553998e-7,0.0000025020586,0.0001911166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99834293,0.0000062970703,0.00026277037,0.00036316534,0.0008364623,0.00018838095],"domain_scores_gemma":[0.9990922,0.0002798424,0.00016789624,0.000014377589,0.0004157545,0.000029919129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029813456,0.000083922794,0.00011258644,0.00013945659,0.00024859174,0.00014836986,0.0016454251,0.000082509396,0.0000031499294],"category_scores_gemma":[0.0006138331,0.00005266197,0.00011670129,0.0014053049,0.00058520853,0.0012971283,0.00020983886,0.00014622022,0.0000026577081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034359111,0.000015549034,0.00031681158,0.00006020458,0.0000055652413,2.981229e-9,0.00022314345,0.00004906675,0.10797987,0.88716793,0.0013201887,0.002858224],"study_design_scores_gemma":[0.000017270953,0.000034741035,0.0031735934,0.000050599498,0.0000030192168,0.0000032928451,0.000044774322,0.034903616,0.4487636,0.5121389,0.0008189203,0.00004769606],"about_ca_topic_score_codex":0.000003902174,"about_ca_topic_score_gemma":6.597666e-8,"teacher_disagreement_score":0.37502906,"about_ca_system_score_codex":0.000061713494,"about_ca_system_score_gemma":0.000070612754,"threshold_uncertainty_score":0.30576366},"labels":[],"label_agreement":null},{"id":"W4390872800","doi":"10.1109/iccv51070.2023.00190","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Warwick; Transport Canada","keywords":"Interpretability; Robustness (evolution); Computer science; Machine learning; Artificial intelligence; Probabilistic logic; Bespoke; Data mining; Trustworthiness","score_opus":0.04740619807341593,"score_gpt":0.3414541511880035,"score_spread":0.29404795311458753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390872800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22989443,0.000012693504,0.7680708,0.00064970175,0.00022557608,0.00031736228,0.000003636638,0.00011632704,0.0007094423],"genre_scores_gemma":[0.9801984,0.0000021111805,0.01950766,0.000026988699,0.000012366653,0.00005348692,0.0000019913557,0.0000040157847,0.00019302621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990959,0.00005562424,0.00022286699,0.00026826843,0.00017196394,0.00018538506],"domain_scores_gemma":[0.99865586,0.0006596175,0.00004741108,0.0003815974,0.00020881122,0.00004673156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011189075,0.00006657286,0.00011249645,0.00010624392,0.00009461317,0.0000457982,0.0003363146,0.000030370744,0.00003406465],"category_scores_gemma":[0.0005353099,0.000059995036,0.000042899097,0.0005415515,0.00007637348,0.00015578466,0.00021558268,0.000033572316,0.000022505888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005485387,0.0002562476,0.0011330039,0.0001840962,0.00004095895,0.0000013259764,0.009057344,0.47783577,0.0066416953,0.38126513,0.002673676,0.120855875],"study_design_scores_gemma":[0.00006358372,0.00006347204,0.0012285378,0.000008702758,0.0000044858843,5.3533955e-7,0.00044332034,0.97257596,0.021504853,0.003861928,0.00017823072,0.000066410175],"about_ca_topic_score_codex":0.000044968412,"about_ca_topic_score_gemma":0.000041399308,"teacher_disagreement_score":0.7503039,"about_ca_system_score_codex":0.000027456994,"about_ca_system_score_gemma":0.000060988874,"threshold_uncertainty_score":0.24465266},"labels":[],"label_agreement":null},{"id":"W4391026313","doi":"10.1145/3641108","title":"Interpreting Deep Forest through Feature Contribution and MDI Feature Importance","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Interpretability; Categorical variable; Feature (linguistics); Random forest; Computer science; Tree (set theory); Artificial intelligence; Variety (cybernetics); Feature model; Data mining; Layer (electronics); Machine learning; Pattern recognition (psychology); Mathematics; Software","score_opus":0.031627270126612386,"score_gpt":0.3094050055243785,"score_spread":0.2777777353977661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391026313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008634987,0.008707508,0.97405374,0.004713938,0.0016654148,0.0003145796,0.001048774,0.00036383327,0.0004972343],"genre_scores_gemma":[0.9754582,0.0006251948,0.021891933,0.00029718515,0.00021115488,0.00004452325,0.00066199346,0.00003575359,0.00077406527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765986,0.00010144492,0.00028922342,0.0012687448,0.0002382861,0.00044242208],"domain_scores_gemma":[0.99628735,0.00075596455,0.00006697805,0.002690597,0.000094277006,0.000104830455],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003044838,0.00032256136,0.00027192238,0.000119979115,0.00038501056,0.0012920587,0.0024090626,0.00020658075,0.00002853731],"category_scores_gemma":[0.00021305529,0.00029159526,0.00009749954,0.00072911684,0.00013021634,0.006327083,0.00026306487,0.0006720266,0.00021043848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004845089,0.0015906603,0.0048880517,0.000591853,0.0015030272,0.00080514204,0.023780737,0.0016781582,0.0097205825,0.17716019,0.07676279,0.7010343],"study_design_scores_gemma":[0.00066307076,0.00040895003,0.0024104156,0.0019115893,0.00034109762,0.0001394918,0.0018916603,0.5436649,0.033323985,0.13702376,0.2763359,0.0018852076],"about_ca_topic_score_codex":0.00014102078,"about_ca_topic_score_gemma":0.0028907503,"teacher_disagreement_score":0.9668232,"about_ca_system_score_codex":0.00014097517,"about_ca_system_score_gemma":0.00013354298,"threshold_uncertainty_score":0.9999536},"labels":[],"label_agreement":null},{"id":"W4391166900","doi":"10.1038/s42256-023-00784-5","title":"Anniversary AI reflections","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformative learning; Theme (computing); Generative grammar; Epistemology; Engineering ethics; Psychology; Cognitive science; Computer science; Philosophy; Artificial intelligence; Engineering; Pedagogy; World Wide Web","score_opus":0.01634707780693423,"score_gpt":0.34906016233957354,"score_spread":0.3327130845326393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391166900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020905235,0.008585289,0.94933665,0.010505583,0.0032638055,0.0001994635,0.000009341407,0.0012691886,0.026621634],"genre_scores_gemma":[0.97221303,0.00026229618,0.020958222,0.0029155638,0.0003507128,0.000021211108,0.0000072755684,0.000030848107,0.0032408673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977076,0.00008625126,0.00035580722,0.00086941343,0.00046685233,0.0005140542],"domain_scores_gemma":[0.9984238,0.0002956641,0.000042826807,0.00086266716,0.0002038422,0.00017117352],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044202083,0.0002812526,0.00019133418,0.00047188145,0.00028394067,0.0006491803,0.0016972222,0.00031751025,0.00025289215],"category_scores_gemma":[0.00020710194,0.00025316083,0.00017238226,0.0023604268,0.000111167064,0.0014084844,0.00037745343,0.0018163556,0.0017374504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007278929,0.000056992256,0.000042254764,0.00003802175,0.000036487334,0.00035195533,0.0010291144,0.00103391,0.0016975311,0.81659245,0.009044355,0.17006966],"study_design_scores_gemma":[0.00001839443,0.00016113493,0.00004831904,0.00012800412,0.000017206528,0.00024854002,0.00013784738,0.33673078,0.13453355,0.18427458,0.3431564,0.0005452269],"about_ca_topic_score_codex":0.00019206086,"about_ca_topic_score_gemma":0.00015464152,"teacher_disagreement_score":0.97200394,"about_ca_system_score_codex":0.00016594904,"about_ca_system_score_gemma":0.00018582448,"threshold_uncertainty_score":0.9999921},"labels":[],"label_agreement":null},{"id":"W4391210548","doi":"10.1145/3623509.3633370","title":"Embodied Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Domain (mathematical analysis); Normative; Computer science; Embodied cognition; Bridge (graph theory); Artificial intelligence; Subject-matter expert; Data science; Human–computer interaction; Machine learning; Knowledge management; Expert system; Epistemology","score_opus":0.026155064778751312,"score_gpt":0.27639513852026654,"score_spread":0.25024007374151525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391210548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011640347,0.0006092024,0.7982666,0.0023721724,0.00051591336,0.00005782146,2.1204575e-7,0.0012414037,0.19577263],"genre_scores_gemma":[0.9621653,0.000031336207,0.017208172,0.00031399954,0.00007522798,0.000007294126,0.0000010631087,0.000010034136,0.02018758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991263,0.000035853664,0.00013524889,0.00030537325,0.00016041286,0.00023678063],"domain_scores_gemma":[0.99952966,0.00011091166,0.0000108371,0.00025522482,0.00003044462,0.00006294761],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027128815,0.00008358644,0.0000723519,0.000106852225,0.000104889376,0.0004499848,0.00049625116,0.000030026547,0.00031397535],"category_scores_gemma":[0.00005264161,0.00006872293,0.000046899248,0.00046184505,0.000020487956,0.0005581636,0.00019152758,0.00017949476,0.003167774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.046626e-7,0.0000088018105,0.00006651541,0.0000098733,0.000006773107,0.00007242168,0.0006875721,0.00035937945,0.00095035124,0.92353284,0.0011325169,0.07317236],"study_design_scores_gemma":[0.000012231201,0.000043488337,0.000014485365,0.000014229789,0.0000016749492,0.000015319538,0.00005791154,0.8284647,0.018675651,0.03305234,0.119526476,0.00012153693],"about_ca_topic_score_codex":0.00015888811,"about_ca_topic_score_gemma":0.000035141344,"teacher_disagreement_score":0.9610013,"about_ca_system_score_codex":0.000029288027,"about_ca_system_score_gemma":0.000037057005,"threshold_uncertainty_score":0.99760836},"labels":[],"label_agreement":null},{"id":"W4391350216","doi":"10.2139/ssrn.4710037","title":"Survey on Explainable Ai: Techniques, Challenges and Open Issues","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Windsor","funders":"","keywords":"Computer science; Data science","score_opus":0.05980798882824797,"score_gpt":0.3433260354350309,"score_spread":0.2835180466067829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391350216","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014680636,0.6810547,0.15120831,0.1022992,0.0047990894,0.004378934,0.000048278765,0.0019062414,0.039624628],"genre_scores_gemma":[0.6131686,0.36445445,0.0042480393,0.00081341324,0.001098976,0.00020662861,0.000018205763,0.00017483794,0.015816873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941964,0.00059260824,0.00059766386,0.0012070911,0.00056383543,0.0028423758],"domain_scores_gemma":[0.9978708,0.00019668102,0.0002835946,0.0011369712,0.00031707017,0.00019488772],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00936709,0.0005298837,0.0006339475,0.00047273823,0.0003522318,0.0022881352,0.0045689894,0.00039804276,0.000011927974],"category_scores_gemma":[0.00022481283,0.00047932728,0.00013414123,0.00029141933,0.00008810293,0.00064687006,0.00645312,0.007563084,0.0001544517],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002641986,0.00007886497,0.000016511218,0.000056795136,0.00013775725,0.000065380205,0.0008110002,0.000038670827,0.000026373897,0.718772,0.0016593678,0.2783109],"study_design_scores_gemma":[0.00006265238,0.0006866577,0.00010702703,0.00041271411,0.000018460181,0.00022047026,0.00059036235,0.0012897454,0.00291711,0.9803978,0.012749241,0.0005477312],"about_ca_topic_score_codex":0.0025503736,"about_ca_topic_score_gemma":0.008704513,"teacher_disagreement_score":0.598488,"about_ca_system_score_codex":0.0014045428,"about_ca_system_score_gemma":0.004083507,"threshold_uncertainty_score":0.9997658},"labels":[],"label_agreement":null},{"id":"W4391384550","doi":"10.1136/bjsports-2023-concussion.207","title":"2.16 Blood biomarkers for sport-related concussion: considering the effects of interval exercise and matrix differences","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Bone and Joint Health Institute; Alberta Children's Hospital; International Collaboration On Repair Discoveries; University of British Columbia; Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Medicine; Internal medicine; Confidence interval; Concussion; Crossover study; High-intensity interval training; Interval training; Randomized controlled trial; Biomarker; Physical therapy; Cardiology; Poison control; Injury prevention; Pathology","score_opus":0.014770245912868274,"score_gpt":0.2687720377957937,"score_spread":0.2540017918829254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391384550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84191895,0.008293393,0.14405234,0.0018928307,0.0014628912,0.0010521563,0.0000023245977,0.00034903755,0.00097604905],"genre_scores_gemma":[0.9951652,0.00019832878,0.0036327075,0.000036112586,0.000017870223,0.000041033218,5.617495e-7,0.0000094329525,0.00089873903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989175,0.000028640841,0.00032460684,0.00035011116,0.00014685265,0.00023226123],"domain_scores_gemma":[0.9985324,0.0009919673,0.00006114935,0.00029413908,0.000053591546,0.00006675496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000330776,0.00014325904,0.00021822663,0.00010128465,0.00010653549,0.00021425396,0.00043060683,0.000062641295,0.00003213755],"category_scores_gemma":[0.00009117402,0.00008329003,0.00008953734,0.00031669138,0.00018362653,0.00029119346,0.00022509352,0.00008554999,0.000013147379],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077202734,0.00017040511,0.0029160967,0.0021262867,0.0005231851,0.00021703307,0.007605723,0.000016134069,0.041782532,0.7058944,0.0030516342,0.23561934],"study_design_scores_gemma":[0.0004368422,0.00050611666,0.0005952459,0.001975683,0.00018708808,0.0000849688,0.001546136,0.15139802,0.7682534,0.07361617,0.00096735946,0.00043298866],"about_ca_topic_score_codex":0.000091403424,"about_ca_topic_score_gemma":0.000017227643,"teacher_disagreement_score":0.7264708,"about_ca_system_score_codex":0.00001304103,"about_ca_system_score_gemma":0.00005857829,"threshold_uncertainty_score":0.3396469},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4886989474982671,"score_gpt":0.45693764807136533,"score_spread":0.03176129942690176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391399751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7477316,0.042496536,0.13808887,0.055915017,0.0016092836,0.0017825239,0.0000041522235,0.00016099011,0.012210985],"genre_scores_gemma":[0.98895484,0.010290089,0.0001776831,0.00010116445,0.00016963342,0.00001189565,0.0000012443251,0.000013489559,0.0002799479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99548125,0.0013487962,0.0008657393,0.00038601653,0.0013652565,0.0005529216],"domain_scores_gemma":[0.99739116,0.0013995982,0.00014059909,0.00032238764,0.0005749958,0.00017126661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016098406,0.00017477208,0.00024573502,0.0010403387,0.000399817,0.000978554,0.000853067,0.00009481851,0.000024843457],"category_scores_gemma":[0.00062151713,0.00013327651,0.000060629663,0.00063025573,0.000337882,0.0010269679,0.00024228731,0.0011571632,0.000037998685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074186835,0.00013097563,0.000025828316,0.00008239266,0.00002895186,0.00065817987,0.008379174,0.0007639015,0.0019025392,0.6098085,0.0002557014,0.37788963],"study_design_scores_gemma":[0.00020841233,0.018440457,0.003094118,0.003374224,0.000040516148,0.0012211674,0.06385919,0.26366472,0.066931054,0.5611815,0.016606592,0.0013780512],"about_ca_topic_score_codex":0.00017475673,"about_ca_topic_score_gemma":0.0002119761,"teacher_disagreement_score":0.37651157,"about_ca_system_score_codex":0.000164014,"about_ca_system_score_gemma":0.00021094031,"threshold_uncertainty_score":0.9436218},"labels":[],"label_agreement":null},{"id":"W4391648709","doi":"10.2139/ssrn.4700751","title":"Beyond AI Exposure: Which Tasks are Cost-Effective to Automate with Computer Vision?","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Future Earth","funders":"","keywords":"Computer science; Human–computer interaction; Artificial intelligence; Software engineering; Computer vision","score_opus":0.006397203122600884,"score_gpt":0.27455143165607726,"score_spread":0.26815422853347637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391648709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03728495,0.0014218605,0.9485853,0.009907302,0.0009972722,0.000903068,0.0000028032039,0.00044038348,0.00045705936],"genre_scores_gemma":[0.9938664,0.00015355505,0.003476405,0.0012334761,0.0005543756,0.00011007186,0.0000015748852,0.000048404603,0.0005557323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99523294,0.00022117657,0.00040095326,0.0007313735,0.0006546062,0.002758944],"domain_scores_gemma":[0.99839574,0.00019164012,0.00011939141,0.0005440918,0.00045238904,0.00029674947],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019949044,0.00033975788,0.0003166136,0.0004068001,0.0004260696,0.001326246,0.001238694,0.00010837809,0.000019420733],"category_scores_gemma":[0.00004334125,0.00026422428,0.000113825,0.0017252727,0.00004995263,0.0014372399,0.00027013585,0.0021749665,0.00061963126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009429917,0.00014974363,0.00030574235,0.000030398996,0.00031642747,0.00040093556,0.0019710164,0.00985659,0.00085514755,0.5708884,0.0031928925,0.4119384],"study_design_scores_gemma":[0.00079319376,0.011402897,0.002001739,0.0008390938,0.000102054095,0.007495141,0.0014515206,0.4358297,0.009137837,0.49978918,0.02941759,0.0017400701],"about_ca_topic_score_codex":0.000042000353,"about_ca_topic_score_gemma":0.0017452143,"teacher_disagreement_score":0.9565815,"about_ca_system_score_codex":0.001323133,"about_ca_system_score_gemma":0.0018605397,"threshold_uncertainty_score":0.999981},"labels":[],"label_agreement":null},{"id":"W4391937457","doi":"10.2196/50475","title":"Integrating Explainable Machine Learning in Clinical Decision Support Systems: Study Involving a Modified Design Thinking Approach","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; National Research Council Canada; Centres Intégré Universitaires de Santé et de Services Sociaux; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"Computer science; Management science; Artificial intelligence; Engineering","score_opus":0.20403969410519682,"score_gpt":0.45625389652657455,"score_spread":0.2522142024213777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391937457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093694605,0.0007498341,0.8983113,0.00010011413,0.00044551602,0.0022568821,0.0000012008288,0.00045505253,0.0039854767],"genre_scores_gemma":[0.979577,0.00006810828,0.019004889,0.000018869376,0.00010022368,0.00077891216,0.000005924175,0.00003897055,0.00040711105],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896929,0.004312264,0.0015774028,0.0010646012,0.0020451332,0.0013076541],"domain_scores_gemma":[0.9928588,0.0054437346,0.00015404675,0.0007688686,0.0005452257,0.00022930148],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.03629216,0.00032064784,0.0005465035,0.0016099577,0.0009436925,0.0025911445,0.0021836422,0.00019493456,0.000015174226],"category_scores_gemma":[0.0019120818,0.00026019476,0.00013175243,0.0038231236,0.00015915766,0.00376117,0.0017072144,0.0032165067,0.00028733557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029080926,0.0027520533,0.00586235,0.0008734855,0.00015657309,0.0016156595,0.4389764,0.0731646,0.00022319469,0.27311447,0.0020984544,0.20087194],"study_design_scores_gemma":[0.00025826728,0.001364588,0.00023727673,0.00051235344,0.0000025117743,0.00002981193,0.047922384,0.94044244,0.00016439926,0.008462292,0.00034556305,0.00025812665],"about_ca_topic_score_codex":0.00076365,"about_ca_topic_score_gemma":0.0000709688,"teacher_disagreement_score":0.8858824,"about_ca_system_score_codex":0.00065843895,"about_ca_system_score_gemma":0.00057774136,"threshold_uncertainty_score":0.99998504},"labels":[],"label_agreement":null},{"id":"W4392148527","doi":"10.1007/978-3-031-54303-6_1","title":"Unlocking the Power of Explainability in Ranking Systems: A Visual Analytics Approach with XAI Techniques","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Ranking (information retrieval); Visual analytics; Analytics; Computer science; Data science; Information retrieval; Visualization; Data mining","score_opus":0.04257029119110668,"score_gpt":0.3098513979998137,"score_spread":0.26728110680870704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392148527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039360454,0.00058456924,0.8630013,0.0004526808,0.0001307864,0.0008474531,0.000003548466,0.000100253164,0.13448581],"genre_scores_gemma":[0.9464093,0.00044506742,0.05261287,0.00016584435,0.000015649643,0.000074328585,0.000007808609,0.00000990177,0.00025924205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786323,0.000059196325,0.0009323616,0.00032073839,0.0005756902,0.00024880588],"domain_scores_gemma":[0.99664146,0.00035178039,0.00037104616,0.0020605035,0.000527473,0.00004776825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029687122,0.00021542166,0.00030578743,0.0011826362,0.0003058426,0.0007729179,0.0034051493,0.00010949226,0.0000012705927],"category_scores_gemma":[0.000053557324,0.00015925009,0.000042037274,0.0012958362,0.0012297482,0.004138361,0.002136135,0.00057027815,0.0000053243107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050338826,0.000027491988,0.00008975631,0.00010000298,0.000006756611,7.7170125e-7,0.008280604,0.0033016093,0.0000025411725,0.96400213,0.000013211102,0.02417009],"study_design_scores_gemma":[0.00005855535,0.00010423129,0.00015453406,0.000635618,0.0000064736673,0.00002864174,0.00074142404,0.9763462,0.00007284251,0.013111179,0.008492081,0.00024824226],"about_ca_topic_score_codex":0.00008492871,"about_ca_topic_score_gemma":0.000028214725,"teacher_disagreement_score":0.9730446,"about_ca_system_score_codex":0.00025466242,"about_ca_system_score_gemma":0.00034404927,"threshold_uncertainty_score":0.7453265},"labels":[],"label_agreement":null},{"id":"W4392735406","doi":"10.1017/s0140525x23002261","title":"Confidence in research findings depends on theory","year":2024,"lang":"en","type":"article","venue":"Behavioral and Brain Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Variable (mathematics); Psychology; Variables; Epistemology; Cognitive psychology; Social psychology; Econometrics; Mathematics; Statistics; Philosophy","score_opus":0.30712623599413175,"score_gpt":0.48235116028578806,"score_spread":0.17522492429165631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392735406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983416,0.00053985056,0.005089793,0.0064388355,0.00036430848,0.00016727798,0.0000014836119,0.00011678869,0.003865658],"genre_scores_gemma":[0.9976892,0.000024950748,0.00087648485,0.0002659901,0.0000316669,0.00002276716,2.1671482e-7,0.000003884795,0.0010848654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977011,0.0002382876,0.00019587216,0.0006874751,0.0006682752,0.00050898275],"domain_scores_gemma":[0.9986207,0.0009931324,0.000013047145,0.00022707324,0.000049746748,0.00009629858],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0058109015,0.000107054126,0.000106079926,0.0005424441,0.00038653138,0.0011106532,0.0010440226,0.00005777018,0.000050726823],"category_scores_gemma":[0.00018012854,0.00008070422,0.00002829895,0.002022621,0.00078738574,0.0010525291,0.0002997027,0.00031041278,0.00015668388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038423723,0.000042967775,0.0010149773,0.000006483047,4.6295492e-7,0.0001380518,0.0022691772,0.000009358488,0.004064766,0.914548,0.00047246442,0.07742944],"study_design_scores_gemma":[0.00011256226,0.0017455388,0.009304985,0.00053046143,0.0000033629763,0.00008701921,0.004943974,0.018493816,0.070626736,0.88625085,0.0073157717,0.00058492215],"about_ca_topic_score_codex":0.00040278092,"about_ca_topic_score_gemma":0.00020247,"teacher_disagreement_score":0.07684452,"about_ca_system_score_codex":0.000046204532,"about_ca_system_score_gemma":0.00015885057,"threshold_uncertainty_score":0.99992627},"labels":[],"label_agreement":null},{"id":"W4392857185","doi":"10.22541/essoar.171052510.02996233/v1","title":"On Robustness of the Explanatory Power of Machine Learning Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Suncor Energy Incorporated","keywords":"Computer science; Machine learning; Robustness (evolution); Artificial intelligence; Explanatory power; Decision tree; Predictive power; Suite; Hyperparameter; Random forest; Initialization; Data mining","score_opus":0.04586587803864699,"score_gpt":0.26702536164807056,"score_spread":0.22115948360942356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392857185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12243952,0.00083856715,0.828854,0.0012009436,0.0029590237,0.00048343485,0.000013228105,0.00024699676,0.04296429],"genre_scores_gemma":[0.9945671,0.000022193033,0.0033254225,0.000070663686,0.00002593552,0.000015367768,0.0000013200233,0.000019752673,0.0019522464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980713,0.00015097861,0.00047796092,0.0005357448,0.0005392456,0.0002247608],"domain_scores_gemma":[0.99804676,0.00020143652,0.00025576484,0.001271263,0.00017879315,0.00004597898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055722287,0.00022526195,0.0003273131,0.00019688063,0.000057263904,0.00006923852,0.002180873,0.00017635214,0.00008505418],"category_scores_gemma":[0.0000897522,0.00015207822,0.00022571611,0.0003309279,0.000097373864,0.000114351875,0.003697019,0.00096713786,0.00002683256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040123055,0.000036095178,0.000009531363,0.00010485215,0.00002362469,0.0000033296737,0.0010016366,0.640438,0.0001221818,0.35714272,0.0002746874,0.0008392864],"study_design_scores_gemma":[0.000017757488,0.0000423036,0.0000063594675,0.00028228774,0.000008488432,0.0000017424494,0.00013460779,0.821083,0.033951286,0.14425622,0.000070355054,0.00014555184],"about_ca_topic_score_codex":0.00035162293,"about_ca_topic_score_gemma":0.000051188308,"teacher_disagreement_score":0.8721276,"about_ca_system_score_codex":0.00005968628,"about_ca_system_score_gemma":0.0002084586,"threshold_uncertainty_score":0.620157},"labels":[],"label_agreement":null},{"id":"W4392864805","doi":"10.1145/3624730","title":"Who Determines What Is Relevant? Humans or AI? Why Not Both?","year":2024,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Australian Research Council","keywords":"Relevance (law); Computer science; Artificial intelligence; Data science; Political science","score_opus":0.09904252942343997,"score_gpt":0.36195128891134437,"score_spread":0.2629087594879044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392864805","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014655354,0.01376154,0.022302724,0.9428486,0.0015177303,0.00072002184,0.000018341423,0.00053135527,0.0036442974],"genre_scores_gemma":[0.846299,0.008057443,0.12820202,0.011082204,0.00008949173,0.00010715424,0.0000034456366,0.000044366596,0.0061148615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872684,0.00017220993,0.00037178415,0.00027716096,0.00023677795,0.00021522296],"domain_scores_gemma":[0.96639377,0.00088233035,0.00009361803,0.032425553,0.00016092914,0.000043816686],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00041619374,0.00012982571,0.00016079747,0.0001197524,0.00042024214,0.000645511,0.04197902,0.000060079936,0.00003847187],"category_scores_gemma":[0.0018684497,0.00009022733,0.00013583325,0.00083442725,0.00032327767,0.0016276995,0.020539943,0.00026470076,0.00017231936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002164944,0.00030561167,0.00032105364,0.0002030923,0.00014262664,0.000010459554,0.028123425,0.00014540365,0.015284537,0.4623253,0.34771895,0.14539789],"study_design_scores_gemma":[0.00007113638,0.00009423602,0.00031071066,0.0010073073,0.000044079923,0.000025300697,0.0010292644,0.08298206,0.12018955,0.39076385,0.4031208,0.00036170546],"about_ca_topic_score_codex":0.00012569755,"about_ca_topic_score_gemma":0.00033645064,"teacher_disagreement_score":0.93176645,"about_ca_system_score_codex":0.000048229125,"about_ca_system_score_gemma":0.00011689525,"threshold_uncertainty_score":0.98738176},"labels":[],"label_agreement":null},{"id":"W4392902614","doi":"10.1109/icassp48485.2024.10446745","title":"Multi-Modal GPT-4 Aided Action Planning and Reasoning for Self-driving Vehicles","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Transparency (behavior); Modal; Action (physics); Artificial intelligence; Monocular; Natural language; Graph; Work (physics); Human–computer interaction; Machine learning; Computer security; Engineering; Theoretical computer science","score_opus":0.06094233051468072,"score_gpt":0.34600985819112495,"score_spread":0.2850675276764442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392902614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15514404,0.0003574285,0.8420564,0.0004850119,0.00043228487,0.00018984161,5.2783366e-7,0.0009058965,0.00042858263],"genre_scores_gemma":[0.72219634,0.000011762047,0.27714038,0.00008268177,0.000097946104,0.000028443588,8.377154e-7,0.000012805167,0.00042881942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885404,0.000029761357,0.00019231906,0.0004609398,0.00013889359,0.0003240596],"domain_scores_gemma":[0.99926853,0.0003491062,0.000032318723,0.00020960353,0.000055757886,0.00008471043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004097148,0.00012775062,0.00011338111,0.00013896404,0.0002630977,0.00068032,0.0002672489,0.000064871274,0.0000055034243],"category_scores_gemma":[0.000104738814,0.00011856502,0.00004642144,0.0002663412,0.000022467322,0.0012027355,0.00015180101,0.00012605403,0.000031087147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032554515,0.00017952581,0.0092824735,0.000546523,0.00019303456,0.00017707245,0.027171573,0.006077736,0.18604113,0.44999343,0.0030310906,0.31727386],"study_design_scores_gemma":[0.000060792656,0.000056225086,0.0010202992,0.00011568028,0.000007147129,0.000022812907,0.00057033985,0.9441085,0.048944198,0.002038606,0.0028901661,0.0001652758],"about_ca_topic_score_codex":0.00007329872,"about_ca_topic_score_gemma":0.000040764913,"teacher_disagreement_score":0.9380307,"about_ca_system_score_codex":0.00006461517,"about_ca_system_score_gemma":0.00005258671,"threshold_uncertainty_score":0.6560342},"labels":[],"label_agreement":null},{"id":"W4392940468","doi":"10.31222/osf.io/bs5xe","title":"Is Ockham’s razor losing its edge? New perspectives on the principle of model parsimony","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"John Templeton Foundation; Nokia Foundation; UK Research and Innovation; National Science Foundation","keywords":"Occam's razor; occam; Interpretability; Computer science; Context (archaeology); Scientific modelling; Artificial intelligence; Machine learning; Overfitting; Data science; Perspective (graphical); Management science; Artificial neural network; Epistemology; Mathematics; Statistics; Paleontology","score_opus":0.11704041179342542,"score_gpt":0.34603160942478095,"score_spread":0.22899119763135553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392940468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05775029,0.002754025,0.8566397,0.022865172,0.0013203702,0.0012233268,0.000022389802,0.0005301662,0.056894578],"genre_scores_gemma":[0.96112186,0.0002522205,0.018887032,0.0008582452,0.00024817704,0.000041440737,0.0000011863414,0.000044329296,0.018545512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703604,0.00009119405,0.00053330074,0.001216032,0.00065558363,0.00046786177],"domain_scores_gemma":[0.997348,0.00026335256,0.00022130074,0.0016938313,0.0003286359,0.00014487932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005934136,0.0004046481,0.00039900804,0.00024220781,0.00015459013,0.000499761,0.0025587978,0.00023617208,0.00017553226],"category_scores_gemma":[0.00021679829,0.00028539862,0.00032540725,0.00048509295,0.00010271898,0.00021201017,0.0043451255,0.0009454604,0.0006124539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009634357,0.000096909964,0.0000057085654,0.00010266652,0.000078999445,0.000009778703,0.015091275,0.046007298,0.000696109,0.92560387,0.009828551,0.0024692253],"study_design_scores_gemma":[0.00002113459,0.00004155224,0.0000046930745,0.00024814473,0.000017466158,0.0000015599855,0.0008992669,0.71331155,0.11336138,0.17096344,0.0008657301,0.00026405248],"about_ca_topic_score_codex":0.00020041183,"about_ca_topic_score_gemma":0.000028926186,"teacher_disagreement_score":0.9033716,"about_ca_system_score_codex":0.00023424679,"about_ca_system_score_gemma":0.00089274894,"threshold_uncertainty_score":0.9999598},"labels":[],"label_agreement":null},{"id":"W4393032343","doi":"10.2139/ssrn.4734082","title":"A Genealogical Approach to Algorithmic Bias","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"","keywords":"Computer science; Econometrics; Mathematics","score_opus":0.03967042808834473,"score_gpt":0.2806421010334069,"score_spread":0.2409716729450622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393032343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009451558,0.0036583613,0.9785371,0.0025571422,0.0005677132,0.00017500721,6.621191e-7,0.0002669224,0.0047855442],"genre_scores_gemma":[0.9664144,0.00088497263,0.028554484,0.00056983065,0.0008262583,0.000030065965,0.000001189412,0.000031062154,0.002687737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958081,0.00013081024,0.00034812282,0.0005214672,0.00045971372,0.0027317328],"domain_scores_gemma":[0.9991747,0.00008509247,0.000044579858,0.00037164745,0.00009185418,0.00023210583],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025338049,0.00019733478,0.00018285666,0.00030825558,0.0002538477,0.0007744075,0.0014145994,0.000086197644,0.00001341855],"category_scores_gemma":[0.000090575995,0.00015895,0.00015799612,0.0011082739,0.000034943958,0.0006144658,0.00021147927,0.0017126077,0.0008603738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004046262,0.000053890544,0.000010675239,0.0000048002057,0.00004457964,0.0000363475,0.00051878573,0.00051913585,0.00052003376,0.84411794,0.00046651994,0.15370323],"study_design_scores_gemma":[0.00008373314,0.0005843077,0.00003099684,0.000031536394,0.000014720628,0.003252772,0.0008805422,0.16037962,0.0019146921,0.80594367,0.02646723,0.00041616897],"about_ca_topic_score_codex":0.00005371854,"about_ca_topic_score_gemma":0.00005905407,"teacher_disagreement_score":0.9569628,"about_ca_system_score_codex":0.0009625875,"about_ca_system_score_gemma":0.0019354754,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W4393034238","doi":"10.21203/rs.3.rs-3871667/v1","title":"Enhancing High-School Dropout Identification: A Collaborative Approach Integrating Human and Machine Insights","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dropout (neural networks); Identification (biology); School dropout; Computer science; Mathematics education; Machine learning; Data science; Artificial intelligence; Psychology; Sociology; Biology","score_opus":0.06382890692652238,"score_gpt":0.38847375005972207,"score_spread":0.3246448431331997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393034238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24472892,0.022713019,0.68928045,0.0047177565,0.0019960098,0.007332228,0.00015492535,0.0016228738,0.027453795],"genre_scores_gemma":[0.9789064,0.00020813066,0.01738462,0.00003065378,0.0004181913,0.00072728004,0.000096630894,0.000057034456,0.0021710873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99361753,0.0011452321,0.000854995,0.0019473113,0.0016272474,0.00080765435],"domain_scores_gemma":[0.99531573,0.00047735908,0.00021713585,0.0017647062,0.0018214447,0.0004036295],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003304412,0.00045317182,0.00052011496,0.001154717,0.0010732705,0.003996646,0.002088234,0.00038507226,0.00004549626],"category_scores_gemma":[0.0011074926,0.00040631066,0.000109313616,0.0024161446,0.00035730485,0.00056921685,0.006872423,0.0035222392,0.00036831634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018955361,0.00026352334,0.00016012383,0.0031633156,0.00016516991,0.0002498193,0.031202123,0.00041322506,0.032992397,0.92023414,0.0018136004,0.009323602],"study_design_scores_gemma":[0.00020410646,0.00041228978,0.00043625614,0.0030143613,0.000033349475,0.00002401169,0.015510909,0.22125793,0.16466397,0.5913708,0.0018178907,0.0012541241],"about_ca_topic_score_codex":0.0016646113,"about_ca_topic_score_gemma":0.0010957059,"teacher_disagreement_score":0.7341775,"about_ca_system_score_codex":0.0006577641,"about_ca_system_score_gemma":0.0010996946,"threshold_uncertainty_score":0.9998389},"labels":[],"label_agreement":null},{"id":"W4393090174","doi":"10.1007/978-3-031-56069-9_20","title":"eval-rationales: An End-to-End Toolkit to Explain and Evaluate Transformers-Based Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de Recherche du Québec - Santé","keywords":"Interpretability; Computer science; Transformer; Artificial intelligence; End-to-end principle; Machine learning; Data science; Software engineering; Engineering","score_opus":0.04916689337903857,"score_gpt":0.30262714349460706,"score_spread":0.2534602501155685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393090174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010118653,0.00036155197,0.98832524,0.0044975383,0.0012761385,0.0011037635,0.000026187914,0.00025059067,0.003147114],"genre_scores_gemma":[0.48438564,0.00003409334,0.50643355,0.007440734,0.0005467195,0.00011665433,0.000017556138,0.00009818701,0.00092684565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99368095,0.00007415668,0.0007463442,0.0026500586,0.0018641569,0.0009843165],"domain_scores_gemma":[0.9968401,0.0006207649,0.00011732481,0.0013374458,0.00045213784,0.00063221925],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0023488558,0.0007324776,0.000586314,0.0016888964,0.00040016588,0.0015834862,0.003001995,0.00029637577,0.00007125084],"category_scores_gemma":[0.000101353246,0.0006900328,0.0001380535,0.0012754184,0.0004974104,0.0017498726,0.00074532506,0.00070899795,0.00024743838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018429924,0.000029861547,0.0000023021773,0.000052591324,0.000010614638,0.000085917694,0.0043870923,0.48211497,0.0009180076,0.09526249,0.000020025716,0.41709772],"study_design_scores_gemma":[0.00008019485,0.00045594337,0.0000051916595,0.00034823015,0.000012195351,0.000024884459,0.0000027207248,0.7210269,0.0062973993,0.26994404,0.0011536382,0.0006486516],"about_ca_topic_score_codex":0.00008898941,"about_ca_topic_score_gemma":0.00068780803,"teacher_disagreement_score":0.4833738,"about_ca_system_score_codex":0.0005054542,"about_ca_system_score_gemma":0.0011640372,"threshold_uncertainty_score":0.9995551},"labels":[],"label_agreement":null},{"id":"W4393156965","doi":"10.1002/asi.24889","title":"<scp>Human‐centered</scp> explainable artificial intelligence: An Annual Review of Information Science and Technology (ARIST) paper","year":2024,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Information science; Data science; Artificial intelligence; Library science","score_opus":0.016856579980316554,"score_gpt":0.29734359588468207,"score_spread":0.28048701590436553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393156965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37033275,0.012861124,0.4215646,0.15426698,0.0107367635,0.006829164,0.00021278014,0.0014571338,0.021738691],"genre_scores_gemma":[0.993342,0.001476695,0.0042595966,0.00079190946,0.000046012392,0.000029588287,0.00000203042,0.0000052093733,0.00004698109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99669135,0.000034607838,0.0012339589,0.00019789649,0.0014003213,0.00044189158],"domain_scores_gemma":[0.9909239,0.0001891677,0.0013578088,0.00040694213,0.0070257974,0.00009642699],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008981952,0.00014461814,0.0002808357,0.0027402255,0.00082792394,0.00070743274,0.0019383124,0.00018756026,0.0000019200563],"category_scores_gemma":[0.00958577,0.00010872337,0.000053849548,0.008442569,0.0010496454,0.024852706,0.0005313387,0.00036617543,0.0000113184915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023820567,0.000029665862,0.00025779766,0.00038552392,0.000014801329,5.569039e-7,0.002711809,0.000024328257,0.003115558,0.85314745,0.0011465502,0.13916355],"study_design_scores_gemma":[0.00029835242,0.0016024723,0.00064765924,0.0026908508,0.00009939328,0.0004012027,0.02544575,0.038109627,0.22528699,0.37997133,0.32507473,0.00037164107],"about_ca_topic_score_codex":0.0000079194815,"about_ca_topic_score_gemma":0.000004737315,"teacher_disagreement_score":0.6230092,"about_ca_system_score_codex":0.00054855825,"about_ca_system_score_gemma":0.0012147813,"threshold_uncertainty_score":0.9987569},"labels":[],"label_agreement":null},{"id":"W4393213693","doi":"10.1145/3639476.3639759","title":"XAIport: A Service Framework for the Early Adoption of XAI in AI Model Development","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cloud computing; Quality (philosophy); Trustworthiness; Computer security","score_opus":0.06778259794620865,"score_gpt":0.32609750242101593,"score_spread":0.25831490447480726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393213693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01681977,0.00027791344,0.9741027,0.006389162,0.0007141773,0.000980281,0.000004848168,0.00014177142,0.00056937407],"genre_scores_gemma":[0.5234649,0.000030942167,0.4741831,0.0012582932,0.000060815237,0.0004819906,0.0000051542293,0.00002333733,0.00049145985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776095,0.000033858676,0.00071185146,0.0007095484,0.0004131518,0.00037065812],"domain_scores_gemma":[0.99802035,0.0003008366,0.00018119342,0.0010615478,0.00037768233,0.000058382066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009271882,0.0002616266,0.00029474671,0.00021888727,0.00008126789,0.00029240487,0.0019321388,0.00033488014,0.000012178418],"category_scores_gemma":[0.000077763776,0.00019875912,0.00011750867,0.0006259261,0.0000312504,0.00018681788,0.0025313043,0.0008117399,0.000117623684],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015362977,0.00008045514,0.000055719756,0.00047638634,0.000048874383,0.000004731704,0.013229705,0.24438953,0.000060521314,0.71720344,0.00026757392,0.024167685],"study_design_scores_gemma":[0.000016336317,0.000012343375,0.000107518936,0.0002890434,0.000007740691,5.7559885e-7,0.00013812543,0.5967112,0.003787103,0.3985167,0.00025894927,0.00015430075],"about_ca_topic_score_codex":0.0006742244,"about_ca_topic_score_gemma":0.0010762272,"teacher_disagreement_score":0.50664514,"about_ca_system_score_codex":0.00016674324,"about_ca_system_score_gemma":0.0008548116,"threshold_uncertainty_score":0.8105162},"labels":[],"label_agreement":null},{"id":"W4393346483","doi":"10.1016/j.teler.2024.100135","title":"Preserving paradata for accountability of semi-autonomous AI agents in dynamic environments: An archival perspective","year":2024,"lang":"en","type":"article","venue":"Telematics and Informatics Reports","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Perspective (graphical); Accountability; Computer science; Human–computer interaction; Multimedia; Artificial intelligence; Political science; Law","score_opus":0.031713037233477175,"score_gpt":0.33737339101267105,"score_spread":0.30566035377919387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393346483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4578922,0.00011917237,0.5391304,0.00018120809,0.00020344135,0.0008808897,0.000021091158,0.00006450685,0.0015070792],"genre_scores_gemma":[0.96402186,0.000055205695,0.035693105,0.0000758622,0.00001116366,0.000047933343,0.000017967941,0.000011643289,0.00006528391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979199,0.000029385857,0.0011837741,0.0002574706,0.00031448802,0.00029498563],"domain_scores_gemma":[0.9985407,0.00018555927,0.00028243946,0.00084176403,0.00006160432,0.00008796319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011651252,0.00016640555,0.0002844003,0.00019248918,0.00007398208,0.0002887803,0.00041857196,0.000054243483,0.000008419626],"category_scores_gemma":[0.00020998305,0.0001527779,0.000055119486,0.00023097725,0.00008680607,0.0022390631,0.000371503,0.00015835732,0.0000028443908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000651789,0.0019063444,0.008945058,0.012154752,0.0004391478,0.00041739535,0.39299822,0.044719227,0.0021553456,0.4208281,0.0014217922,0.11394945],"study_design_scores_gemma":[0.000044656477,0.00010402499,0.0010448238,0.00013706785,0.000010869679,0.0000682667,0.0025943203,0.90048385,0.0010110134,0.09353249,0.00080974965,0.00015886831],"about_ca_topic_score_codex":0.00012678716,"about_ca_topic_score_gemma":0.000055818884,"teacher_disagreement_score":0.8557646,"about_ca_system_score_codex":0.00016867713,"about_ca_system_score_gemma":0.00012549607,"threshold_uncertainty_score":0.62301016},"labels":[],"label_agreement":null},{"id":"W4394782008","doi":"10.1145/3613904.3642934","title":"Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Dilemma; Computer science; Artificial intelligence; Natural language processing; Human–machine system; Cognitive science; Machine learning; Epistemology; Psychology; Philosophy","score_opus":0.08759386332772177,"score_gpt":0.33596353880249485,"score_spread":0.24836967547477307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394782008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20638551,0.00059461914,0.7903651,0.0005446076,0.0003666996,0.00096816616,0.00007029673,0.000081537284,0.0006234891],"genre_scores_gemma":[0.99670786,0.000023398874,0.002623344,0.0000391388,0.00005312532,0.000457109,0.0000132387,0.000020515772,0.000062251704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838054,0.00024910423,0.00041497353,0.00044841476,0.00026215598,0.0002447964],"domain_scores_gemma":[0.9974342,0.0012872155,0.00014037415,0.00088542886,0.00021938355,0.000033401066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024966176,0.0002039169,0.00030367987,0.00016289241,0.0002241629,0.00016082624,0.0011914268,0.00007491501,0.0000050005024],"category_scores_gemma":[0.0001380182,0.000120581666,0.00014714444,0.00025770615,0.000076513046,0.00024998936,0.0020330558,0.0004294884,0.0000017389725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009440129,0.00003867895,0.000027946815,0.0006876977,0.0000699795,0.0000021290527,0.009415229,0.01862338,0.0023812747,0.96726286,0.000016463619,0.0014649126],"study_design_scores_gemma":[0.00007783267,0.000056395755,0.00011268769,0.00048721692,0.00004385447,0.0000021828785,0.0019865665,0.5334286,0.10356676,0.36002666,0.000039707782,0.00017152121],"about_ca_topic_score_codex":0.0017145409,"about_ca_topic_score_gemma":0.00060775125,"teacher_disagreement_score":0.79032236,"about_ca_system_score_codex":0.000035391546,"about_ca_system_score_gemma":0.000085685555,"threshold_uncertainty_score":0.49171776},"labels":[],"label_agreement":null},{"id":"W4395109821","doi":"10.2139/ssrn.4805663","title":"Human Performance Effects of Combining Counterfactual Explanations with Normative and Contrastive Explanations in Supervised Machine Learning for Automated Decision Assistance","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Normative; Artificial intelligence; Computer science; Machine learning; Contrastive analysis; Psychology; Cognitive psychology; Natural language processing; Social psychology; Epistemology; Linguistics; Philosophy","score_opus":0.011385047574780942,"score_gpt":0.2713207258632177,"score_spread":0.2599356782884368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395109821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5761429,0.0015770545,0.42123738,0.00014138853,0.00017809811,0.0005283106,0.000010243658,0.000116650655,0.00006799007],"genre_scores_gemma":[0.9961746,0.00072001904,0.0028373532,0.000017143106,0.000031797605,0.00010905777,0.00002332489,0.000029574703,0.000057144738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713284,0.00016837292,0.0006591308,0.00047376135,0.00042349318,0.0011423927],"domain_scores_gemma":[0.99803644,0.00080748036,0.00045174602,0.00022848188,0.00039776159,0.00007810128],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015855557,0.00032325642,0.00047918566,0.00062975904,0.0004199157,0.0002910528,0.00065228104,0.00014802911,0.0000018389128],"category_scores_gemma":[0.00022158683,0.00028512313,0.00007508437,0.00043400703,0.00009581927,0.000548106,0.00031399576,0.0028675825,0.0000027603212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008359719,0.0007740059,0.008915818,0.002110665,0.0017261084,0.00011072942,0.05261634,0.29593903,0.0045387205,0.5685178,0.000121277146,0.06379355],"study_design_scores_gemma":[0.0010067065,0.0012210424,0.0013983065,0.0017730424,0.000061270446,0.00010324669,0.0020897028,0.9062408,0.0027146933,0.08300287,0.000013841426,0.00037442928],"about_ca_topic_score_codex":0.00012243613,"about_ca_topic_score_gemma":0.0025810655,"teacher_disagreement_score":0.6103018,"about_ca_system_score_codex":0.0009477136,"about_ca_system_score_gemma":0.0014493802,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W4396234746","doi":"10.1109/aihcir61661.2023.00056","title":"Structural Segmentation and Large Language Model Make Behavior Tree More Explainable","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Modular design; Tree (set theory); Robot; Machine learning; Robotics; Task (project management); Natural language; Segmentation; Field (mathematics); Reuse; Human–computer interaction; Engineering; Systems engineering; Programming language","score_opus":0.03308277149821073,"score_gpt":0.3156483097816421,"score_spread":0.2825655382834314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396234746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.840418,0.000038803817,0.156799,0.00051109656,0.00011803633,0.00026058836,0.0000077864315,0.0005059364,0.0013407688],"genre_scores_gemma":[0.9745635,0.000009400254,0.019006513,0.0003131541,0.000029435927,0.00007527286,0.00002020738,0.000013553792,0.005969009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987029,0.000027196324,0.00018897152,0.0003803386,0.0002610096,0.00043959086],"domain_scores_gemma":[0.99937975,0.000039677056,0.00004310913,0.00038428666,0.000052916497,0.00010022939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022490184,0.00013672584,0.00011687584,0.00015496423,0.000288831,0.0002921579,0.0003868861,0.000053395644,0.000040568466],"category_scores_gemma":[0.000023805078,0.00012385868,0.000034640474,0.0005177889,0.00004240997,0.0007256844,0.00031567624,0.0000853636,0.000119136916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003126541,0.00017117002,0.011515048,0.00011312448,0.00004248473,0.0008592755,0.07947752,0.014847526,0.0966429,0.40546647,0.0059056845,0.38492754],"study_design_scores_gemma":[0.00014195738,0.000033803055,0.0018923974,0.000004459916,0.000006170533,0.000011864701,0.0061401627,0.9521021,0.036729656,0.0026628987,0.000086327644,0.0001881807],"about_ca_topic_score_codex":0.0001643786,"about_ca_topic_score_gemma":0.0003747813,"teacher_disagreement_score":0.9372546,"about_ca_system_score_codex":0.000041342446,"about_ca_system_score_gemma":0.000037397276,"threshold_uncertainty_score":0.50508106},"labels":[],"label_agreement":null},{"id":"W4396598857","doi":"10.1111/2041-210x.14325","title":"Harnessing large language models for coding, teaching and inclusion to empower research in ecology and evolution","year":2024,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Coding (social sciences); Computer science; Social science; Sociology","score_opus":0.08054531930976476,"score_gpt":0.4658574914980209,"score_spread":0.38531217218825614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396598857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42155686,0.0011414409,0.5752587,0.0012443851,0.00030173038,0.00028826497,0.0000013774466,0.00003549538,0.0001717593],"genre_scores_gemma":[0.7749746,0.00003760986,0.22468248,0.00010182984,0.000040054212,0.00007920136,0.0000013111154,0.000007596787,0.00007531756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966929,0.0017542279,0.00029136782,0.0006082928,0.000110501045,0.000542728],"domain_scores_gemma":[0.9977758,0.001886112,0.000032760992,0.00017368722,0.00005764004,0.000074031144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014528626,0.0001158841,0.00021253187,0.00085360743,0.0010229064,0.00009566348,0.00020469073,0.00024113651,0.0000020239872],"category_scores_gemma":[0.0010401228,0.00011797114,0.000017596181,0.0004995679,0.00011774907,0.0007264609,0.0019431323,0.0005477506,0.0000023728337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010835951,0.00016351335,0.033378363,0.00025562244,0.000012955353,0.000064187625,0.061594076,0.0018013779,0.0218191,0.7364873,0.00016968093,0.14414543],"study_design_scores_gemma":[0.00015009081,0.00017653454,0.026192553,0.00008054407,0.0000032352839,0.000020124757,0.0014905735,0.672491,0.0004105393,0.29857418,0.00029895993,0.00011167662],"about_ca_topic_score_codex":0.00038793427,"about_ca_topic_score_gemma":0.0031370712,"teacher_disagreement_score":0.67068964,"about_ca_system_score_codex":0.0004154639,"about_ca_system_score_gemma":0.00009089971,"threshold_uncertainty_score":0.7867472},"labels":[],"label_agreement":null},{"id":"W4396673247","doi":"10.1038/s41598-024-60743-x","title":"Pseudo-class part prototype networks for interpretable breast cancer classification","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Metric (unit); Class (philosophy); Deep learning","score_opus":0.03085558344980622,"score_gpt":0.3026203385397177,"score_spread":0.2717647550899115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396673247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061031044,0.0008716278,0.9399227,0.0040379106,0.04257916,0.0023543837,0.000011884929,0.0009086689,0.0032105837],"genre_scores_gemma":[0.98263055,0.000024395778,0.0041299365,0.0001352733,0.00053031824,0.0016477272,0.000030373514,0.000037779988,0.010833631],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99658966,0.000054963195,0.0006838533,0.0015230721,0.0004942989,0.0006541319],"domain_scores_gemma":[0.99760526,0.00010193012,0.0002038673,0.0014445964,0.0004677136,0.00017662342],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022064454,0.00021448119,0.00020665064,0.00024194882,0.00049430825,0.0026776385,0.0006821436,0.000113749804,0.00014493718],"category_scores_gemma":[0.00009256601,0.0001901036,0.0001589553,0.0014947915,0.00020421496,0.0014831729,0.00019212435,0.00019173793,0.000105350875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006817062,0.00030361753,0.0016909738,0.0004602298,0.00015072894,0.00056596386,0.0025742035,0.012584598,0.030072397,0.17805664,0.42508292,0.34838954],"study_design_scores_gemma":[0.00002051461,0.00003433742,0.00009112342,0.00019561227,0.000014596483,0.00019736208,0.0000486568,0.7239854,0.007453205,0.024131967,0.24358374,0.0002435455],"about_ca_topic_score_codex":0.00006685078,"about_ca_topic_score_gemma":0.00007813111,"teacher_disagreement_score":0.97652745,"about_ca_system_score_codex":0.00020920763,"about_ca_system_score_gemma":0.0005158505,"threshold_uncertainty_score":0.99835765},"labels":[],"label_agreement":null},{"id":"W4396786982","doi":"10.1145/3630106.3658955","title":"Machine learning data practices through a data curation lens: An evaluation framework","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data curation; Rubric; Computer science; Data science; Transparency (behavior); Documentation; Best practice; Machine learning; Artificial intelligence; Knowledge management","score_opus":0.498315670419755,"score_gpt":0.48841087690354146,"score_spread":0.00990479351621354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396786982","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006041442,0.0038026383,0.9739664,0.008931396,0.002547112,0.00093442306,0.000098995144,0.0008732797,0.008241594],"genre_scores_gemma":[0.2897741,0.0017192763,0.69674146,0.00087792025,0.0013350112,0.00010530339,0.008777655,0.000076626726,0.0005926479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99368405,0.00097617815,0.0006925885,0.002910121,0.0013353382,0.00040174753],"domain_scores_gemma":[0.9877489,0.0006844898,0.0009228157,0.010129569,0.0004379505,0.000076249875],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0062581375,0.0003832755,0.000319047,0.00016412031,0.00030962843,0.0032290146,0.009856921,0.0004083749,0.00028564205],"category_scores_gemma":[0.0074705333,0.00035488204,0.000041125022,0.00061190844,0.00006008376,0.013516544,0.027430646,0.0023611535,0.00079650735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026128977,0.00035044292,0.00014631619,0.00043275423,0.00024250786,0.00006286088,0.00952951,0.045316026,0.00020116953,0.632741,0.00674104,0.30421028],"study_design_scores_gemma":[0.000018626819,0.00004765346,0.0000056594713,0.00018879795,0.00009013442,0.0000084671765,0.00030797702,0.7113247,0.000247897,0.26480526,0.02265826,0.00029658922],"about_ca_topic_score_codex":0.0045579723,"about_ca_topic_score_gemma":0.0018432148,"teacher_disagreement_score":0.66600865,"about_ca_system_score_codex":0.00014587528,"about_ca_system_score_gemma":0.0009032907,"threshold_uncertainty_score":0.99998146},"labels":[],"label_agreement":null},{"id":"W4396817440","doi":"10.1109/tcc.2024.3398609","title":"An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cloud Computing","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cloud computing; Computer science; Trustworthiness; Architecture; World Wide Web; Computer security; Data science; Software engineering; Operating system","score_opus":0.02158993656709975,"score_gpt":0.31347719339672814,"score_spread":0.2918872568296284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396817440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09671965,0.00004791066,0.8959414,0.003664349,0.002535299,0.0004928532,0.000012954295,0.00024761137,0.00033802152],"genre_scores_gemma":[0.99102145,0.0000046351656,0.0071658646,0.0013466432,0.00030522322,0.000023704404,0.0000020398218,0.000026083038,0.00010436219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979202,0.00020928137,0.00044321155,0.000636495,0.0004188869,0.00037189084],"domain_scores_gemma":[0.9984151,0.00039036162,0.00008317646,0.00087441923,0.00011102577,0.00012589342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007260997,0.00022571496,0.00022219107,0.00023015784,0.0004936055,0.0010186217,0.0024242173,0.00007546171,0.000027611708],"category_scores_gemma":[0.0000045302863,0.00017438806,0.00010290986,0.0013219063,0.00005140015,0.000706245,0.000035437082,0.00043886225,0.0000908191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030915002,0.00013521065,0.000006629349,0.00006318562,0.00004879941,0.000013103028,0.0117314225,0.76308227,0.0025622712,0.018613197,0.00015982514,0.20355316],"study_design_scores_gemma":[0.00010107604,0.00041321668,0.00005188315,0.00031701094,0.000027600854,0.00002754497,0.000995132,0.9011484,0.0858715,0.007142431,0.0035679576,0.00033624904],"about_ca_topic_score_codex":0.00074766035,"about_ca_topic_score_gemma":0.0007001616,"teacher_disagreement_score":0.8943018,"about_ca_system_score_codex":0.0000741478,"about_ca_system_score_gemma":0.000116016534,"threshold_uncertainty_score":0.9822593},"labels":[],"label_agreement":null},{"id":"W4396827212","doi":"10.1145/3613904.3642689","title":"Incremental XAI: Memorable Understanding of AI with Incremental Explanations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Interpretability; Salient; Formative assessment; USable; Schema (genetic algorithms); Partition (number theory); Knowledge base; Artificial intelligence; Machine learning; Psychology; World Wide Web; Mathematics; Mathematics education","score_opus":0.06380983511256992,"score_gpt":0.2959201789090633,"score_spread":0.23211034379649337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396827212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02083178,0.0001010869,0.93294823,0.0020994772,0.00027446158,0.00021814425,0.0000050492044,0.00030089857,0.04322086],"genre_scores_gemma":[0.98382217,0.000008068827,0.01521542,0.0002748505,0.000031820506,0.0000142127155,0.0000043655223,0.000012072863,0.0006170204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998611,0.000038889888,0.00027229276,0.00035202896,0.00043981455,0.00028602217],"domain_scores_gemma":[0.99938923,0.000108630775,0.000039168648,0.0003235442,0.000060566985,0.00007884129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003534977,0.00013306865,0.00013506472,0.00026484084,0.00017031327,0.00031084116,0.00050555187,0.000036265035,0.0003280495],"category_scores_gemma":[0.000013684167,0.00010930393,0.00004457503,0.00088600913,0.00009164259,0.001433366,0.00018849052,0.0001393911,0.0001218828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007092164,0.000055682787,0.00047288163,0.00003516838,0.00004815955,0.00004327138,0.0011736355,0.00029614344,0.010351317,0.98336214,0.0033619297,0.00079259934],"study_design_scores_gemma":[0.00023113191,0.00049388706,0.000076296106,0.00023841589,0.000030024981,0.000074952644,0.011218776,0.21092005,0.7167972,0.057144538,0.0022871508,0.0004876177],"about_ca_topic_score_codex":0.0006254497,"about_ca_topic_score_gemma":0.0005714749,"teacher_disagreement_score":0.9629904,"about_ca_system_score_codex":0.00031525063,"about_ca_system_score_gemma":0.00016347335,"threshold_uncertainty_score":0.44572848},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.034325354910127136,"score_gpt":0.3172028789804958,"score_spread":0.2828775240703687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396833700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027358849,0.00040832348,0.8793388,0.07957968,0.0004429597,0.00025282236,0.000005202633,0.0002305324,0.012382816],"genre_scores_gemma":[0.9902675,0.00009849432,0.0022821291,0.0006255548,0.00005632147,0.000039305844,0.0000013632507,0.000008374675,0.0066209235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885005,0.0000731172,0.00024160826,0.0003003079,0.00025885846,0.00027605167],"domain_scores_gemma":[0.9990113,0.0004081351,0.00002370599,0.00037956395,0.00012530042,0.000052016014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040068847,0.00010484631,0.00010993209,0.00019997022,0.00021143373,0.0007686863,0.0008232863,0.00004984811,0.00016445054],"category_scores_gemma":[0.00005649411,0.000074818374,0.00007117625,0.0009834724,0.00011305925,0.0012191107,0.00017103764,0.0002176775,0.00026585162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.9221817e-7,0.000028536158,0.000252688,0.000009014296,0.000008636779,0.0000084021785,0.0019806197,0.00037871493,0.0008612852,0.97430015,0.0116120465,0.010559044],"study_design_scores_gemma":[0.000063557054,0.00010782575,0.005165272,0.00011746608,0.000009148172,0.000019588597,0.009505549,0.8033332,0.0058152876,0.11062455,0.06491067,0.00032787083],"about_ca_topic_score_codex":0.0003054224,"about_ca_topic_score_gemma":0.0031795166,"teacher_disagreement_score":0.9629087,"about_ca_system_score_codex":0.000070041424,"about_ca_system_score_gemma":0.00013132245,"threshold_uncertainty_score":0.741246},"labels":[],"label_agreement":null},{"id":"W4398160873","doi":"10.1609/aaaiss.v3i1.31256","title":"The Impacts of Text-to-Image Generative AI on Creative Professionals According to Prospective Generative AI Researchers: Insights from Japan","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Generative grammar; Generative model; Psychology; Artificial intelligence; Computer science","score_opus":0.02575015745906898,"score_gpt":0.32340933341082173,"score_spread":0.29765917595175273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88797337,0.00043298345,0.0028590232,0.09419564,0.00086427724,0.0030846251,0.000057022597,0.00021650956,0.0103165405],"genre_scores_gemma":[0.98983926,0.000047871374,0.0059295557,0.0013384579,0.00027452066,0.0003841614,0.0000012996155,0.000043651366,0.0021412214],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99673045,0.00012544339,0.0006120693,0.00089022645,0.0010356514,0.0006061561],"domain_scores_gemma":[0.99650794,0.00060119067,0.00025837604,0.00049008935,0.0019104345,0.00023197572],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000775311,0.00039780483,0.00045124858,0.00030688389,0.0008815407,0.0011420221,0.0022384033,0.00011582701,0.00001086446],"category_scores_gemma":[0.0012445467,0.00022947125,0.00017067556,0.002120362,0.0004482467,0.0028279624,0.0015331539,0.0005788781,0.00007370676],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028909967,0.000100082834,0.00039479637,0.000060665538,0.00015473238,0.0000022674599,0.086552665,0.00008868236,0.6842115,0.22299573,0.004663326,0.00048643615],"study_design_scores_gemma":[0.00007378488,0.0008495909,0.000678965,0.0007666721,0.000019115272,0.0000027915562,0.015518862,0.0019607255,0.93251485,0.046647687,0.0007033184,0.00026363926],"about_ca_topic_score_codex":0.0003268723,"about_ca_topic_score_gemma":0.000095970645,"teacher_disagreement_score":0.24830332,"about_ca_system_score_codex":0.0003483989,"about_ca_system_score_gemma":0.00040490238,"threshold_uncertainty_score":0.9998949},"labels":[],"label_agreement":null},{"id":"W4398168828","doi":"10.2139/ssrn.4834834","title":"The Explainability Imperative","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Business","score_opus":0.009119315583850136,"score_gpt":0.26923839091446927,"score_spread":0.2601190753306191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398168828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033212874,0.016315196,0.9286986,0.0170749,0.0015363652,0.00020919078,5.1281586e-7,0.0002697327,0.0026826155],"genre_scores_gemma":[0.9934767,0.0030370615,0.0003626012,0.000105544066,0.0003185181,0.000016900824,2.0352313e-7,0.000013078181,0.0026694268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964592,0.00020587149,0.00030905032,0.00032936805,0.00034471104,0.0023518354],"domain_scores_gemma":[0.99886346,0.0003980392,0.000051579234,0.0004399817,0.00015710416,0.00008984818],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0042582257,0.00014984018,0.000108077744,0.00008014113,0.0009747401,0.0012242184,0.0013203527,0.000049766142,0.000011019125],"category_scores_gemma":[0.00021863212,0.000094219205,0.00013842346,0.0005616967,0.000109873254,0.0010361313,0.00015353179,0.0018891554,0.0002590786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045538995,0.000011807019,0.000019701296,0.0000020404564,0.000039970557,0.00001545395,0.0007917734,0.000036241392,0.0002191598,0.8592596,0.0002680213,0.13933167],"study_design_scores_gemma":[0.000032977525,0.00020937058,0.000023501269,0.000012352219,0.0000052487876,0.0005059851,0.0027046693,0.014484442,0.002437061,0.9553559,0.024092784,0.00013574705],"about_ca_topic_score_codex":0.000048162532,"about_ca_topic_score_gemma":0.00066026393,"teacher_disagreement_score":0.9602638,"about_ca_system_score_codex":0.0012790785,"about_ca_system_score_gemma":0.003152402,"threshold_uncertainty_score":0.9998126},"labels":[],"label_agreement":null},{"id":"W4398764826","doi":"10.1162/99608f92.f86474d0","title":"A Familiar, Invisible Engine Is Driving the AI Revolution","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Aeronautics; Psychology; Automotive engineering; Engineering","score_opus":0.06234315868469324,"score_gpt":0.3537710257510638,"score_spread":0.2914278670663705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398764826","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009748259,0.08522278,0.8624473,0.044370238,0.0018768648,0.001089006,0.000047845468,0.0006322328,0.0042162086],"genre_scores_gemma":[0.060891006,0.81604576,0.074855015,0.044802792,0.00078441453,0.00025029367,0.0000781731,0.00007508175,0.0022174877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648774,0.00012259507,0.000497275,0.001248897,0.0009891655,0.00065434945],"domain_scores_gemma":[0.99518174,0.00020992028,0.000082572886,0.0041378224,0.0002104397,0.00017750564],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006343241,0.00020494383,0.0002574095,0.00018718706,0.000575754,0.0013185566,0.00814305,0.00003507293,0.0002588726],"category_scores_gemma":[0.0012505536,0.00013532938,0.000082089595,0.0053066653,0.0004342335,0.0082205115,0.002836374,0.00033074623,0.0063350517],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4111852e-7,0.000026929709,0.000036031826,0.0009802855,0.000010675025,0.000031810872,0.00031810824,0.000017208624,0.001158578,0.1521634,0.18055229,0.6647043],"study_design_scores_gemma":[0.00000842393,0.000017092496,0.00005534928,0.0027518268,0.000017895127,0.000043459113,0.000015534344,0.21894854,0.0009498262,0.0024846096,0.77453864,0.00016882626],"about_ca_topic_score_codex":0.0000924201,"about_ca_topic_score_gemma":0.00002077043,"teacher_disagreement_score":0.78759235,"about_ca_system_score_codex":0.00014911921,"about_ca_system_score_gemma":0.00072117045,"threshold_uncertainty_score":0.9997182},"labels":[],"label_agreement":null},{"id":"W4399123777","doi":"10.4018/978-1-6684-8127-1.ch001","title":"A Comprehensive Review of Trustworthy, Ethical, and Explainable Computer Vision Advancements in Online Social Media","year":2024,"lang":"en","type":"review","venue":"Advances in information security, privacy, and ethics book series","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Trustworthiness; Social media; Ethical issues; Internet privacy; Engineering ethics; Psychology; Computer science; World Wide Web; Engineering","score_opus":0.0563179339493908,"score_gpt":0.3984399402121335,"score_spread":0.3421220062627427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399123777","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008731269,0.99368674,0.002381138,0.0020769457,0.0005741817,0.00087495346,0.000057565718,0.000065265405,0.00027446786],"genre_scores_gemma":[0.00002609068,0.9920692,0.005134462,0.0024092055,0.000080777434,0.00009448604,0.00015917863,0.000018020879,0.000008583517],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99588835,0.0004692744,0.0020021687,0.0005009734,0.0007109328,0.00042831583],"domain_scores_gemma":[0.9969989,0.0012630931,0.00075633626,0.00045167934,0.000432756,0.0000972343],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015588074,0.0005106406,0.0016263688,0.00059423025,0.00019937207,0.00024724362,0.000818908,0.0007253588,0.000009166566],"category_scores_gemma":[0.00061331404,0.00045442246,0.00014204896,0.0010247971,0.0005529193,0.008343988,0.0015876363,0.00265942,0.000014682211],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149370035,0.00004769056,0.0000014973044,0.23710993,0.000020395946,0.00002407443,0.023856707,0.000009162047,3.943315e-8,0.11765363,0.00046136425,0.62080055],"study_design_scores_gemma":[0.00012510973,0.00011516028,0.0000022514298,0.059721693,0.0000439202,0.00004449418,0.00065026566,0.0006053162,0.0000020249288,0.026163038,0.9121399,0.00038684445],"about_ca_topic_score_codex":0.000020088548,"about_ca_topic_score_gemma":0.00013614721,"teacher_disagreement_score":0.9116785,"about_ca_system_score_codex":0.00012462077,"about_ca_system_score_gemma":0.00037925175,"threshold_uncertainty_score":0.9997907},"labels":[],"label_agreement":null},{"id":"W4399286752","doi":"10.3390/bdcc8060058","title":"Enhancing Self-Supervised Learning through Explainable Artificial Intelligence Mechanisms: A Computational Analysis","year":2024,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning","score_opus":0.09645907606096538,"score_gpt":0.3265741638221873,"score_spread":0.23011508776122191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399286752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011872735,0.0010642329,0.98462266,0.00030481198,0.0005129762,0.00025914673,0.000031027277,0.00072613114,0.00060631],"genre_scores_gemma":[0.86294645,0.000047479967,0.13625011,0.0002540876,0.00025245346,0.000009637718,0.00018740805,0.00002245175,0.000029926923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632466,0.00029574905,0.00067309506,0.0015177461,0.00052707054,0.00066168164],"domain_scores_gemma":[0.99720186,0.0016442982,0.00013405386,0.0005273022,0.0003445373,0.00014797288],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014424461,0.00033866242,0.0004024766,0.0004642618,0.00088183687,0.00159528,0.0011518946,0.00010385155,0.000027474665],"category_scores_gemma":[0.00043907829,0.0003514838,0.00011446177,0.0029164604,0.00010172281,0.0016736988,0.001957934,0.0004560535,0.00015635042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001162978,0.000096193646,0.00007104599,0.00013685961,0.0006075683,0.00021933575,0.010118027,0.0045766737,0.00048448262,0.18146949,0.000017721995,0.80219096],"study_design_scores_gemma":[0.000035427383,0.00009259444,0.000040150535,0.00027274856,0.00026540313,0.00003278918,0.0061082765,0.9216929,0.005157444,0.06569115,0.00021118957,0.0003999156],"about_ca_topic_score_codex":0.000170888,"about_ca_topic_score_gemma":0.00008292349,"teacher_disagreement_score":0.9171162,"about_ca_system_score_codex":0.00006446715,"about_ca_system_score_gemma":0.00022624223,"threshold_uncertainty_score":0.9998937},"labels":[],"label_agreement":null},{"id":"W4399365260","doi":"10.1007/s43681-024-00482-x","title":"Automated ethical decision, value-ladenness, and the moral prior problem","year":2024,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Social Sciences and Humanities Research Council; Fonds de Recherche du Québec-Société et Culture; Université du Québec à Trois-Rivières","keywords":"Value (mathematics); Ethical decision; Psychology; Computer science; Social psychology","score_opus":0.03837206724161501,"score_gpt":0.3435417644443215,"score_spread":0.3051696972027065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399365260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027988393,0.005565593,0.55271155,0.40852213,0.0011618999,0.0006048499,0.0000033371514,0.0017165806,0.0017256484],"genre_scores_gemma":[0.9732754,0.00065720617,0.01645614,0.009262975,0.000089333524,0.000022825232,8.4784995e-7,0.000014399312,0.00022084182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839836,0.00025778977,0.00025639092,0.0004208257,0.00039243925,0.00027420736],"domain_scores_gemma":[0.99689734,0.00249078,0.000028119804,0.00034198372,0.00014262121,0.00009916168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002994874,0.00013417496,0.00015598812,0.0000624043,0.00046676304,0.0009668308,0.00044651082,0.0003997665,0.0000068885115],"category_scores_gemma":[0.00073173764,0.00008394415,0.000040189665,0.0004372237,0.0005298342,0.0003930847,0.0004033097,0.0017249823,0.00006808739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013617628,0.000008234224,0.000033608023,0.00005978913,0.000012358322,0.000036581743,0.010180955,0.00008671353,0.00004228777,0.95791525,0.002752959,0.02885763],"study_design_scores_gemma":[0.000103923725,0.00003676728,0.00015008326,0.000121600955,0.000010554347,0.000058779016,0.00013540247,0.5597831,0.00034280226,0.43163007,0.007513053,0.00011382675],"about_ca_topic_score_codex":0.0001825506,"about_ca_topic_score_gemma":0.000076403194,"teacher_disagreement_score":0.94528705,"about_ca_system_score_codex":0.000016634505,"about_ca_system_score_gemma":0.00021172907,"threshold_uncertainty_score":0.9323172},"labels":[],"label_agreement":null},{"id":"W4399428774","doi":"10.1145/3665601.3669841","title":"TbExplain: A Text-Based Explanation Method for Scene Classification Models With the Statistical Prediction Correction","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Statistical model; Pattern recognition (psychology); Natural language processing","score_opus":0.055580695099355655,"score_gpt":0.3216964549341441,"score_spread":0.26611575983478847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399428774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008577375,0.000038214963,0.98882854,0.007120524,0.00075361517,0.0006968763,0.00001748242,0.00057703495,0.0018819348],"genre_scores_gemma":[0.55184954,0.000005635669,0.44613317,0.0004442674,0.00013893688,0.00056067854,0.000059526184,0.000021498332,0.00078673614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840975,0.00015317577,0.00025962276,0.00053849205,0.0003765674,0.00026237607],"domain_scores_gemma":[0.9980459,0.0011900637,0.00006044278,0.00038974624,0.00024664233,0.00006721286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010285743,0.00014932787,0.00011025919,0.00017329444,0.00031292898,0.0005200691,0.00034693914,0.000074748634,0.000022567363],"category_scores_gemma":[0.00008448694,0.00009677995,0.00004546152,0.0006692229,0.000051965802,0.0010377814,0.000025694728,0.00014916796,0.0000395948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054451222,0.000048673122,0.000006368943,0.000030081243,0.000018838322,0.0000026285452,0.00057592755,0.045303144,0.0012851069,0.7536128,0.015536189,0.1835258],"study_design_scores_gemma":[0.000086369895,0.00024265898,0.000061816456,0.00003254531,0.00002085624,0.000011679756,0.00040785852,0.96493655,0.011423318,0.018175706,0.004478227,0.00012243859],"about_ca_topic_score_codex":0.00011838079,"about_ca_topic_score_gemma":0.0001663662,"teacher_disagreement_score":0.9196334,"about_ca_system_score_codex":0.00017738205,"about_ca_system_score_gemma":0.00019498623,"threshold_uncertainty_score":0.5015038},"labels":[],"label_agreement":null},{"id":"W4399432489","doi":"10.1063/5.0211100","title":"Chinese Academy of Science Journal Ranking System (2015–2023)","year":2024,"lang":"en","type":"article","venue":"Physics of Fluids","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Canada Research Chairs","keywords":"Science Citation Index; Popularity; Physics; China; Ranking (information retrieval); Citation; Library science; Mainstream; Position (finance); Political science; Computer science; Law; Artificial intelligence; Business","score_opus":0.028623664723155536,"score_gpt":0.3299815132898782,"score_spread":0.30135784856672265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399432489","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21766444,0.0020510785,0.7738695,0.00059853203,0.0016660648,0.00015597818,0.000004236776,0.00016184709,0.0038283179],"genre_scores_gemma":[0.9918129,0.000031245647,0.007740541,0.00002805049,0.0003200765,0.0000033421566,1.6727485e-7,0.000010838157,0.00005286636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979294,0.000039546812,0.00048386957,0.00034601212,0.0008413988,0.00035980632],"domain_scores_gemma":[0.9990267,0.00013700098,0.00012538045,0.00033695696,0.00026302,0.00011090471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014745493,0.00014538277,0.00026251527,0.0002586557,0.00020092406,0.0002614284,0.0018953459,0.000044103363,0.0000060891566],"category_scores_gemma":[0.000074276024,0.00012032609,0.00013894786,0.0024276348,0.0004556919,0.0019026187,0.00037839494,0.00028286205,0.000061218176],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033136168,0.00003704051,0.00017310177,0.0002250916,0.00002268954,0.000011719156,0.0019681014,0.00085173047,0.291216,0.68772686,0.00021185515,0.017552504],"study_design_scores_gemma":[0.00008259743,0.000097333075,0.0005047372,0.00062017917,0.000017593837,0.000069643655,0.00026398167,0.36496913,0.53578377,0.0968923,0.00045722627,0.00024149603],"about_ca_topic_score_codex":0.000022714676,"about_ca_topic_score_gemma":2.8249337e-7,"teacher_disagreement_score":0.77414846,"about_ca_system_score_codex":0.00010791612,"about_ca_system_score_gemma":0.00030379693,"threshold_uncertainty_score":0.49067554},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05443953291172988,"score_gpt":0.33828205273502,"score_spread":0.2838425198232901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399433746","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.373471e-8,0.61284643,0.38553435,0.00019342572,0.00059757533,0.0005976254,0.0000021130545,0.00020588952,0.000022575718],"genre_scores_gemma":[0.000015846765,0.98182935,0.017513143,0.0002060646,0.00016707864,0.00017249752,0.000011074507,0.00007081481,0.000014114808],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99523205,0.00018233771,0.0020070632,0.00108793,0.00046615183,0.0010244673],"domain_scores_gemma":[0.997673,0.00061690115,0.00030166583,0.0010252697,0.0001430499,0.00024016501],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009599119,0.0006937796,0.0024612688,0.001265435,0.000045270077,0.00015313097,0.0023817362,0.0003226177,0.0000051352035],"category_scores_gemma":[0.00035995492,0.0006448428,0.00064309087,0.0064267037,0.000036123893,0.0003225606,0.00065854273,0.001368832,0.00017011266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.9354034e-7,0.000041465733,2.419787e-8,0.112890325,0.000030280034,0.00013346509,0.000040049697,0.00033264668,6.0703115e-7,0.10763235,0.0003739002,0.7785243],"study_design_scores_gemma":[0.000011758329,0.00018033356,4.7596394e-8,0.2651437,0.0001247522,0.00012392232,0.0000020908894,0.28972834,0.000048266418,0.0030598228,0.44076914,0.00080783374],"about_ca_topic_score_codex":0.00007653718,"about_ca_topic_score_gemma":0.0000039325105,"teacher_disagreement_score":0.77771646,"about_ca_system_score_codex":0.00066173327,"about_ca_system_score_gemma":0.00059800106,"threshold_uncertainty_score":0.9996003},"labels":[],"label_agreement":null},{"id":"W4399448652","doi":"","title":"Affective AIED: From Detection to Adaptation","year":2009,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Adaptation (eye); Computer science; Artificial intelligence; Cognitive psychology; Computer vision; Speech recognition; Psychology; Neuroscience","score_opus":0.015159212051315393,"score_gpt":0.23100526953581407,"score_spread":0.21584605748449867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399448652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10277569,0.00009167688,0.8724943,0.008909667,0.0001611742,0.00028821884,0.000003934001,0.00035067587,0.014924703],"genre_scores_gemma":[0.8873082,0.000020942183,0.11124431,0.00043867616,0.0000234286,0.000026373149,0.000015129189,0.00001150774,0.00091146375],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963752,0.0019420395,0.00031287532,0.00065547804,0.00037464662,0.00033972858],"domain_scores_gemma":[0.99609816,0.00095913326,0.00016702658,0.0013560196,0.0012152647,0.00020438412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021703884,0.0001868217,0.00017378037,0.0002018737,0.00039372875,0.00045076502,0.0011586703,0.000097370365,0.000040024217],"category_scores_gemma":[0.0012799855,0.00020736967,0.000088520035,0.0009957849,0.000050384206,0.00071925967,0.00022276501,0.00019783225,0.00033914618],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012199787,0.00026648576,0.00010669131,0.0000032687838,0.000013827133,0.000005175611,0.020646362,0.00047585118,0.052884515,0.17859298,0.00021862274,0.746774],"study_design_scores_gemma":[0.00017322332,0.00000316476,0.006735518,0.00015779526,0.000008328803,0.000004320839,0.00034097413,0.1584146,0.79573554,0.03403845,0.0040664324,0.00032166153],"about_ca_topic_score_codex":0.002343674,"about_ca_topic_score_gemma":0.0045721494,"teacher_disagreement_score":0.7845325,"about_ca_system_score_codex":0.00015170236,"about_ca_system_score_gemma":0.000082628474,"threshold_uncertainty_score":0.845629},"labels":[],"label_agreement":null},{"id":"W4399528640","doi":"10.1109/incacct61598.2024.10551183","title":"Examining the Influence of Explainable Artificial Intelligence on Healthcare Diagnosis and Decision Making","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Computer science; Health care; Artificial intelligence","score_opus":0.08916495782349809,"score_gpt":0.3440174099027219,"score_spread":0.2548524520792238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399528640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5731969,0.0008983025,0.4225633,0.0019864244,0.00032536386,0.00029372174,0.0000016616843,0.00018769375,0.00054663996],"genre_scores_gemma":[0.983008,0.00026171407,0.015973762,0.0005857756,0.00005659533,0.000074718744,2.3349372e-7,0.000014249074,0.000024934254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978121,0.00009761523,0.0005479256,0.00064632675,0.0004756497,0.00042041822],"domain_scores_gemma":[0.9961972,0.0027670201,0.00008503854,0.0007114629,0.00015394506,0.00008531332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011044384,0.00019632971,0.00019951914,0.00025519915,0.000316468,0.0005020446,0.000962087,0.00008066193,0.000030087856],"category_scores_gemma":[0.00047377814,0.00013721823,0.00005004891,0.0011640812,0.00016680207,0.00083753193,0.0004653115,0.0002747176,0.00010063659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000091448,0.000021385003,0.00032752298,0.000055909553,0.000005793435,0.000031465537,0.0018337374,0.005761292,0.00017890232,0.48831162,0.00006162052,0.5034016],"study_design_scores_gemma":[0.000019989675,0.00083859556,0.002640953,0.0024757308,0.00001296933,0.000046102727,0.0044655753,0.27230498,0.07409023,0.64144737,0.0011642143,0.0004932832],"about_ca_topic_score_codex":0.00023522507,"about_ca_topic_score_gemma":0.00013905749,"teacher_disagreement_score":0.50290835,"about_ca_system_score_codex":0.000070931674,"about_ca_system_score_gemma":0.000098176744,"threshold_uncertainty_score":0.5595597},"labels":[],"label_agreement":null},{"id":"W4399552717","doi":"10.1613/jair.1.15155","title":"Mitigating Value Hallucination in Dyna-Style Planning via Multistep Predecessor Models","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hallucinating; Computer science; Reinforcement learning; Bootstrapping (finance); Artificial intelligence; Value (mathematics); Function (biology); Successor cardinal; Sample (material); Bellman equation; Machine learning; Algorithm; Mathematical optimization; Econometrics; Mathematics","score_opus":0.1987057900527737,"score_gpt":0.4453474910418657,"score_spread":0.24664170098909202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399552717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050352093,0.0019441413,0.94247717,0.0018950899,0.00096669997,0.00036296944,0.0000018885117,0.00008402641,0.001915903],"genre_scores_gemma":[0.95631075,0.00013852106,0.042860087,0.00003842357,0.0004738994,0.000021635246,0.0000010717757,0.000033785658,0.0001218312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937815,0.00076476065,0.0017343761,0.0006438794,0.00203045,0.001045046],"domain_scores_gemma":[0.9956499,0.0019959111,0.00027296224,0.0005203468,0.001264336,0.0002965523],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010032645,0.00025640425,0.00041138416,0.0020666001,0.00035621904,0.0013895925,0.0019873134,0.00020434882,0.000052483403],"category_scores_gemma":[0.0014179586,0.00023955024,0.00018735263,0.0033154693,0.00025806768,0.0036983583,0.00041606737,0.0017838042,0.0001961936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006659534,0.00024482803,0.000050364026,0.00012934576,0.000037990503,0.0011886855,0.013620905,0.2711004,0.018127918,0.1926791,0.00011036147,0.50264347],"study_design_scores_gemma":[0.000018745439,0.00027697123,0.00001824968,0.0006513834,0.0000040670056,0.00010055937,0.0021835829,0.73122627,0.07439232,0.19078285,0.00017234273,0.00017266402],"about_ca_topic_score_codex":0.0004407792,"about_ca_topic_score_gemma":0.00015799032,"teacher_disagreement_score":0.90595865,"about_ca_system_score_codex":0.00066737115,"about_ca_system_score_gemma":0.0006213395,"threshold_uncertainty_score":0.9996471},"labels":[],"label_agreement":null},{"id":"W4399771149","doi":"10.1371/journal.pone.0296985","title":"CAManim: Animating end-to-end network activation maps","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Newborn Screening Ontario; Institute for Clinical Evaluative Sciences; University of Ottawa; Ottawa Hospital; Children's Hospital of Eastern Ontario","funders":"","keywords":"Computer science; Convolutional neural network; End-to-end principle; Artificial intelligence; Visualization; Focus (optics); Metric (unit); Deep learning; Data science; Machine learning; Information retrieval","score_opus":0.07015756192468069,"score_gpt":0.26231552342935316,"score_spread":0.19215796150467246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399771149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29714045,0.00038810362,0.67099005,0.008684849,0.000601701,0.0007542819,0.0000057260527,0.0015900313,0.01984484],"genre_scores_gemma":[0.9105511,0.000010502535,0.08719107,0.000597622,0.00058115856,0.000050669692,0.0000047199164,0.000022733375,0.0009904843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983365,0.000057301284,0.00025865727,0.0004566322,0.00045990315,0.0004310145],"domain_scores_gemma":[0.9990553,0.0002551317,0.000044651213,0.0004346941,0.00009794692,0.00011223551],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042827724,0.00013529768,0.00015549113,0.00012669234,0.00018882926,0.0005219589,0.0005700908,0.000055459488,0.00011636257],"category_scores_gemma":[0.000154078,0.00014007917,0.00003905164,0.0010644579,0.000020568104,0.00087751774,0.00026171608,0.00020299837,0.0013836975],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001852639,0.00060721283,0.0005440083,0.00035529945,0.0002488023,0.00012154775,0.007843934,0.0033494309,0.2743984,0.61179733,0.01053699,0.090178534],"study_design_scores_gemma":[0.000046112265,0.00024749554,0.00038780956,0.0010408971,0.000033752734,0.0000054931747,0.00021180388,0.39928117,0.55472785,0.03870764,0.0048273504,0.0004826008],"about_ca_topic_score_codex":0.00010078587,"about_ca_topic_score_gemma":0.00004088852,"teacher_disagreement_score":0.6134106,"about_ca_system_score_codex":0.000118280856,"about_ca_system_score_gemma":0.000067647685,"threshold_uncertainty_score":0.9993938},"labels":[],"label_agreement":null},{"id":"W4399801841","doi":"10.1109/ichms59971.2024.10555660","title":"An Overview of Multidisciplinary Research on Explainability: Concepts, Challenges, and Design Considerations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Multidisciplinary approach; Computer science; Perspective (graphical); Task (project management); Intelligent decision support system; Everyday life; Human–computer interaction; Artificial intelligence; Data science; Management science; Systems engineering; Engineering; Epistemology","score_opus":0.5115880257343175,"score_gpt":0.49506990691745567,"score_spread":0.016518118816861826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399801841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06299384,0.14689378,0.72168285,0.03728868,0.0010789001,0.0035166612,0.000014631768,0.0014980943,0.025032572],"genre_scores_gemma":[0.965233,0.003146773,0.031286664,0.00006945869,0.000041391417,0.00006999859,8.027795e-7,0.000011988163,0.00013987909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974741,0.0007606605,0.0003164452,0.0006822392,0.0004261071,0.00034047235],"domain_scores_gemma":[0.99619204,0.0025160357,0.000024366955,0.00083353376,0.00028823497,0.00014577995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027932008,0.00013307609,0.00018690008,0.00027460192,0.0002501107,0.0002357818,0.00039804494,0.000079217956,0.000082357634],"category_scores_gemma":[0.00024817977,0.000113589485,0.000038033504,0.0004175403,0.0003141049,0.0009400489,0.0002628663,0.00024619827,0.00007496667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060294005,0.00012821959,0.0000057955854,0.0001125421,0.000008943675,0.000053817454,0.0074884132,0.00030174453,0.0012623817,0.94815075,0.00036565677,0.042115673],"study_design_scores_gemma":[0.00008250734,0.0015069632,0.00043850602,0.00026329973,0.0000051417296,0.00003241825,0.0065193106,0.27028817,0.056117926,0.6630826,0.0013991119,0.0002640256],"about_ca_topic_score_codex":0.00008634961,"about_ca_topic_score_gemma":0.0000992019,"teacher_disagreement_score":0.9022392,"about_ca_system_score_codex":0.000066777655,"about_ca_system_score_gemma":0.00024487008,"threshold_uncertainty_score":0.46320447},"labels":[],"label_agreement":null},{"id":"W4399880449","doi":"10.1093/rfs/hhae029","title":"Computational Reproducibility in Finance: Evidence from 1,000 Tests","year":2024,"lang":"en","type":"article","venue":"Review of Financial Studies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cascades (Canada)","funders":"Riksbankens Jubileumsfond; Vermont Agency of Natural Resources; Knut och Alice Wallenbergs Stiftelse; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Agence Nationale de la Recherche","keywords":"Reproducibility; Overconfidence effect; Coding (social sciences); Computer science; Code (set theory); Psychology; Statistics; Mathematics; Social psychology","score_opus":0.09613543887438811,"score_gpt":0.38885568834591167,"score_spread":0.29272024947152353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399880449","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04102318,0.9401248,0.012809853,0.00454729,0.0007473008,0.0004773712,0.000013949804,0.00009547557,0.00016079446],"genre_scores_gemma":[0.5442932,0.431693,0.022737429,0.0008316806,0.00021733953,0.00012285443,0.0000030902308,0.000011644238,0.00008973443],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972772,0.00014955616,0.00080003386,0.0011463834,0.00037606116,0.00025078724],"domain_scores_gemma":[0.9973241,0.0011427776,0.00013317548,0.001038791,0.00033427833,0.000026861968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025619897,0.00017301778,0.0005642309,0.00008673109,0.000078865436,0.000039494164,0.0006555077,0.000040423864,0.000014875089],"category_scores_gemma":[0.008283358,0.0001493392,0.00012501885,0.0013819259,0.00015588169,0.0006489202,0.00038589534,0.00017485334,0.00009923128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012908931,0.00018768111,0.006789584,0.0138335405,0.000048191403,0.00019854054,0.0046576816,0.0011623348,0.00014240656,0.07962809,0.020054173,0.8732849],"study_design_scores_gemma":[0.00017158805,0.0004638443,0.22652318,0.24991684,0.000089975445,0.000020073912,0.00012014715,0.021132147,0.0067494633,0.4182517,0.075294755,0.001266314],"about_ca_topic_score_codex":0.00032229617,"about_ca_topic_score_gemma":0.00014618068,"teacher_disagreement_score":0.8720186,"about_ca_system_score_codex":0.00014489808,"about_ca_system_score_gemma":0.0002804045,"threshold_uncertainty_score":0.99165523},"labels":[],"label_agreement":null},{"id":"W4399913501","doi":"10.1145/3627043.3659566","title":"Initial results on personalizing explanations of AI hints in an ITS","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing","score_opus":0.09974566932648732,"score_gpt":0.38639480767081796,"score_spread":0.28664913834433065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399913501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57457805,0.0002624802,0.22540973,0.018568546,0.0020964157,0.00060427736,0.000048785576,0.00085657684,0.17757514],"genre_scores_gemma":[0.99693066,0.000004575633,0.002102041,0.00043457092,0.000053827822,0.000008769746,0.0000041698017,0.000006085651,0.00045532314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885046,0.00006624082,0.00028839332,0.00034366056,0.0002572933,0.00019392892],"domain_scores_gemma":[0.99935085,0.00019577146,0.000024683772,0.00028097973,0.00009025293,0.00005748756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039969542,0.00008307354,0.00009261492,0.00032581048,0.000047481717,0.00016026727,0.00046401448,0.000043724383,0.00005602727],"category_scores_gemma":[0.00013856865,0.00007624592,0.000032815347,0.0006617181,0.00002327022,0.001072668,0.00005600962,0.00015466665,0.00021964344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001545393,0.00008892354,0.00003780955,0.00001634406,0.0000045584306,0.00009152459,0.007758487,0.0012548321,0.0028550487,0.9721181,0.0009372794,0.014821655],"study_design_scores_gemma":[0.00013834667,0.0003550109,0.00041059274,0.00020936872,0.0000026562727,0.000009313374,0.0012563854,0.72312456,0.25022557,0.021276576,0.0027447597,0.0002468738],"about_ca_topic_score_codex":0.00020510025,"about_ca_topic_score_gemma":0.0004600533,"teacher_disagreement_score":0.9508415,"about_ca_system_score_codex":0.000058496124,"about_ca_system_score_gemma":0.00010308367,"threshold_uncertainty_score":0.31092182},"labels":[],"label_agreement":null},{"id":"W4399917675","doi":"10.1145/3635636.3660763","title":"Explainable AI for the Arts 2 (XAIxArts2)","year":2024,"lang":"en","type":"article","venue":"Creativity and Cognition","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Engineering and Physical Sciences Research Council; UK Research and Innovation","keywords":"The arts; Manifesto; Sociology; Computer science; Engineering ethics; Visual arts; Engineering; Political science; Art","score_opus":0.04589826887072394,"score_gpt":0.3127543293377939,"score_spread":0.26685606046706994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399917675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004817663,0.0011569539,0.9798565,0.0071527543,0.00029742552,0.00036906562,0.0000076833,0.00020370043,0.0061382386],"genre_scores_gemma":[0.9964649,0.00012743272,0.0012247094,0.00072167563,0.00014398336,0.00022082614,0.0000058452324,0.0000075447892,0.001083091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992386,0.000034383196,0.00010993042,0.000292656,0.000115119896,0.00020931772],"domain_scores_gemma":[0.99889946,0.00074359303,0.000019659115,0.00019737906,0.00009415548,0.00004573305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041912327,0.00009492842,0.000082371924,0.000056565048,0.00042257167,0.0006363162,0.00016933637,0.00004338399,0.0000283472],"category_scores_gemma":[0.000108136235,0.0000701286,0.000048815073,0.00023581806,0.00008419423,0.0009903061,0.00007194042,0.000098798366,0.000070254304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015061996,0.000046273042,0.000017880513,0.00008925747,0.000027771015,0.000017711089,0.0015509466,0.000029943696,0.0012128717,0.6328227,0.0054640383,0.35870555],"study_design_scores_gemma":[0.00011937255,0.00022077102,0.0001798767,0.00014859703,0.000057621848,0.00004335368,0.0008270323,0.2817986,0.06913026,0.47128478,0.1759277,0.00026203363],"about_ca_topic_score_codex":0.000036386053,"about_ca_topic_score_gemma":0.000035056986,"teacher_disagreement_score":0.99164724,"about_ca_system_score_codex":0.000017500714,"about_ca_system_score_gemma":0.000042546468,"threshold_uncertainty_score":0.6136012},"labels":[],"label_agreement":null},{"id":"W4400219672","doi":"10.21203/rs.3.rs-4578348/v1","title":"Using Generative and Explainable Neural Networks to Investigate the Relationship Between Motor Cortex Activity and Animal Behavior During Motor Task Learning.","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Task (project management); Premovement neuronal activity; Neuroscience; Computer science; Generative grammar; Motor learning; Predictability; Motor cortex; Animal behavior; Relation (database); Artificial intelligence; Motor activity; Motor behavior; Neural activity; Machine learning; Psychology; Biology; Engineering","score_opus":0.1949887667463972,"score_gpt":0.4133067679272923,"score_spread":0.21831800118089512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400219672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98402345,0.0010266665,0.0107617,0.0016020883,0.00019086844,0.0021469009,0.000032547447,0.00017722536,0.000038574773],"genre_scores_gemma":[0.9960757,0.000047678543,0.0022663423,0.000021524658,0.00050335814,0.0004956723,0.00000759999,0.000055840148,0.0005263228],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994701,0.0014978403,0.000399293,0.001412529,0.000931533,0.0010577684],"domain_scores_gemma":[0.99639,0.0016139575,0.00013388226,0.0009026227,0.0004325069,0.00052706525],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023755743,0.00040104432,0.00040409312,0.0005664576,0.0018802104,0.0023101473,0.001033964,0.00034277473,0.000005584769],"category_scores_gemma":[0.0014035995,0.00034545216,0.000097341435,0.0010520947,0.00046163952,0.00054575637,0.0074135656,0.0039894693,0.000018810171],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047931256,0.00026904096,0.67770255,0.0036957862,0.00029138793,0.0016558019,0.03516181,0.07742732,0.15872474,0.026473885,0.00032289678,0.017795457],"study_design_scores_gemma":[0.00006563717,0.00036295166,0.4354318,0.00039582863,0.000030610863,0.000021209236,0.0006267469,0.5568721,0.0021487824,0.003613079,0.000034050438,0.00039715713],"about_ca_topic_score_codex":0.0014829156,"about_ca_topic_score_gemma":0.00012760953,"teacher_disagreement_score":0.47944483,"about_ca_system_score_codex":0.00042508094,"about_ca_system_score_gemma":0.00033395988,"threshold_uncertainty_score":0.99989974},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Computer science; Data science; Artificial intelligence","score_opus":0.07160439259705363,"score_gpt":0.35152822231162967,"score_spread":0.279923829714576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400400027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016506398,0.083962895,0.8665949,0.013855263,0.000269487,0.004446736,0.000022134023,0.0017066444,0.02897688],"genre_scores_gemma":[0.93519515,0.0071472395,0.025987705,0.0008990611,0.00060118345,0.018177534,0.00003867266,0.00011766314,0.0118357865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982362,0.00014283371,0.0002680571,0.00078778004,0.0002551852,0.00030998164],"domain_scores_gemma":[0.9983416,0.0002629571,0.000052921376,0.0010531428,0.00015674402,0.0001326217],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007862095,0.00020461023,0.0002426606,0.00016396125,0.00028798275,0.0011737433,0.0012790228,0.00008332034,0.000005760847],"category_scores_gemma":[0.000021233182,0.00016177249,0.00001993105,0.0005135197,0.00007189199,0.00087840104,0.00033539342,0.00015000589,0.00021826739],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075226753,0.00008936416,0.000022338214,0.00007624341,0.00002866501,0.000017758015,0.002920003,0.000023228597,0.00039206652,0.90267366,0.018115757,0.07563339],"study_design_scores_gemma":[0.000046954727,0.00024025246,0.00017420878,0.00032358532,0.0000030435167,0.000040045274,0.0009924666,0.008597127,0.011166899,0.0033968263,0.97463197,0.000386639],"about_ca_topic_score_codex":0.0033925907,"about_ca_topic_score_gemma":0.00038235,"teacher_disagreement_score":0.9565162,"about_ca_system_score_codex":0.00008488349,"about_ca_system_score_gemma":0.00010083603,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W4400438538","doi":"10.1007/978-3-031-63787-2_1","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Interpretability; Binary number; Artificial neural network; Computer science; Artificial intelligence; Mathematics; Arithmetic","score_opus":0.036713966182022446,"score_gpt":0.30121830911232206,"score_spread":0.2645043429302996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400438538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017457802,0.00310868,0.81524634,0.005530919,0.001592729,0.0021177614,0.00001462911,0.0005535999,0.15437752],"genre_scores_gemma":[0.98672986,0.0007381044,0.011907803,0.00038565043,0.000019395593,0.000035436908,0.00001013112,0.000008316942,0.00016532448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794436,0.00006772355,0.000859034,0.0004959085,0.0003054248,0.00032756565],"domain_scores_gemma":[0.9969778,0.00045768823,0.00020063118,0.0020026527,0.00025125832,0.00010998867],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019816635,0.00025810933,0.00029323163,0.0010608045,0.00033363502,0.00096308475,0.0025352398,0.0001594347,0.000004513501],"category_scores_gemma":[0.00009775773,0.00026051493,0.00004116304,0.0008666002,0.0012155871,0.008920732,0.004720196,0.00086139713,0.000013625224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007506354,0.000029739445,0.0005383287,0.00008926723,0.000004715275,0.0000032169396,0.0071082404,0.005390376,0.000018893461,0.7312997,0.000020132777,0.25548992],"study_design_scores_gemma":[0.00005990988,0.00004663281,0.0014347311,0.00023122698,0.0000022885504,0.00001694979,0.00008261006,0.965652,0.00001694778,0.029093927,0.0031160747,0.00024672973],"about_ca_topic_score_codex":0.0000692099,"about_ca_topic_score_gemma":0.00007272075,"teacher_disagreement_score":0.969272,"about_ca_system_score_codex":0.00032530446,"about_ca_system_score_gemma":0.00015474307,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W4400438864","doi":"10.1007/978-3-031-63797-1","title":"Explainable Artificial Intelligence","year":2024,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Università degli Studi di Perugia; Akademia Górniczo-Hutnicza im. Stanislawa Staszica; Università degli Studi di Torino; Universidad de Granada; University of Illinois at Urbana-Champaign; Université de Bordeaux; Tallinna Tehnikaülikool; Universiteit Utrecht; Università degli Studi di Pavia; University of Waterloo; Kungliga Tekniska Högskolan; Universiteit Maastricht; Aristotle University of Thessaloniki; Universita degli Studi di Bari Aldo Moro; Dublin City University; Haute école Spécialisée de Suisse Occidentale; Technische Universität Berlin; University of Galway; Imperial College London; Università degli Studi di Napoli Federico II","keywords":"Computer science; Thesaurus; Artificial intelligence; Information retrieval","score_opus":0.06743547468698971,"score_gpt":0.327571071654115,"score_spread":0.2601355969671253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400438864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012188337,0.0008039643,0.7595713,0.0020880685,0.0008431455,0.0004274172,0.0000075162916,0.00024668046,0.2359997],"genre_scores_gemma":[0.07866707,0.012172459,0.86268204,0.0062312535,0.0006473735,0.00054949673,0.0002198228,0.00009468594,0.038735766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971247,0.00006450876,0.0010960405,0.00053389097,0.00067925215,0.00050166034],"domain_scores_gemma":[0.99557275,0.00036820208,0.00026292595,0.0031019326,0.00052773766,0.00016643877],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021584292,0.00031009017,0.00030657434,0.0019049245,0.0006416037,0.0025335192,0.006682411,0.00018285404,0.000013691937],"category_scores_gemma":[0.00013297732,0.0003175061,0.000068565656,0.0021781651,0.001283395,0.012617327,0.005253973,0.00080348755,0.0011328342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.328373e-7,0.000014997164,0.0000010625668,0.00004648568,0.0000027147858,0.0000018440692,0.0024614965,0.00034776525,0.0000027166616,0.729669,0.00089040445,0.2665607],"study_design_scores_gemma":[0.000014155263,0.000048069272,0.000010387192,0.00028046587,0.0000039288807,0.00002494869,0.00010947441,0.5907298,0.00016836164,0.2587889,0.14950214,0.00031938148],"about_ca_topic_score_codex":0.000029054809,"about_ca_topic_score_gemma":0.00002787767,"teacher_disagreement_score":0.590382,"about_ca_system_score_codex":0.00051212986,"about_ca_system_score_gemma":0.0013381555,"threshold_uncertainty_score":0.9999277},"labels":[],"label_agreement":null},{"id":"W4400439049","doi":"10.1007/978-3-031-63803-9","title":"Explainable Artificial Intelligence","year":2024,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Università degli Studi di Perugia; Haute école Spécialisée de Suisse Occidentale; Technological University Dublin; University of Illinois at Urbana-Champaign; Universidade do Minho; Università di Pisa; Università degli Studi di Salerno; Universität Paderborn; Università degli Studi di Torino; Universidad de Granada; Università di Bologna; Tallinna Tehnikaülikool; Universidade de Coimbra; Università degli Studi di Camerino; Universiteit Utrecht; Universita degli Studi di Bari Aldo Moro; University of Waterloo; Technische Universiteit Eindhoven; Universiteit Maastricht; Universität Bielefeld; University of Texas at San Antonio; Università degli Studi di Milano-Bicocca; Akademia Górniczo-Hutnicza im. Stanislawa Staszica; Universidad Complutense de Madrid; Dublin City University; Università degli Studi di Milano; Trinity College Dublin; Sapienza Università di Roma; Technische Universität Berlin; University of Galway; University College Dublin; Université de Bordeaux; Università degli Studi di Napoli Federico II; Oak Ridge National Laboratory; Imperial College London; Kungliga Tekniska Högskolan; Università degli Studi di Siena; Aristotle University of Thessaloniki; Università degli Studi di Pavia; Sveučilište u Zagrebu","keywords":"Computer science; Thesaurus; Artificial intelligence; Information retrieval","score_opus":0.06743547468698971,"score_gpt":0.327571071654115,"score_spread":0.2601355969671253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400439049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012188337,0.0008039643,0.7595713,0.0020880685,0.0008431455,0.0004274172,0.0000075162916,0.00024668046,0.2359997],"genre_scores_gemma":[0.07866707,0.012172459,0.86268204,0.0062312535,0.0006473735,0.00054949673,0.0002198228,0.00009468594,0.038735766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971247,0.00006450876,0.0010960405,0.00053389097,0.00067925215,0.00050166034],"domain_scores_gemma":[0.99557275,0.00036820208,0.00026292595,0.0031019326,0.00052773766,0.00016643877],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021584292,0.00031009017,0.00030657434,0.0019049245,0.0006416037,0.0025335192,0.006682411,0.00018285404,0.000013691937],"category_scores_gemma":[0.00013297732,0.0003175061,0.000068565656,0.0021781651,0.001283395,0.012617327,0.005253973,0.00080348755,0.0011328342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.328373e-7,0.000014997164,0.0000010625668,0.00004648568,0.0000027147858,0.0000018440692,0.0024614965,0.00034776525,0.0000027166616,0.729669,0.00089040445,0.2665607],"study_design_scores_gemma":[0.000014155263,0.000048069272,0.000010387192,0.00028046587,0.0000039288807,0.00002494869,0.00010947441,0.5907298,0.00016836164,0.2587889,0.14950214,0.00031938148],"about_ca_topic_score_codex":0.000029054809,"about_ca_topic_score_gemma":0.00002787767,"teacher_disagreement_score":0.590382,"about_ca_system_score_codex":0.00051212986,"about_ca_system_score_gemma":0.0013381555,"threshold_uncertainty_score":0.9999277},"labels":[],"label_agreement":null},{"id":"W4400439200","doi":"10.1007/978-3-031-63800-8","title":"Explainable Artificial Intelligence","year":2024,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Università degli Studi di Perugia; Akademia Górniczo-Hutnicza im. Stanislawa Staszica; Università degli Studi di Torino; Universidad de Granada; University of Illinois at Urbana-Champaign; Université de Bordeaux; Tallinna Tehnikaülikool; Universiteit Utrecht; Università degli Studi di Pavia; University of Waterloo; Kungliga Tekniska Högskolan; Universiteit Maastricht; Aristotle University of Thessaloniki; Universita degli Studi di Bari Aldo Moro; Dublin City University; Haute école Spécialisée de Suisse Occidentale; Technische Universität Berlin; University of Galway; Imperial College London; Università degli Studi di Napoli Federico II","keywords":"Computer science; Thesaurus; Information retrieval; Artificial intelligence","score_opus":0.06743547468698971,"score_gpt":0.327571071654115,"score_spread":0.2601355969671253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400439200","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012188337,0.0008039643,0.7595713,0.0020880685,0.0008431455,0.0004274172,0.0000075162916,0.00024668046,0.2359997],"genre_scores_gemma":[0.07866707,0.012172459,0.86268204,0.0062312535,0.0006473735,0.00054949673,0.0002198228,0.00009468594,0.038735766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971247,0.00006450876,0.0010960405,0.00053389097,0.00067925215,0.00050166034],"domain_scores_gemma":[0.99557275,0.00036820208,0.00026292595,0.0031019326,0.00052773766,0.00016643877],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021584292,0.00031009017,0.00030657434,0.0019049245,0.0006416037,0.0025335192,0.006682411,0.00018285404,0.000013691937],"category_scores_gemma":[0.00013297732,0.0003175061,0.000068565656,0.0021781651,0.001283395,0.012617327,0.005253973,0.00080348755,0.0011328342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.328373e-7,0.000014997164,0.0000010625668,0.00004648568,0.0000027147858,0.0000018440692,0.0024614965,0.00034776525,0.0000027166616,0.729669,0.00089040445,0.2665607],"study_design_scores_gemma":[0.000014155263,0.000048069272,0.000010387192,0.00028046587,0.0000039288807,0.00002494869,0.00010947441,0.5907298,0.00016836164,0.2587889,0.14950214,0.00031938148],"about_ca_topic_score_codex":0.000029054809,"about_ca_topic_score_gemma":0.00002787767,"teacher_disagreement_score":0.590382,"about_ca_system_score_codex":0.00051212986,"about_ca_system_score_gemma":0.0013381555,"threshold_uncertainty_score":0.9999277},"labels":[],"label_agreement":null},{"id":"W4400439306","doi":"10.1007/978-3-031-63787-2","title":"Explainable Artificial Intelligence","year":2024,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Università degli Studi di Perugia; Haute école Spécialisée de Suisse Occidentale; Technological University Dublin; University of Illinois at Urbana-Champaign; Universidade do Minho; Università di Pisa; Università degli Studi di Salerno; Universität Paderborn; Università degli Studi di Torino; Universidad de Granada; Università di Bologna; Tallinna Tehnikaülikool; Universidade de Coimbra; Università degli Studi di Camerino; Universiteit Utrecht; Universita degli Studi di Bari Aldo Moro; University of Waterloo; Technische Universiteit Eindhoven; Universiteit Maastricht; Universität Bielefeld; University of Texas at San Antonio; Università degli Studi di Milano-Bicocca; Akademia Górniczo-Hutnicza im. Stanislawa Staszica; Universidad Complutense de Madrid; Dublin City University; Università degli Studi di Milano; Trinity College Dublin; Sapienza Università di Roma; Technische Universität Berlin; University of Galway; University College Dublin; Université de Bordeaux; Università degli Studi di Napoli Federico II; Oak Ridge National Laboratory; Imperial College London; Kungliga Tekniska Högskolan; Università degli Studi di Siena; Aristotle University of Thessaloniki; Università degli Studi di Pavia; Sveučilište u Zagrebu","keywords":"Computer science; Artificial intelligence; Thesaurus; Information retrieval","score_opus":0.06743547468698971,"score_gpt":0.327571071654115,"score_spread":0.2601355969671253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400439306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012188337,0.0008039643,0.7595713,0.0020880685,0.0008431455,0.0004274172,0.0000075162916,0.00024668046,0.2359997],"genre_scores_gemma":[0.07866707,0.012172459,0.86268204,0.0062312535,0.0006473735,0.00054949673,0.0002198228,0.00009468594,0.038735766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971247,0.00006450876,0.0010960405,0.00053389097,0.00067925215,0.00050166034],"domain_scores_gemma":[0.99557275,0.00036820208,0.00026292595,0.0031019326,0.00052773766,0.00016643877],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021584292,0.00031009017,0.00030657434,0.0019049245,0.0006416037,0.0025335192,0.006682411,0.00018285404,0.000013691937],"category_scores_gemma":[0.00013297732,0.0003175061,0.000068565656,0.0021781651,0.001283395,0.012617327,0.005253973,0.00080348755,0.0011328342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.328373e-7,0.000014997164,0.0000010625668,0.00004648568,0.0000027147858,0.0000018440692,0.0024614965,0.00034776525,0.0000027166616,0.729669,0.00089040445,0.2665607],"study_design_scores_gemma":[0.000014155263,0.000048069272,0.000010387192,0.00028046587,0.0000039288807,0.00002494869,0.00010947441,0.5907298,0.00016836164,0.2587889,0.14950214,0.00031938148],"about_ca_topic_score_codex":0.000029054809,"about_ca_topic_score_gemma":0.00002787767,"teacher_disagreement_score":0.590382,"about_ca_system_score_codex":0.00051212986,"about_ca_system_score_gemma":0.0013381555,"threshold_uncertainty_score":0.9999277},"labels":[],"label_agreement":null},{"id":"W4400443603","doi":"10.5465/amproc.2024.17872symposium","title":"Building an Inference Engine Using AI and The World’s Largest Meta- Analysis: Lesson Learned","year":2024,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University; University of Calgary","funders":"","keywords":"Inference; Computer science; Meta-analysis; Artificial intelligence; Machine learning; Medicine","score_opus":0.10467965907266726,"score_gpt":0.38115024911290496,"score_spread":0.2764705900402377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400443603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11057275,0.0070320372,0.8339143,0.04237506,0.0001597233,0.0011651793,0.0000028206957,0.00073252054,0.004045644],"genre_scores_gemma":[0.96718055,0.00023121196,0.031071365,0.000832732,0.000047949765,0.000042112406,3.6958684e-7,0.000014877564,0.00057883735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797964,0.000038802795,0.00043417342,0.0006895645,0.00047182202,0.00038598644],"domain_scores_gemma":[0.9993874,0.0001421605,0.00014267737,0.00017216663,0.00007034131,0.00008525046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021080468,0.00022918526,0.0004754784,0.0008518982,0.00019777117,0.00075466867,0.0011802017,0.00006638647,0.000024173401],"category_scores_gemma":[0.000044054264,0.00016487887,0.0002225488,0.0032399173,0.00017165006,0.0023831467,0.0006995449,0.0003719146,0.000006676325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000098268,0.000020616451,0.000059731196,0.00016155666,0.0050156163,0.0000034285404,0.0008263933,0.0015901389,0.00042998692,0.9782299,0.00009177881,0.013561027],"study_design_scores_gemma":[0.0001492171,0.00003242482,0.0002323963,0.00006523747,0.013151972,0.0000035762403,0.00029360864,0.8899958,0.013701849,0.0754838,0.006572799,0.0003173082],"about_ca_topic_score_codex":0.00006439466,"about_ca_topic_score_gemma":0.000006510914,"teacher_disagreement_score":0.9027461,"about_ca_system_score_codex":0.000036077465,"about_ca_system_score_gemma":0.000010373066,"threshold_uncertainty_score":0.7277288},"labels":[],"label_agreement":null},{"id":"W4400450585","doi":"10.31219/osf.io/dwcjv","title":"Hidden Markov Model: Tutorial","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Markov model; Markov chain; Artificial intelligence; Machine learning","score_opus":0.035869576498276115,"score_gpt":0.29636047524120135,"score_spread":0.26049089874292525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400450585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017892302,0.0003654694,0.8278137,0.0043106186,0.013829064,0.00044325672,0.00001031564,0.001664208,0.14977416],"genre_scores_gemma":[0.40103278,0.00010040146,0.5441639,0.00090425316,0.0033371004,0.00021425128,0.000015399417,0.00009639365,0.050135538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997183,0.00006132447,0.00046782504,0.0012106202,0.0005705693,0.0005066274],"domain_scores_gemma":[0.9977444,0.000087342014,0.00008879296,0.0017469653,0.00016927111,0.00016325069],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00051806064,0.00035871728,0.0003283579,0.00023991795,0.00008604059,0.001215332,0.0029231054,0.00038306505,0.00012757553],"category_scores_gemma":[0.00007333149,0.0003288222,0.00023901107,0.00031991705,0.000053780783,0.000243762,0.009066428,0.0009949867,0.002346155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006539379,0.000044506047,0.0000026293924,0.00013835049,0.00005137746,0.00011369521,0.0011377048,0.007265644,0.00022212337,0.8566606,0.055982288,0.07837455],"study_design_scores_gemma":[0.000013045728,0.000012088481,5.5163997e-7,0.000043599473,0.000008822231,0.0000030718197,0.0000147482715,0.5677972,0.0035143744,0.4264928,0.0018462186,0.00025345501],"about_ca_topic_score_codex":0.0003972781,"about_ca_topic_score_gemma":0.000077142475,"teacher_disagreement_score":0.56053156,"about_ca_system_score_codex":0.00020671201,"about_ca_system_score_gemma":0.0006551581,"threshold_uncertainty_score":0.9999164},"labels":[],"label_agreement":null},{"id":"W4400450746","doi":"10.31219/osf.io/mru2x","title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Encoder; Computer science; Generative grammar; Artificial intelligence; Speech recognition; Electrical engineering; Voltage; Engineering","score_opus":0.03091224222555638,"score_gpt":0.2746827783910922,"score_spread":0.2437705361655358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400450746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13490675,0.00082899537,0.8474644,0.0020218806,0.008209097,0.0007986247,0.000042057953,0.000507257,0.005220937],"genre_scores_gemma":[0.988212,0.0005142873,0.008426339,0.00012604319,0.00033168716,0.00004360786,0.000027435452,0.000029131752,0.00228949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978872,0.0001405044,0.00035844438,0.00096754654,0.00031676152,0.00032952416],"domain_scores_gemma":[0.9991231,0.00014761076,0.0000620423,0.00041203416,0.00011097533,0.00014424833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012013877,0.00028600908,0.00029386723,0.0001795183,0.00012031486,0.0009343059,0.00048227963,0.00028951457,0.00002884941],"category_scores_gemma":[0.000048267368,0.00026174504,0.00007613272,0.00021463957,0.00006846351,0.00027464784,0.0013893163,0.0004934743,0.00007253263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002890269,0.00005760504,0.0002747856,0.0004384246,0.000120260454,0.00005543915,0.0020756468,0.00002488022,0.0023330736,0.9236777,0.0015806147,0.06933266],"study_design_scores_gemma":[0.00018327338,0.00020972316,0.001855927,0.00023935658,0.00006735944,0.000041785814,0.0002073114,0.12865813,0.015772576,0.84960407,0.0021345087,0.0010259671],"about_ca_topic_score_codex":0.0032591203,"about_ca_topic_score_gemma":0.0019335974,"teacher_disagreement_score":0.8533052,"about_ca_system_score_codex":0.00005727902,"about_ca_system_score_gemma":0.00013235428,"threshold_uncertainty_score":0.9999835},"labels":[],"label_agreement":null},{"id":"W4400582718","doi":"10.1016/j.crsus.2024.100132","title":"Human-AI collaboration to identify literature for evidence synthesis","year":2024,"lang":"en","type":"article","venue":"Cell Reports Sustainability","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Commonwealth Scientific and Industrial Research Organisation","keywords":"Data science; Computer science; Computational biology; Biology","score_opus":0.020869938389024734,"score_gpt":0.36906413020841056,"score_spread":0.3481941918193858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400582718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2637539,0.0029118198,0.70397437,0.020595461,0.0024376845,0.00415493,0.000009831125,0.0011111253,0.0010509132],"genre_scores_gemma":[0.9916705,0.000008964799,0.0038749871,0.00029155423,0.00018091177,0.0004959122,0.000003877072,0.000025964331,0.003447316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965162,0.00017276946,0.0008016982,0.0014168166,0.00048175553,0.0006107361],"domain_scores_gemma":[0.99456376,0.0007540171,0.00014391514,0.0017400639,0.0025553368,0.00024288447],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029005222,0.00027180975,0.0002872794,0.0003029829,0.00042310663,0.0025344228,0.0006787429,0.00016919765,0.0000303326],"category_scores_gemma":[0.0061611948,0.0002625,0.00018968486,0.0022492628,0.00008020529,0.0025182136,0.00032960213,0.00023184728,0.000027581393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019079931,0.0016143675,0.007801279,0.023283035,0.00017597129,0.016726254,0.07630655,0.019062523,0.14629146,0.38319486,0.21365419,0.11169871],"study_design_scores_gemma":[0.000045763605,0.00044556314,0.0018034901,0.0008146072,0.000083217594,0.00013825772,0.003196718,0.01772022,0.4087889,0.4711219,0.09470144,0.0011399298],"about_ca_topic_score_codex":0.00009227687,"about_ca_topic_score_gemma":0.00004352566,"teacher_disagreement_score":0.7279166,"about_ca_system_score_codex":0.0010451654,"about_ca_system_score_gemma":0.0010655103,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W4400676355","doi":"10.1007/978-3-031-65112-0_2","title":"Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Oralys (Canada); Concordia University","funders":"","keywords":"Computer science; Shapley value; Perspective (graphical); Value (mathematics); Algorithm; Theoretical computer science; Mathematical economics; Artificial intelligence; Machine learning; Game theory; Mathematics","score_opus":0.04241876940155365,"score_gpt":0.3149556739187277,"score_spread":0.27253690451717405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400676355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014973164,0.00025163076,0.99013066,0.00064759725,0.00041634327,0.00040161354,0.000052944757,0.00019043397,0.007759058],"genre_scores_gemma":[0.6098104,0.000020730267,0.38817766,0.001398931,0.00012224063,0.00003093483,0.000035727753,0.000042736676,0.00036061788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956917,0.00004505799,0.0008392369,0.0014751524,0.0013605962,0.0005882173],"domain_scores_gemma":[0.99606925,0.00072049955,0.00042265543,0.0016264401,0.0009632417,0.00019791182],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001155714,0.0005344841,0.00076478877,0.00429632,0.00023368724,0.000570192,0.0036269908,0.00030986947,0.00003138062],"category_scores_gemma":[0.00019992077,0.0004964498,0.0003010902,0.0035592092,0.0008266287,0.0017817694,0.0007746224,0.0007854853,0.000045422086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041853586,0.000026687929,0.00000487478,0.000016938578,0.00007030958,0.000014985157,0.0057948697,0.63086075,0.00003425002,0.35477993,0.000002274843,0.008389968],"study_design_scores_gemma":[0.00004129432,0.00013161253,0.000009825971,0.00012040193,0.000089778,0.0000020360394,0.000011330765,0.70575666,0.0016538971,0.29179227,0.000026120091,0.00036477277],"about_ca_topic_score_codex":0.00024320363,"about_ca_topic_score_gemma":0.0010629653,"teacher_disagreement_score":0.6096607,"about_ca_system_score_codex":0.0007853989,"about_ca_system_score_gemma":0.0012147614,"threshold_uncertainty_score":0.9997487},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2151034924898165,"score_gpt":0.45912439523832704,"score_spread":0.24402090274851054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400810536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050395783,0.0071507376,0.9719965,0.0092111025,0.0037193014,0.0016433023,0.000016385045,0.0004166623,0.0008064475],"genre_scores_gemma":[0.8975225,0.005920322,0.07811157,0.0023090781,0.0057035154,0.005050626,0.000020065174,0.00016982605,0.0051924605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734193,0.00011069428,0.000511817,0.0009322559,0.00032776833,0.00077552395],"domain_scores_gemma":[0.9955,0.0029017355,0.000062279476,0.0006526283,0.00071400724,0.00016929988],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010412657,0.00023142542,0.00028178387,0.00041815563,0.0008589418,0.0021920842,0.0014578569,0.00015932975,0.00002540643],"category_scores_gemma":[0.00037313657,0.0002240535,0.00014243834,0.001244305,0.000117672025,0.0017189397,0.00041721333,0.00032984235,0.000040098326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028701195,0.00008307935,0.000017248803,0.00055576715,0.000049972914,0.000033258977,0.0021183633,0.0002998526,0.0018264302,0.50943285,0.021153681,0.46440077],"study_design_scores_gemma":[0.0000353915,0.00034315747,0.000022155888,0.00023204567,0.0000170738,0.000025243971,0.0010836669,0.15075208,0.117002,0.23544222,0.49469596,0.00034902015],"about_ca_topic_score_codex":0.00034398705,"about_ca_topic_score_gemma":0.0005705218,"teacher_disagreement_score":0.8938849,"about_ca_system_score_codex":0.00014584929,"about_ca_system_score_gemma":0.00028510595,"threshold_uncertainty_score":0.9988437},"labels":[],"label_agreement":null},{"id":"W4400909960","doi":"10.1109/icde60146.2024.00468","title":"Exploring the Space of Model Comparisons","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science; Space (punctuation)","score_opus":0.2854287988091037,"score_gpt":0.32725046277145375,"score_spread":0.04182166396235004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400909960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01562071,0.00016331469,0.95872515,0.0047427933,0.00047128115,0.000074192074,4.3817425e-7,0.00022259999,0.019979488],"genre_scores_gemma":[0.9642354,0.000030756742,0.034120653,0.000077096935,0.00003076885,0.000017826003,1.0076318e-7,0.000005619101,0.0014817525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923986,0.000022907354,0.00016029028,0.0002022166,0.00019044241,0.00018428509],"domain_scores_gemma":[0.9992471,0.00017526501,0.000017347624,0.00047834084,0.00004531672,0.00003668545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002746191,0.000070286645,0.00008393384,0.00006680413,0.00007705135,0.00015679443,0.0007603159,0.000012307966,0.000013869845],"category_scores_gemma":[0.000023538485,0.000045071636,0.000054567052,0.00050732406,0.000051882722,0.0007593418,0.0002303488,0.00010552462,0.00018763162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.7604814e-7,0.00001178215,0.000010087406,0.000010390233,0.000006633874,0.0000033652327,0.0019066485,0.02889011,0.001731469,0.955457,0.004465846,0.0075061424],"study_design_scores_gemma":[0.0000055297387,0.000012721689,0.000014885208,0.000017574439,0.0000022267707,0.0000020372222,0.0003579741,0.89163697,0.091496184,0.012234364,0.0041642454,0.00005525767],"about_ca_topic_score_codex":0.00014454027,"about_ca_topic_score_gemma":0.000047872632,"teacher_disagreement_score":0.9486147,"about_ca_system_score_codex":0.000019318719,"about_ca_system_score_gemma":0.000059755122,"threshold_uncertainty_score":0.24116874},"labels":[],"label_agreement":null},{"id":"W4400936793","doi":"10.1007/s10044-024-01306-8","title":"Causal generative explainers using counterfactual inference: a case study on the Morpho-MNIST dataset","year":2024,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Counterfactual thinking; Artificial intelligence; Machine learning; Computer science; Generative grammar; Classifier (UML); Inference; Interpretability; MNIST database; Generative model; Pattern recognition (psychology); Artificial neural network; Psychology","score_opus":0.08872213112094182,"score_gpt":0.3729687433924339,"score_spread":0.28424661227149206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400936793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25369635,0.00005222173,0.7450216,0.00056747627,0.000022362106,0.00029912274,0.0002624891,0.000041441228,0.000036951886],"genre_scores_gemma":[0.99883884,0.000011338244,0.0003019091,0.00040471394,0.000070174145,0.00024809278,0.00008878558,0.0000071963236,0.000028940194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867034,0.000106948624,0.00025731683,0.00055078726,0.00022458145,0.00019004257],"domain_scores_gemma":[0.9987242,0.00033903695,0.000057768135,0.0007412119,0.000060439834,0.00007733525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034851307,0.00015736904,0.00016519238,0.00021498126,0.0005396509,0.00089318963,0.00041006578,0.000026699423,0.000060814422],"category_scores_gemma":[0.00001287395,0.000108914166,0.000060677383,0.0013455566,0.00008088781,0.00023292222,0.00018555956,0.00015449189,0.00007705175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002374371,0.0044928407,0.057995573,0.0001500707,0.012734523,0.008330988,0.12115723,0.06562826,0.017546767,0.30563965,0.015114665,0.3911857],"study_design_scores_gemma":[0.00004846331,0.00008378532,0.00026428793,0.000010403154,0.0004940514,0.00010339731,0.011852855,0.98032534,0.0021200841,0.0005159533,0.0038951826,0.0002862082],"about_ca_topic_score_codex":0.003279159,"about_ca_topic_score_gemma":0.0020453,"teacher_disagreement_score":0.91469705,"about_ca_system_score_codex":0.000046481713,"about_ca_system_score_gemma":0.000045249068,"threshold_uncertainty_score":0.8613048},"labels":[],"label_agreement":null},{"id":"W4401024451","doi":"10.24963/ijcai.2024/1025","title":"DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Perception; Computer science; Human–computer interaction; Computer vision; Artificial intelligence; Vision science; Visual perception; Psychology","score_opus":0.06619888836545691,"score_gpt":0.320404242772277,"score_spread":0.2542053544068201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401024451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012369108,0.0015184989,0.970806,0.00950286,0.0003705164,0.0012783004,0.000013849853,0.00044712794,0.003693729],"genre_scores_gemma":[0.8474334,0.00040079473,0.13382146,0.00039960045,0.0002109748,0.0002752825,0.00013290532,0.00004856754,0.01727701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980289,0.00018369454,0.0004239733,0.0007923456,0.00021082406,0.00036030743],"domain_scores_gemma":[0.99767053,0.0012876163,0.000073162926,0.00077634316,0.00011616516,0.000076189084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014260592,0.00020477248,0.0003542995,0.00026078548,0.00018533289,0.0009007697,0.00077614066,0.00015672608,0.000033876517],"category_scores_gemma":[0.0010571736,0.00017463845,0.000042155036,0.00060283876,0.00020599527,0.0015752169,0.0003748625,0.00024014944,0.000072167655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003498163,0.00010789277,0.0000945256,0.0002625435,0.00013177324,0.000034027096,0.007850716,0.0008327787,0.024526253,0.5691855,0.0035005098,0.3899753],"study_design_scores_gemma":[0.0049311877,0.00012287486,0.000116333016,0.00019663127,0.00004113044,0.000037649796,0.0025258944,0.8180224,0.13281238,0.029487336,0.011123311,0.0005829149],"about_ca_topic_score_codex":0.00017048481,"about_ca_topic_score_gemma":0.00064389507,"teacher_disagreement_score":0.8369846,"about_ca_system_score_codex":0.00006182314,"about_ca_system_score_gemma":0.00014346685,"threshold_uncertainty_score":0.8686143},"labels":[],"label_agreement":null},{"id":"W4401054519","doi":"10.1007/978-3-031-67434-1_49","title":"Explainable Machine Learning Models Assessing Lending Risk","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Machine learning; Model risk; Artificial intelligence; Economics; Risk management; Finance","score_opus":0.038671824997245134,"score_gpt":0.2545121031238287,"score_spread":0.21584027812658357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401054519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054800494,0.06164423,0.87928206,0.00008737024,0.0018173173,0.0003776046,0.0000036388988,0.00026877027,0.056464203],"genre_scores_gemma":[0.9698339,0.0036165735,0.0016431574,0.000071182985,0.0011290478,0.00003830046,0.000020658215,0.00013693247,0.023510227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692523,0.00013918894,0.0007389873,0.0010923553,0.0004009874,0.0007032354],"domain_scores_gemma":[0.9979502,0.0008463445,0.00037302912,0.0006049057,0.000089922905,0.00013558488],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001269007,0.00058852194,0.0007587457,0.00042282508,0.00042572536,0.0018236947,0.00063128286,0.00069965544,0.000011730764],"category_scores_gemma":[0.00007901194,0.00052497804,0.00014402796,0.00025131158,0.00007392481,0.00068927405,0.00047166873,0.0022136727,0.000024281073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030239032,0.0000040084897,0.00007907335,0.00014743203,0.00003816087,0.00019384925,0.00050994474,0.7664976,0.0000036091883,0.20995209,0.000026343585,0.022544855],"study_design_scores_gemma":[0.000046706544,0.000049028924,8.47149e-7,0.0014857025,0.00002781199,0.00006661645,0.000023738101,0.8573731,0.00001124687,0.13059728,0.00984132,0.00047657182],"about_ca_topic_score_codex":0.00078700896,"about_ca_topic_score_gemma":0.0002504095,"teacher_disagreement_score":0.96977913,"about_ca_system_score_codex":0.00022524287,"about_ca_system_score_gemma":0.000060466795,"threshold_uncertainty_score":0.99972016},"labels":[],"label_agreement":null},{"id":"W4401108397","doi":"10.1007/978-3-031-66431-1_9","title":"Formal Definition of Interpretability and Explainability in XAI","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence","score_opus":0.023423250703421987,"score_gpt":0.24266667627886326,"score_spread":0.21924342557544127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401108397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010008757,0.03004513,0.9234231,0.00024814648,0.001717996,0.001303326,0.000015573507,0.000099682504,0.0331383],"genre_scores_gemma":[0.99880356,0.0003373351,0.00046440426,0.000040861487,0.00012752296,0.000034362376,0.0000055760534,0.000020565503,0.0001658088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978185,0.000088175424,0.00081883674,0.00070291135,0.00020833037,0.00036319662],"domain_scores_gemma":[0.9984054,0.0007196727,0.00018519395,0.0005349781,0.00008510817,0.000069634756],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011919431,0.0003245442,0.00063582766,0.00023786182,0.00004939838,0.00017760624,0.0003153566,0.0005225757,0.0000059108365],"category_scores_gemma":[0.00011206132,0.0002857347,0.00007986315,0.00016069051,0.00018159232,0.00031244603,0.00035888396,0.0007068736,0.0000023218402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005208129,0.00003219661,0.0024453863,0.0013666238,0.000029221817,0.00006919957,0.0028446692,0.020359362,0.000011794614,0.93441683,0.000012604973,0.03836005],"study_design_scores_gemma":[0.000089591274,0.00016035872,0.00019380637,0.0016729693,0.0000131602965,0.000041329306,0.0000395463,0.4768194,0.00003430427,0.5200912,0.00048839295,0.00035597692],"about_ca_topic_score_codex":0.0004212241,"about_ca_topic_score_gemma":0.0014530238,"teacher_disagreement_score":0.9887948,"about_ca_system_score_codex":0.00013714224,"about_ca_system_score_gemma":0.00004565162,"threshold_uncertainty_score":0.99995947},"labels":[],"label_agreement":null},{"id":"W4401169054","doi":"10.2196/preprints.64482","title":"The Right to Explanation in AI: In a Lonely Place (Preprint)","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Preprint; Psychology; Psychoanalysis; Art; Computer science; World Wide Web","score_opus":0.02245255998930591,"score_gpt":0.3009184627245638,"score_spread":0.2784659027352579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401169054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18358596,0.0007930201,0.6136897,0.10803822,0.005893879,0.0038891796,0.0000060617554,0.0009124721,0.0831915],"genre_scores_gemma":[0.98739046,0.0000609765,0.0065186485,0.0011477651,0.00008370893,0.0004760487,0.0000027675808,0.000021345872,0.004298305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971571,0.00018308361,0.0006528454,0.0010738025,0.0004362385,0.0004969309],"domain_scores_gemma":[0.9979549,0.00040724073,0.00007658646,0.0013557791,0.000105821004,0.00009964768],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001741832,0.0002632469,0.0002511842,0.00054707634,0.00007908315,0.00094486057,0.0024734258,0.00020437493,0.000039953058],"category_scores_gemma":[0.00026884757,0.0001997349,0.0000797164,0.0010265611,0.000034792363,0.00023187627,0.0045733303,0.0010765692,0.0017972457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033573062,0.000119434066,0.00028442542,0.000101755075,0.000019158513,0.00034718678,0.010776476,0.09623473,0.0003744941,0.83592194,0.010470288,0.04531655],"study_design_scores_gemma":[0.00006308233,0.000040499053,0.0008490122,0.0003982516,0.0000026601897,0.000007701699,0.0004471631,0.46340138,0.019131474,0.5006902,0.014479374,0.00048918434],"about_ca_topic_score_codex":0.002779328,"about_ca_topic_score_gemma":0.03038128,"teacher_disagreement_score":0.80380446,"about_ca_system_score_codex":0.00052857376,"about_ca_system_score_gemma":0.00033862723,"threshold_uncertainty_score":0.99898},"labels":[],"label_agreement":null},{"id":"W4401214884","doi":"10.1145/3638530.3654271","title":"ATOMIC: an Interpretable Clustering Method Based on Data Topology","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cluster analysis; Computer science; Topology (electrical circuits); Data mining; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.05880182550493654,"score_gpt":0.3237061137358929,"score_spread":0.26490428823095635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401214884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073573716,0.00019595341,0.922852,0.0017308384,0.00053275516,0.00021805178,0.000007751999,0.00013549418,0.0007534531],"genre_scores_gemma":[0.86802596,0.00001608453,0.13169193,0.00014983951,0.000053569052,0.0000082394945,0.000007552376,0.00000877853,0.00003806878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852777,0.000056508605,0.00032640083,0.0006089695,0.0002634113,0.0002169466],"domain_scores_gemma":[0.99907374,0.0001729526,0.000112898655,0.00030893003,0.0002577143,0.000073766554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044632424,0.00015677723,0.00017555871,0.00016532741,0.00020353754,0.0002526411,0.0012592614,0.000064033346,0.0000148091685],"category_scores_gemma":[0.000056269066,0.00012898343,0.000035986694,0.00038765967,0.00012243376,0.00076457614,0.00074285874,0.00016115746,0.000010953673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012251669,0.0003335279,0.0047702403,0.00064656534,0.00008222839,0.0000048704774,0.004294783,0.20257191,0.014991898,0.43281054,0.003912589,0.33545834],"study_design_scores_gemma":[0.000064335036,0.00013576643,0.0048655043,0.00016193453,0.000012330255,0.000033410484,0.00018885385,0.94786316,0.0010665235,0.045150593,0.00032405704,0.00013352909],"about_ca_topic_score_codex":0.000086404085,"about_ca_topic_score_gemma":0.0000070119627,"teacher_disagreement_score":0.7944522,"about_ca_system_score_codex":0.000055370252,"about_ca_system_score_gemma":0.00014380022,"threshold_uncertainty_score":0.52597916},"labels":[],"label_agreement":null},{"id":"W4401267042","doi":"10.2139/ssrn.4885662","title":"Will User-Contributed AI Training Data Eat Its Own Tail?","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Training (meteorology); Computer science; Geography","score_opus":0.05195564040774149,"score_gpt":0.3158387788508273,"score_spread":0.2638831384430858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401267042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012712472,0.034648158,0.9225699,0.021909885,0.0055093165,0.0007500848,0.00012607545,0.00074583763,0.0010283224],"genre_scores_gemma":[0.97489184,0.011073732,0.0034659342,0.001071344,0.002890871,0.000044403998,0.00015184133,0.00015876684,0.006251242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99043363,0.00034895656,0.0010990569,0.0017152154,0.001029884,0.0053732833],"domain_scores_gemma":[0.99572086,0.00019454974,0.0005266253,0.0027062683,0.0005110013,0.0003407101],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0062664216,0.0006892885,0.0007522017,0.00056746515,0.0004977535,0.0021788871,0.009453242,0.00051596126,0.000057304438],"category_scores_gemma":[0.0005840783,0.0006370381,0.00032854587,0.0008496387,0.00008508608,0.0023108637,0.0075971493,0.013513473,0.0005736255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033079512,0.00008034956,0.000022264985,0.00007102753,0.00067940325,0.00028786476,0.0015924331,0.0021192809,0.00041435953,0.89006454,0.00269678,0.10193863],"study_design_scores_gemma":[0.00019203959,0.00023223425,0.0000044982085,0.00035549194,0.00011620514,0.0011132887,0.00091212173,0.10744885,0.00079783687,0.8569556,0.031097902,0.0007739337],"about_ca_topic_score_codex":0.00013567558,"about_ca_topic_score_gemma":0.0019343074,"teacher_disagreement_score":0.9621794,"about_ca_system_score_codex":0.0022384499,"about_ca_system_score_gemma":0.014249025,"threshold_uncertainty_score":0.9996081},"labels":[],"label_agreement":null},{"id":"W4401383183","doi":"10.1016/j.compmedimag.2024.102422","title":"Evidence modeling for reliability learning and interpretable decision-making under multi-modality medical image segmentation","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Modality (human–computer interaction); Artificial intelligence; Reliability (semiconductor); Computer science; Segmentation; Image segmentation; Image (mathematics); Machine learning; Medical decision making; Medical imaging; Pattern recognition (psychology); Computer vision; Medicine","score_opus":0.037670357995041884,"score_gpt":0.3738711265333765,"score_spread":0.33620076853833464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401383183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031260043,0.003455683,0.9559226,0.00788106,0.0008019786,0.0002718168,0.0000014116154,0.0003950054,0.000010377902],"genre_scores_gemma":[0.7820655,0.0012558479,0.21566166,0.0008543487,0.000104784354,0.0000310771,0.0000025944385,0.000018170016,0.0000060095977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692553,0.00023678191,0.0005991777,0.0009477672,0.00083369244,0.00045707205],"domain_scores_gemma":[0.9954292,0.0035667976,0.00006764204,0.0003100263,0.00022040297,0.0004059223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038419475,0.00023910546,0.00032063643,0.00021110395,0.00041114836,0.00088452303,0.0005733365,0.00014800446,0.000018144367],"category_scores_gemma":[0.003645609,0.00021230879,0.000104922336,0.00047320384,0.00037916464,0.0012961231,0.0007673668,0.000656609,0.0000036218294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006291551,0.00009921512,0.00072407036,0.0005946656,0.00004587826,0.00013819114,0.0019411884,0.0013767353,0.00089346594,0.022080434,0.00017683905,0.9718664],"study_design_scores_gemma":[0.00022033475,0.000038338298,0.0000567357,0.0024250625,0.000016583072,0.00008302077,0.00016382917,0.9489591,0.00008595395,0.047532737,0.00019788141,0.00022041467],"about_ca_topic_score_codex":0.00006271036,"about_ca_topic_score_gemma":0.000014260843,"teacher_disagreement_score":0.971646,"about_ca_system_score_codex":0.000055843542,"about_ca_system_score_gemma":0.00025481192,"threshold_uncertainty_score":0.86577016},"labels":[],"label_agreement":null},{"id":"W4401504510","doi":"10.1016/j.jveb.2024.08.001","title":"Using deep learning to assess and understand behavior","year":2024,"lang":"en","type":"article","venue":"Journal of Veterinary Behavior","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health PEI","funders":"","keywords":"Psychology; Cognitive science; Cognitive psychology; Artificial intelligence; Computer science","score_opus":0.2554221613866123,"score_gpt":0.4141974894955101,"score_spread":0.15877532810889783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401504510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7569478,0.00055006205,0.24139318,0.00011877654,0.0007798764,0.0001162776,6.2652526e-7,0.00004557157,0.000047808786],"genre_scores_gemma":[0.9545844,0.00004094994,0.045094606,0.00004337003,0.00012377216,0.0000062753147,1.5965571e-7,0.000020928017,0.00008549032],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985044,0.0001061282,0.0004505396,0.00026805047,0.0003705462,0.00030033122],"domain_scores_gemma":[0.9991819,0.000104580686,0.0001232397,0.00020155059,0.00015060444,0.0002380904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058061286,0.00016227248,0.00022551075,0.0003832641,0.00017319027,0.00066290796,0.00048130163,0.00006900384,0.00003152367],"category_scores_gemma":[0.00004162088,0.00015024105,0.000099513745,0.00043356518,0.00004818223,0.0013097583,0.0002731609,0.00039156014,0.00001732802],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072363895,0.00034716006,0.005741171,0.0000970308,0.000045049816,0.022215094,0.0084164925,0.0011446864,0.7036219,0.003347419,0.000083394785,0.25486824],"study_design_scores_gemma":[0.0025595513,0.05759792,0.12631036,0.0058946228,0.0028523342,0.2239113,0.05104499,0.24732736,0.20819776,0.005751913,0.061138295,0.007413598],"about_ca_topic_score_codex":0.000016129417,"about_ca_topic_score_gemma":0.0000031237585,"teacher_disagreement_score":0.49542415,"about_ca_system_score_codex":0.00019206558,"about_ca_system_score_gemma":0.000098598204,"threshold_uncertainty_score":0.63924366},"labels":[],"label_agreement":null},{"id":"W4401571420","doi":"10.1080/03155986.2024.2385189","title":"Diagnosing infeasible optimization problems using large language models","year":2024,"lang":"en","type":"article","venue":"INFOR Information Systems and Operational Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Solver; Optimization problem; Artificial intelligence; Natural language; Machine learning; Mathematical optimization; Programming language; Algorithm","score_opus":0.12038116634689246,"score_gpt":0.3876422347020393,"score_spread":0.26726106835514685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401571420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007237496,0.0009231284,0.98300093,0.00029918933,0.0003336225,0.00068594265,0.00002175353,0.00014600281,0.007351914],"genre_scores_gemma":[0.9891824,0.00011981117,0.009936917,0.00011316861,0.00013073468,0.00013908048,0.00006377441,0.00000913505,0.00030499217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979072,0.00009649602,0.0005338273,0.00018142919,0.00090393954,0.0003770644],"domain_scores_gemma":[0.9985897,0.00024591497,0.00004891399,0.00023144268,0.0007730095,0.000111050256],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024993925,0.0001115327,0.00011726627,0.00063675607,0.00058816053,0.0044936365,0.0003014118,0.00009057839,0.000019888139],"category_scores_gemma":[0.00016010534,0.00009801434,0.000028202225,0.0009577987,0.000045771005,0.01359476,0.00023178417,0.00023237735,0.00013769644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000153379,0.000006417495,0.000022844377,0.0001214431,0.0000064001783,0.0000021884575,0.0051929215,0.55605996,0.000044849385,0.43589136,0.00029980455,0.0023502903],"study_design_scores_gemma":[0.00007550365,0.000032625478,0.0000061842366,0.00019247545,0.0000012105676,0.000038958806,0.0016384237,0.98604375,0.00029173752,0.000626464,0.010935646,0.00011700216],"about_ca_topic_score_codex":0.0006195657,"about_ca_topic_score_gemma":0.000016330709,"teacher_disagreement_score":0.9819449,"about_ca_system_score_codex":0.000168097,"about_ca_system_score_gemma":0.00040349032,"threshold_uncertainty_score":0.9965398},"labels":[],"label_agreement":null},{"id":"W4401632399","doi":"10.22215/etd/2024-16083","title":"On the Interpretability and Explainability of Prototype-Based Methods and Reinforcement Learning","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Reinforcement learning; Computer science; Artificial intelligence; Field (mathematics); Machine learning; Artificial neural network; Metric (unit); Feature (linguistics); Transparency (behavior); Engineering; Mathematics","score_opus":0.02459170313212264,"score_gpt":0.35262027812037194,"score_spread":0.32802857498824933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401632399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26775494,0.00039531998,0.6969769,0.0010994197,0.0005725453,0.0033788113,9.658474e-7,0.00023967025,0.029581392],"genre_scores_gemma":[0.9857944,0.000011101097,0.012407281,0.00008949651,0.000009477804,0.00030958245,0.0000059296963,0.000013887847,0.0013588376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980275,0.00044020588,0.00045526432,0.0006116334,0.00026504693,0.00020036483],"domain_scores_gemma":[0.9976352,0.0013332131,0.00016268576,0.0006287978,0.00018211686,0.000058005993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024825772,0.00023187202,0.00028390245,0.00012484229,0.00014089768,0.00018624456,0.00044171602,0.00013424573,0.00007373309],"category_scores_gemma":[0.0011756619,0.00015146603,0.00007766985,0.0002780685,0.00011927264,0.00016077874,0.00014660346,0.00047763955,0.000007883519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024270796,0.000071220806,0.00017129938,0.0017268452,0.00005433467,0.0000034125535,0.016810916,0.0010484488,0.0016792507,0.8789761,0.00005840962,0.09915702],"study_design_scores_gemma":[0.00007214632,0.0010247257,0.0004132687,0.000530926,0.000039604292,0.0000013517554,0.0050211214,0.589022,0.2497132,0.15317707,0.00057820324,0.00040644087],"about_ca_topic_score_codex":0.00021446013,"about_ca_topic_score_gemma":0.00007867275,"teacher_disagreement_score":0.7257991,"about_ca_system_score_codex":0.000064920474,"about_ca_system_score_gemma":0.00014496397,"threshold_uncertainty_score":0.6176605},"labels":[],"label_agreement":null},{"id":"W4401656650","doi":"10.1016/j.engappai.2024.109131","title":"Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance Propagation","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics; University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Relevance (law); Artificial intelligence; Layer (electronics); Algorithm; Machine learning; Materials science; Composite material","score_opus":0.024555620711097847,"score_gpt":0.2863314128269965,"score_spread":0.26177579211589863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401656650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01636146,0.0006739351,0.98174125,0.000125497,0.00016069123,0.0006705828,0.0000014315178,0.00019635144,0.00006880983],"genre_scores_gemma":[0.937009,0.000060256334,0.06264158,0.000004790092,0.00004108234,0.00019255144,0.0000061245933,0.00002256459,0.00002206025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997564,0.000053036252,0.0010549201,0.0005711825,0.0003864074,0.00037045917],"domain_scores_gemma":[0.99843794,0.00041843747,0.00018073616,0.00065077195,0.000228258,0.00008384767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083645346,0.00021877507,0.00028942927,0.00041076154,0.00009386099,0.00009476423,0.0007616196,0.00009875418,0.000012539618],"category_scores_gemma":[0.00034056997,0.0002478033,0.00009086295,0.002102419,0.00011696706,0.0006440722,0.00016063388,0.00032881903,0.000027186552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036969002,0.00007325894,0.000020867832,0.00016642669,0.0000091826405,0.0000021493584,0.0008685615,0.7670337,0.050402734,0.11362658,0.000002214267,0.06779066],"study_design_scores_gemma":[0.000007319826,0.000044509736,0.0000065085674,0.00009806495,0.0000058817413,0.0000025411857,0.00021883089,0.68261063,0.312279,0.004426122,0.00015129113,0.00014933529],"about_ca_topic_score_codex":0.00024157982,"about_ca_topic_score_gemma":0.000020948792,"teacher_disagreement_score":0.9206475,"about_ca_system_score_codex":0.00026414052,"about_ca_system_score_gemma":0.00011676989,"threshold_uncertainty_score":0.99999744},"labels":[],"label_agreement":null},{"id":"W4401942373","doi":"10.1016/j.procs.2024.08.026","title":"Forecasting Future Behavior: Agents in Board Game Strategy","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Operations research; Artificial intelligence; Human–computer interaction","score_opus":0.06968261981308498,"score_gpt":0.3158349713752454,"score_spread":0.24615235156216042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401942373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29303852,0.0005625159,0.6984992,0.00096367364,0.0045842594,0.00052850775,0.0000017938087,0.0006604687,0.0011610376],"genre_scores_gemma":[0.9382791,0.000022665643,0.06066633,0.0002921194,0.00058484846,0.00006996832,7.978316e-7,0.000016076185,0.00006812829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99641305,0.000037901777,0.00045069412,0.0012888656,0.0008404647,0.0009690509],"domain_scores_gemma":[0.9987533,0.000095742755,0.000068928224,0.000623581,0.00020287864,0.00025556693],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010703946,0.0002657532,0.00020964826,0.0006672262,0.00021329401,0.0019390093,0.002827224,0.00008287603,0.000015358348],"category_scores_gemma":[0.000046656798,0.0002483794,0.000073270036,0.004086857,0.00026945665,0.0033765594,0.0009037941,0.00039276,0.00020032976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034796938,0.00014839302,0.0035190403,0.0001127243,0.000005334659,0.00090773834,0.006342778,0.004137527,0.0012850713,0.07181522,0.00068148185,0.9110412],"study_design_scores_gemma":[0.000054224045,0.000120633515,0.00364321,0.00011011006,0.0000031846478,0.00010784717,0.00006774832,0.9835112,0.004177511,0.0062691993,0.0016083579,0.0003267898],"about_ca_topic_score_codex":0.000061002127,"about_ca_topic_score_gemma":0.00006232601,"teacher_disagreement_score":0.97937363,"about_ca_system_score_codex":0.00023199459,"about_ca_system_score_gemma":0.00066425453,"threshold_uncertainty_score":0.99999684},"labels":[],"label_agreement":null},{"id":"W4401990439","doi":"10.1109/dsn-s60304.2024.00018","title":"Harnessing Explainability to Improve ML Ensemble Resilience","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Resilience (materials science); Computer science; Materials science","score_opus":0.021838976802734607,"score_gpt":0.2982170399967199,"score_spread":0.2763780631939853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401990439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036958512,0.00017792342,0.93819904,0.005176844,0.0012679261,0.00031051142,8.570863e-7,0.0009183503,0.016990053],"genre_scores_gemma":[0.9234547,0.000004423103,0.06999552,0.00078799523,0.000115078066,0.000060837807,3.3794913e-7,0.000014920195,0.0055661644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99756473,0.00007582941,0.0003489047,0.001016071,0.00038215748,0.0006122864],"domain_scores_gemma":[0.99820596,0.00028730783,0.000025798881,0.0010824664,0.00015348181,0.00024497087],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088442885,0.00019135713,0.00016771094,0.00019597042,0.00024155354,0.0011125383,0.0012171724,0.00006860777,0.00008958094],"category_scores_gemma":[0.0003556529,0.00016754068,0.00008287387,0.0013379023,0.000068478665,0.0016804718,0.0005596054,0.00019004103,0.0018196199],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072815624,0.000055926605,0.000077551194,0.00007529373,0.000007276327,0.0001321101,0.0030554913,0.00077986345,0.08177869,0.50396115,0.0045020897,0.4055673],"study_design_scores_gemma":[0.000032598116,0.0001903516,0.00017943213,0.00009099503,0.000004388462,0.000023242415,0.0006966371,0.22370234,0.66733605,0.072611764,0.034657218,0.0004750047],"about_ca_topic_score_codex":0.00030686328,"about_ca_topic_score_gemma":0.00010858384,"teacher_disagreement_score":0.8864962,"about_ca_system_score_codex":0.00019136444,"about_ca_system_score_gemma":0.00022658467,"threshold_uncertainty_score":0.9999244},"labels":[],"label_agreement":null},{"id":"W4402130453","doi":"10.1080/0960085x.2024.2395531","title":"Reducing the incidence of biased algorithmic decisions through feature importance transparency: an empirical study","year":2024,"lang":"en","type":"article","venue":"European Journal of Information Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; McMaster University; University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Transparency (behavior); Computer science; Strategic information system; Empirical research; Feature (linguistics); Data science; Information system; Management information systems; Computer security; Statistics; Mathematics; Engineering","score_opus":0.06517048671140001,"score_gpt":0.33219287540864634,"score_spread":0.2670223886972463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402130453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19655141,0.00081053766,0.7984072,0.0006962792,0.0015095498,0.00036004256,0.0000054744646,0.0000652199,0.0015943148],"genre_scores_gemma":[0.9937848,0.000042604697,0.005825852,0.00010898454,0.00019631692,0.0000028339468,0.0000013202097,0.000009896126,0.00002742131],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964968,0.00077040395,0.0015537089,0.00014649081,0.000834629,0.00019798112],"domain_scores_gemma":[0.9976818,0.00033060444,0.00073554146,0.000574147,0.0005789547,0.00009896155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046704565,0.0001481699,0.0002498748,0.00024065941,0.00018734379,0.0007016852,0.001544852,0.000027162463,0.0000051944508],"category_scores_gemma":[0.00033240006,0.00009249856,0.00011421036,0.0010597986,0.000054256376,0.0058427476,0.00007734742,0.00040898361,0.00006783157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012851751,0.00048321136,0.004796237,0.00029195455,0.00034919812,0.0014605141,0.6854564,0.11318206,0.0016729695,0.015027623,0.022672916,0.1544784],"study_design_scores_gemma":[0.0012273992,0.005698993,0.028362881,0.00490882,0.00016574137,0.0044636517,0.12767012,0.73915577,0.0045232745,0.0011815667,0.081465505,0.0011762646],"about_ca_topic_score_codex":0.000028831822,"about_ca_topic_score_gemma":0.0000051224742,"teacher_disagreement_score":0.79723334,"about_ca_system_score_codex":0.000071760034,"about_ca_system_score_gemma":0.000237001,"threshold_uncertainty_score":0.6766367},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03465311982436982,"score_gpt":0.28141044563202017,"score_spread":0.24675732580765036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402202846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95873326,0.008186368,0.029494023,0.0011280467,0.00089475885,0.0004535125,0.0000037487127,0.0003609339,0.00074533396],"genre_scores_gemma":[0.99897975,0.00016336872,0.00009280502,0.00006309303,0.00018046654,0.000037126723,0.0000040497202,0.000018494522,0.0004608324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980467,0.00020361773,0.00025504845,0.000541923,0.00025374835,0.00069898146],"domain_scores_gemma":[0.99912184,0.00036322087,0.000031313102,0.00035679716,0.000034400902,0.00009242235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009753426,0.00017915748,0.00022514243,0.00021152217,0.00009866235,0.00072868867,0.00048662492,0.00010908178,0.0000034417394],"category_scores_gemma":[0.00009110409,0.00017438232,0.000037155332,0.000614045,0.000036621077,0.00084788277,0.00020834377,0.00061955693,0.00007717958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007445006,0.0002836064,0.0011089038,0.00021776052,0.00010698066,0.0006850506,0.005894092,0.004934493,0.002653652,0.7598102,0.0062034917,0.21802731],"study_design_scores_gemma":[0.00042645528,0.00066776684,0.0010638754,0.00031240168,0.00001621001,0.00012381967,0.00032690054,0.7193784,0.09907631,0.046678055,0.1308971,0.0010327153],"about_ca_topic_score_codex":0.00069238566,"about_ca_topic_score_gemma":0.0008871775,"teacher_disagreement_score":0.7144439,"about_ca_system_score_codex":0.00031906003,"about_ca_system_score_gemma":0.0003133139,"threshold_uncertainty_score":0.7111105},"labels":[],"label_agreement":null},{"id":"W4402263850","doi":"10.1109/imsa61967.2024.10652803","title":"Focus on Carbon Dioxide Footprint of AI/ML Model Training","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Ericsson (Canada)","funders":"","keywords":"Carbon footprint; Focus (optics); Carbon dioxide; Footprint; Computer science; Training (meteorology); Artificial intelligence; Chemistry; Meteorology; Greenhouse gas; Geology","score_opus":0.061446737731810634,"score_gpt":0.2987434715150127,"score_spread":0.23729673378320204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402263850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04213897,0.000077539495,0.83492297,0.0027907141,0.0003021396,0.00012246081,7.135058e-7,0.00037882003,0.11926566],"genre_scores_gemma":[0.9829654,0.0000077317145,0.015960066,0.0001976207,0.00004212255,0.000013540408,1.5261361e-7,0.000013903667,0.00079944707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858665,0.000029852179,0.0002965744,0.000438283,0.00032687635,0.0003217342],"domain_scores_gemma":[0.99914116,0.00014103537,0.00002945988,0.0005424034,0.000060998384,0.00008496845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035940672,0.00013687268,0.00016909966,0.000183396,0.000038493738,0.00010472604,0.0006551037,0.000057757996,0.000007932672],"category_scores_gemma":[0.000050121816,0.00011776793,0.0000923909,0.0004439667,0.00004369022,0.00018812747,0.00018273531,0.0002022955,0.000044015924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003506779,0.00002399159,0.0000068509507,0.000015032208,0.0000111796235,0.000025533014,0.0025593794,0.021392824,0.015198795,0.84933776,0.000034577253,0.11139056],"study_design_scores_gemma":[0.0000148430045,0.0000757723,0.000005456858,0.000040162373,0.0000022126749,0.0000027670555,0.00010205778,0.58366334,0.2966911,0.11917938,0.00013376793,0.00008912505],"about_ca_topic_score_codex":0.00031437568,"about_ca_topic_score_gemma":0.000099152305,"teacher_disagreement_score":0.9408264,"about_ca_system_score_codex":0.00006488332,"about_ca_system_score_gemma":0.00016017623,"threshold_uncertainty_score":0.48024368},"labels":[],"label_agreement":null},{"id":"W4402460553","doi":"10.1007/s10664-024-10536-7","title":"Quality issues in machine learning software systems","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software quality; Quality (philosophy); Software engineering; Software; Software development; Operating system","score_opus":0.04127975929546383,"score_gpt":0.3288721992370755,"score_spread":0.28759243994161166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402460553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039526228,0.008408898,0.94716465,0.00058844907,0.0012090023,0.00017051201,0.0000033574008,0.0028855617,0.00004334557],"genre_scores_gemma":[0.9464851,0.000081469734,0.051937096,0.00010369704,0.00030808238,0.00006983627,0.000009740812,0.00006422296,0.00094077474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767184,0.00012103039,0.00053643616,0.00063818623,0.00043086975,0.00060161],"domain_scores_gemma":[0.9982638,0.001049557,0.0000370722,0.00042776906,0.000057517314,0.00016433545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008984094,0.00026795318,0.00033805342,0.0003060975,0.000090160414,0.00054447865,0.0006957834,0.0001397366,0.000027661921],"category_scores_gemma":[0.0019475752,0.00026049907,0.000106784064,0.001279749,0.00002226869,0.00075463945,0.0003044161,0.0006934678,0.00031760873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000089139785,0.00011718368,0.18421172,0.0010532324,0.000066855384,0.00094632775,0.0050369664,0.7523727,0.00047235907,0.019435294,0.0016828073,0.034595694],"study_design_scores_gemma":[0.00008031623,0.00007946778,0.008508105,0.0004067263,0.000004291565,0.0000380241,0.000068309375,0.864954,0.0009978769,0.00079935533,0.123400934,0.00066261814],"about_ca_topic_score_codex":0.0005549881,"about_ca_topic_score_gemma":0.000027773458,"teacher_disagreement_score":0.9069589,"about_ca_system_score_codex":0.00024914808,"about_ca_system_score_gemma":0.00006160173,"threshold_uncertainty_score":0.99998474},"labels":[],"label_agreement":null},{"id":"W4402464099","doi":"10.11159/cist24.158","title":"Enhancing Model Explainability with CTGAN-LIME: A Novel Approach for Interpretable Machine Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Lime; Artificial intelligence; Machine learning; Geology","score_opus":0.010997941517334667,"score_gpt":0.21960067466094652,"score_spread":0.20860273314361186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402464099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05059748,0.0005527653,0.94757664,0.00013935461,0.00038562124,0.00040323008,0.0000010490338,0.00017291315,0.00017095158],"genre_scores_gemma":[0.96786636,0.000007930112,0.03150756,0.00002320586,0.000056484456,0.0000674302,1.02784604e-7,0.0000125199385,0.000458415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828213,0.000005184141,0.00027290644,0.00065922446,0.0003504565,0.00043011093],"domain_scores_gemma":[0.9992413,0.00018477812,0.00007895624,0.00015296732,0.00022244753,0.000119573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095118734,0.00019898987,0.00026363588,0.00029963648,0.00029801368,0.00086148025,0.0007666935,0.000034170207,6.956499e-8],"category_scores_gemma":[0.0000847595,0.0001304308,0.0000443857,0.0014036945,0.00014651084,0.0006542384,0.00028216306,0.00029260424,1.37999e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040341543,0.000092574686,0.0002840177,0.0011052929,0.000041991232,0.0000011570077,0.0011420255,0.30420288,0.039684124,0.6457474,0.000052570133,0.007605573],"study_design_scores_gemma":[0.000077446326,0.00020196979,0.00002381189,0.00036597674,0.0000080101345,0.000036290414,0.00001828053,0.9826112,0.016128235,0.00013715799,0.0002195757,0.0001720534],"about_ca_topic_score_codex":0.000025040494,"about_ca_topic_score_gemma":0.0000011679653,"teacher_disagreement_score":0.9172689,"about_ca_system_score_codex":0.00007076858,"about_ca_system_score_gemma":0.00008286337,"threshold_uncertainty_score":0.8307274},"labels":[],"label_agreement":null},{"id":"W4402503164","doi":"10.1016/j.jogc.2024.102639","title":"Imagerie time-lapse et intelligence artificielle : Ce n’est que la fin du début!","year":2024,"lang":"fr","type":"editorial","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Medicine; Humanities","score_opus":0.014589047194357482,"score_gpt":0.2487246035797566,"score_spread":0.23413555638539912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402503164","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032108135,0.022840803,0.011322229,0.005918366,0.9486288,0.00031087938,0.00016514273,0.00002956191,0.007573398],"genre_scores_gemma":[0.5310035,0.04019919,0.02769609,0.006632494,0.23940043,0.000114912196,0.00017309697,0.00089784455,0.15388249],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99369025,0.00077816145,0.0021206448,0.00089893263,0.0014371353,0.0010748804],"domain_scores_gemma":[0.9664863,0.028381385,0.0014502339,0.0006459585,0.0022687465,0.0007673971],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002914977,0.00073649787,0.0012673726,0.0007928057,0.00042302132,0.0011238059,0.0020645566,0.001094232,0.0009823355],"category_scores_gemma":[0.028982818,0.00071407715,0.00030489356,0.0019470769,0.0005425467,0.0007663357,0.0008818152,0.0034763166,0.00014615218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011695668,0.0002722521,0.00015266419,0.00028412134,0.00027344484,0.03907684,0.0021853473,0.0039129285,0.00004130734,0.018145481,0.83506876,0.100575164],"study_design_scores_gemma":[0.00019085327,0.0007342062,0.00013341966,0.0001093811,0.00017388434,0.00036451948,0.0006593918,0.021037146,0.0005194169,0.005291281,0.97010374,0.0006827589],"about_ca_topic_score_codex":0.05810168,"about_ca_topic_score_gemma":0.07458182,"teacher_disagreement_score":0.7092284,"about_ca_system_score_codex":0.002837469,"about_ca_system_score_gemma":0.02443207,"threshold_uncertainty_score":0.9999309},"labels":[],"label_agreement":null},{"id":"W4402524684","doi":"10.1145/3696009","title":"Artificial Intelligence and the Future of Evaluation: From Augmented to Automated Evaluation","year":2024,"lang":"en","type":"article","venue":"Digital Government Research and Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial intelligence; Computer science","score_opus":0.12135520286618941,"score_gpt":0.42697036054730436,"score_spread":0.30561515768111497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402524684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2645188,0.033837017,0.37860554,0.21781373,0.0024758459,0.009306395,0.00028833217,0.000735185,0.092419155],"genre_scores_gemma":[0.99788535,0.00025583096,0.0013543847,0.00014113779,0.0001491641,0.0001100119,0.000008126879,0.0000073628944,0.000088631525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99506605,0.00071967556,0.00033321508,0.00047911287,0.0031246457,0.00027731547],"domain_scores_gemma":[0.99403584,0.0047050435,0.00007100615,0.00040530247,0.0006511929,0.00013158757],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008671964,0.00011454629,0.00012416414,0.00007430212,0.0001951259,0.0017650123,0.0003593676,0.00004865835,0.000053714884],"category_scores_gemma":[0.0045829895,0.000081414364,0.000027100903,0.00087721186,0.00022591515,0.0022700173,0.00047718396,0.00024308455,0.00008602482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004136293,0.00010132359,0.000011566388,0.00001804291,0.00006323012,0.000014278534,0.003202456,0.00016304181,0.00054478465,0.21463028,0.0012408375,0.7795965],"study_design_scores_gemma":[0.0001013953,0.00038409905,0.00013979783,0.00008083322,0.000033775792,0.000021799142,0.008354261,0.83746344,0.009143619,0.123848446,0.020291103,0.00013742567],"about_ca_topic_score_codex":0.00014333284,"about_ca_topic_score_gemma":0.000038981427,"teacher_disagreement_score":0.8373004,"about_ca_system_score_codex":0.00021311094,"about_ca_system_score_gemma":0.0002202089,"threshold_uncertainty_score":0.9992713},"labels":[],"label_agreement":null},{"id":"W4402577460","doi":"10.3390/app14188287","title":"Alzheimer’s Multiclassification Using Explainable AI Techniques","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Servier; Iran Telecommunication Research Center; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Ministry of Science and ICT, South Korea; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Psychology","score_opus":0.11531692364793643,"score_gpt":0.36214081461218106,"score_spread":0.24682389096424462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402577460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009422526,0.0008636375,0.95960027,0.0024691327,0.0005393143,0.0004346355,9.656438e-7,0.001285843,0.025383651],"genre_scores_gemma":[0.8748081,0.000016277674,0.12447546,0.00043445794,0.000098134304,0.000067187335,6.1444285e-7,0.000010070381,0.00008972224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978935,0.00003881457,0.00029479657,0.00078244496,0.00048872695,0.0005017312],"domain_scores_gemma":[0.99916184,0.00016281406,0.000056742498,0.00045335683,0.000071856884,0.00009340131],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011724883,0.00016955483,0.00013643173,0.0003251953,0.0006240259,0.0012632873,0.0013616383,0.00007403782,0.000028611346],"category_scores_gemma":[0.000031903637,0.00014664869,0.00005063457,0.0019513692,0.00037616192,0.001617572,0.00024021305,0.00016455041,0.000301563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001118617,0.000025295314,0.000015923455,0.000011030916,0.000008772464,0.000011163034,0.00090143806,0.00041287628,0.10053128,0.81307137,0.00063255907,0.08437716],"study_design_scores_gemma":[0.000012856942,0.000036261925,0.000009632597,0.000029632727,0.00000897185,0.000013197645,0.00047427256,0.4144246,0.52629286,0.04534183,0.013133186,0.00022268848],"about_ca_topic_score_codex":0.0001362131,"about_ca_topic_score_gemma":0.000012502137,"teacher_disagreement_score":0.86538553,"about_ca_system_score_codex":0.0000791145,"about_ca_system_score_gemma":0.00025529167,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W4402716388","doi":"10.1109/cvpr52733.2024.00547","title":"Building Optimal Neural Architectures Using Interpretable Knowledge","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning","score_opus":0.0376890908295621,"score_gpt":0.33702948326634236,"score_spread":0.29934039243678023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402716388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13732831,0.0010130103,0.85238385,0.0002999047,0.0010727368,0.000098055,5.2350464e-7,0.0006529477,0.0071506556],"genre_scores_gemma":[0.819987,0.0000018204613,0.17904027,0.000118434466,0.00014454979,0.0000054577504,1.6202326e-7,0.000015333884,0.0006869613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985417,0.000061690575,0.00024092368,0.0005178842,0.00016386884,0.00047390128],"domain_scores_gemma":[0.9992101,0.00019325898,0.000020684563,0.0004145635,0.000053232518,0.00010811157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029067814,0.00017270468,0.00014211834,0.00026636806,0.00015307675,0.0008695417,0.0009238627,0.000050644867,0.00009413157],"category_scores_gemma":[0.00005279514,0.00014573938,0.00010283331,0.00074153545,0.00006021618,0.0006114174,0.0005621646,0.00023827201,0.0002104304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074627533,0.000057351877,0.000043096272,0.000087883556,0.000044257242,0.00018083338,0.004830419,0.086230524,0.08684941,0.5835749,0.0009656675,0.23712824],"study_design_scores_gemma":[0.000013640442,0.000038433922,0.0000064042706,0.00005983911,0.000004700052,0.000079334066,0.00005442316,0.9105096,0.07779349,0.0072258087,0.004040391,0.0001739495],"about_ca_topic_score_codex":0.00015384499,"about_ca_topic_score_gemma":0.000026144404,"teacher_disagreement_score":0.82427907,"about_ca_system_score_codex":0.00008530803,"about_ca_system_score_gemma":0.00010096918,"threshold_uncertainty_score":0.8385011},"labels":[],"label_agreement":null},{"id":"W4402796311","doi":"10.3390/tropicalmed9090216","title":"Enhancing the Interpretability of Malaria and Typhoid Diagnosis with Explainable AI and Large Language Models","year":2024,"lang":"en","type":"article","venue":"Tropical Medicine and Infectious Disease","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Interpretability; Transparency (behavior); Malaria; Computer science; Typhoid fever; Artificial intelligence; Machine learning; Data science; Risk analysis (engineering); Medicine; Computer security; Pathology","score_opus":0.01093516839986291,"score_gpt":0.26984133428355545,"score_spread":0.25890616588369253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402796311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72948086,0.0062501878,0.25899357,0.0044396413,0.00009337342,0.00024320834,0.0000038455437,0.00008914656,0.00040617574],"genre_scores_gemma":[0.99865454,0.000370676,0.00012555484,0.00070020865,0.00006315464,0.000052135383,7.0377297e-7,0.000007270887,0.00002576791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990342,0.000081145394,0.00019864873,0.0003278601,0.00015312944,0.00020497311],"domain_scores_gemma":[0.99908733,0.00037001015,0.00002827633,0.00026881098,0.000053268068,0.00019229775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021366608,0.00012459526,0.00018823922,0.000070924674,0.0001236029,0.0000849192,0.00011513662,0.000031544387,0.000031648342],"category_scores_gemma":[0.00023801447,0.00007072046,0.000021496535,0.00023280724,0.0002737658,0.00045480332,0.00015690908,0.00016429191,0.0000014203591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017307131,0.0003104445,0.12477285,0.0013576328,0.00012746574,0.00028791768,0.025330534,0.00006592969,0.00090623763,0.7872672,0.00055790594,0.05884281],"study_design_scores_gemma":[0.001892952,0.0042890795,0.09014812,0.002572043,0.00058059435,0.00019546691,0.007072808,0.6826181,0.00976371,0.19546412,0.0043750103,0.0010280159],"about_ca_topic_score_codex":0.0003314224,"about_ca_topic_score_gemma":0.00017614457,"teacher_disagreement_score":0.68255216,"about_ca_system_score_codex":0.000017945633,"about_ca_system_score_gemma":0.000046096695,"threshold_uncertainty_score":0.28838968},"labels":[],"label_agreement":null},{"id":"W4402815995","doi":"10.1016/j.jbusres.2024.114981","title":"Post hoc explanations improve consumer responses to algorithmic decisions","year":2024,"lang":"en","type":"article","venue":"Journal of Business Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Post hoc; Post-hoc analysis; Computer science; Psychology; Advertising; Business; Mathematics; Statistics; Medicine","score_opus":0.13025680298592354,"score_gpt":0.4249878653474128,"score_spread":0.29473106236148927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402815995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16308735,0.0035351824,0.78152114,0.047783,0.002693474,0.00046593603,0.000032311647,0.0000968458,0.00078477233],"genre_scores_gemma":[0.9335572,0.0010756744,0.060113963,0.00037724074,0.00079805555,0.00004017752,0.0000017326968,0.000044273016,0.003991659],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965501,0.00034486418,0.000623724,0.0003477727,0.0015616671,0.0005719169],"domain_scores_gemma":[0.9904165,0.0030868102,0.000079662306,0.00056497735,0.0055150557,0.0003369706],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038453445,0.00013670138,0.0002304005,0.0023609102,0.00036547464,0.00126348,0.0017108228,0.0000817461,0.00009196206],"category_scores_gemma":[0.0058178976,0.00010921444,0.00010455058,0.0044697355,0.00013579031,0.0015656088,0.0005138888,0.00068095105,0.0008541145],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004840679,0.000366175,0.00011289752,0.00008019897,0.00014075534,0.004321213,0.004478053,0.0008632817,0.14592794,0.05094865,0.048205208,0.74407154],"study_design_scores_gemma":[0.00094053097,0.0036248898,0.014206803,0.0029678715,0.00006199314,0.0037601998,0.006032528,0.0870779,0.117050074,0.06803905,0.6947167,0.001521449],"about_ca_topic_score_codex":0.00011921041,"about_ca_topic_score_gemma":0.000050206745,"teacher_disagreement_score":0.77046984,"about_ca_system_score_codex":0.0002537626,"about_ca_system_score_gemma":0.0016904919,"threshold_uncertainty_score":0.9999238},"labels":[],"label_agreement":null},{"id":"W4402906011","doi":"10.1167/jov.24.10.1245","title":"Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Concordance; Illusion; Lightness; Perception; Optical illusion; Psychology; Cognitive psychology; Artificial intelligence; Medicine; Computer science; Neuroscience; Internal medicine","score_opus":0.025612894693779434,"score_gpt":0.3638951594530557,"score_spread":0.3382822647592763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402906011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4613758,0.0005937386,0.5337107,0.0031861407,0.0004454444,0.00006594183,4.366876e-7,0.000045769193,0.000575977],"genre_scores_gemma":[0.98259157,0.00014827907,0.016585583,0.00033657515,0.00020299363,0.0000010843905,4.5130477e-7,0.000012124573,0.00012135722],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865866,0.000086184584,0.00039737715,0.00024662065,0.0004155486,0.00019561185],"domain_scores_gemma":[0.99910194,0.00013603519,0.00017979534,0.0002127826,0.0002779707,0.00009149108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053723773,0.00013061197,0.00020632977,0.00014846206,0.00031246807,0.0009204208,0.0003593948,0.00005967715,0.000032910746],"category_scores_gemma":[0.00003261186,0.00009066742,0.00005665668,0.00039546023,0.00011049178,0.0036135518,0.00012757938,0.00033408275,0.000020763377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007125881,0.00032844892,0.001180148,0.0002645685,0.0000961097,0.0015716525,0.02391372,0.0015281077,0.6929769,0.11879274,0.006389773,0.1528866],"study_design_scores_gemma":[0.002315263,0.01277648,0.09319536,0.019542385,0.00033338685,0.008490632,0.018139899,0.42746884,0.109199286,0.17630897,0.12934521,0.0028842995],"about_ca_topic_score_codex":0.0000335656,"about_ca_topic_score_gemma":0.000018611403,"teacher_disagreement_score":0.5837776,"about_ca_system_score_codex":0.00009192257,"about_ca_system_score_gemma":0.00012059844,"threshold_uncertainty_score":0.88756394},"labels":[],"label_agreement":null},{"id":"W4402981370","doi":"10.1109/otcon60325.2024.10687856","title":"The Interpretability of Invariant Neural Networks in Deep Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Invariant (physics); Artificial neural network; Deep learning; Machine learning; Mathematics","score_opus":0.01443153052582199,"score_gpt":0.2620617949792454,"score_spread":0.24763026445342343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402981370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033042297,0.0009771101,0.9578816,0.0012593853,0.0005719323,0.00012647697,5.1264823e-8,0.00014544753,0.005995675],"genre_scores_gemma":[0.99855,0.00002972523,0.0011290419,0.00006687596,0.000025802721,0.000009622963,1.5841148e-7,0.000004838011,0.0001839384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988349,0.0001792286,0.00031628532,0.00026879244,0.00013748264,0.0002632821],"domain_scores_gemma":[0.998707,0.0008180432,0.000030457752,0.00036560325,0.000042891596,0.0000360177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011033112,0.00007990643,0.000100837424,0.000059932285,0.00008156561,0.00026201288,0.00076011446,0.000038745424,0.000027719676],"category_scores_gemma":[0.00023259038,0.000052149666,0.000054841286,0.0006542599,0.00008699774,0.00042660104,0.00033875345,0.00031259036,0.000022508597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009188881,0.00002534258,0.002288335,0.000017572469,0.000009366981,0.000032323016,0.0035465597,0.10000221,0.00022357737,0.54816484,0.00004393302,0.34563676],"study_design_scores_gemma":[0.00001095662,0.000042427946,0.0005512247,0.000018351817,0.0000010108909,0.0000041183835,0.00031107094,0.9880665,0.001199302,0.009231426,0.0005037694,0.000059872],"about_ca_topic_score_codex":0.00028159807,"about_ca_topic_score_gemma":0.000743457,"teacher_disagreement_score":0.9655077,"about_ca_system_score_codex":0.000042022355,"about_ca_system_score_gemma":0.000028649714,"threshold_uncertainty_score":0.25265962},"labels":[],"label_agreement":null},{"id":"W4403113340","doi":"10.1093/bioinformatics/btae589","title":"Learning to explain is a good biomedical few-shot learner","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Shot (pellet); One shot; Artificial intelligence; Chemistry; Engineering; Mechanical engineering","score_opus":0.035562380217422467,"score_gpt":0.29649448069667717,"score_spread":0.2609321004792547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403113340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012516186,0.00018953565,0.9557982,0.0070677237,0.0012557029,0.00032057555,0.0000061762353,0.0010348755,0.02181103],"genre_scores_gemma":[0.68541676,0.000098615594,0.2954409,0.006416241,0.0005269985,0.00008907572,0.00002210421,0.000066246175,0.011923065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979529,0.000040738276,0.0005378892,0.00029382465,0.00059773144,0.000576917],"domain_scores_gemma":[0.9988585,0.00018262268,0.000056647303,0.0005071816,0.00007729267,0.00031773842],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00068423885,0.00020506528,0.00018907216,0.00038232392,0.00021225504,0.0008585477,0.0009559494,0.00012224662,0.00016881239],"category_scores_gemma":[0.0002237391,0.0001779664,0.00010190538,0.0013730344,0.00006360257,0.0011763547,0.0004868513,0.0003638254,0.009011252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008806258,0.00010227287,0.000099361874,0.00035725092,0.00007211043,0.0001520492,0.10038531,0.00082361,0.0013289938,0.13824886,0.08174791,0.6766735],"study_design_scores_gemma":[0.000037257898,0.00023701174,0.000012082659,0.0001007346,0.0000050507283,0.000034191027,0.0021034537,0.54781,0.004902814,0.0009027354,0.4436105,0.00024415128],"about_ca_topic_score_codex":0.00003027955,"about_ca_topic_score_gemma":0.0000052500827,"teacher_disagreement_score":0.67642933,"about_ca_system_score_codex":0.000104503415,"about_ca_system_score_gemma":0.00017054021,"threshold_uncertainty_score":0.9917604},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","score_opus":0.10430319272960026,"score_gpt":0.3456309742213749,"score_spread":0.24132778149177464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403334020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7104168,0.0007533851,0.2503306,0.0020168375,0.000520216,0.0008307959,0.0000039608512,0.00057023787,0.03455719],"genre_scores_gemma":[0.9958168,0.0000072861467,0.003187867,0.00009534427,0.000059317037,0.000056893467,0.000004842114,0.0000137644365,0.0007578763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973073,0.0003559139,0.00040601558,0.000522015,0.0010999682,0.00030879935],"domain_scores_gemma":[0.99827415,0.00030709818,0.00012106217,0.0007383279,0.00049617235,0.00006320511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002414408,0.00019084761,0.00019694703,0.00017058272,0.00026533034,0.0007339276,0.0011243732,0.00006123649,0.00014955063],"category_scores_gemma":[0.000085091735,0.00011099556,0.000069339316,0.0009812253,0.00014130995,0.0009803624,0.00021758502,0.00014296488,0.00008668765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010490661,0.0002644316,0.0018724753,0.00013532903,0.00024406052,0.000015938365,0.016286287,0.0022233585,0.017395169,0.8652802,0.003851483,0.092420764],"study_design_scores_gemma":[0.00014806449,0.00062032486,0.0021894095,0.00044248297,0.00015497167,0.000019526778,0.0028535286,0.20130765,0.72989625,0.060121004,0.0018047419,0.00044204076],"about_ca_topic_score_codex":0.00037944474,"about_ca_topic_score_gemma":0.00031699607,"teacher_disagreement_score":0.8051592,"about_ca_system_score_codex":0.00007011749,"about_ca_system_score_gemma":0.00023199312,"threshold_uncertainty_score":0.7077281},"labels":[],"label_agreement":null},{"id":"W4403335660","doi":"10.3390/app14209231","title":"Helping CNAs Generate CVSS Scores Faster and More Confidently Using XAI","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","score_opus":0.06350634013231286,"score_gpt":0.31582306430185847,"score_spread":0.2523167241695456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403335660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7012504,0.0013011605,0.29019552,0.0012347955,0.00079380214,0.00024672167,0.0000015372647,0.0002674906,0.0047085974],"genre_scores_gemma":[0.979622,0.00003055402,0.019250281,0.0007381107,0.00014887148,0.000015582658,4.107416e-7,0.0000098639,0.00018430722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978578,0.00003335888,0.00027514528,0.00082569855,0.00048392973,0.00052408344],"domain_scores_gemma":[0.9993237,0.00014605408,0.000056011286,0.0003010741,0.000047376077,0.00012574096],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00083743554,0.00018670074,0.00016867771,0.00025224313,0.0006183653,0.002193977,0.00093284005,0.00005461822,0.000022148479],"category_scores_gemma":[0.00002150813,0.00015570923,0.00003768956,0.001132109,0.00064187427,0.0010860678,0.00043199788,0.0001372019,0.000115305476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033923022,0.000019139708,0.00038883265,0.000058448055,0.000018338782,0.00007184388,0.006415013,0.0044501317,0.19936451,0.7520456,0.00030224514,0.036862534],"study_design_scores_gemma":[0.000054835535,0.0000587408,0.00017898549,0.00012032071,0.000011326429,0.0000617585,0.0020002003,0.7299814,0.2363631,0.028991647,0.0017268369,0.00045081414],"about_ca_topic_score_codex":0.00017759147,"about_ca_topic_score_gemma":0.000044655248,"teacher_disagreement_score":0.7255313,"about_ca_system_score_codex":0.000038667327,"about_ca_system_score_gemma":0.00017582848,"threshold_uncertainty_score":0.9988418},"labels":[],"label_agreement":null},{"id":"W4403447509","doi":"10.1109/vl/hcc60511.2024.00024","title":"Supporting User Critiques of AI Systems via Training Dataset Explanations: Investigating Critique Properties and the Impact of Presentation Style","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Style (visual arts); Presentation (obstetrics); Computer science; Training (meteorology); Artificial intelligence; Natural language processing; Human–computer interaction; Information retrieval; History","score_opus":0.09466484882499099,"score_gpt":0.3889581525787565,"score_spread":0.2942933037537655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403447509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2551812,0.0017769318,0.7386095,0.002456978,0.00017754696,0.0008797465,0.00013353459,0.00020469373,0.0005799037],"genre_scores_gemma":[0.99638176,0.00002233744,0.0033467687,0.00008436558,0.000032485805,0.000038711874,0.00003164517,0.000008810139,0.00005313168],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984888,0.00025378916,0.0005783028,0.00024282343,0.00023223615,0.0002040426],"domain_scores_gemma":[0.9988106,0.00052506226,0.0001244254,0.00028326697,0.00020704471,0.000049635146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013533689,0.00011144596,0.00020086888,0.00013667531,0.000106534055,0.00039505734,0.00034902935,0.000037698734,0.000010760793],"category_scores_gemma":[0.00060217816,0.00006907084,0.000048394773,0.00033650617,0.00024133123,0.001861031,0.00013256962,0.00012911283,0.0000020034681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023565395,0.000061518294,0.0015074714,0.0012264169,0.0001878513,0.000020308358,0.109799154,0.007245868,0.065476604,0.7979205,0.008443167,0.008087576],"study_design_scores_gemma":[0.00007511371,0.00008390369,0.00008824711,0.0003528329,0.000012035797,0.00003116889,0.011698519,0.89423436,0.08237569,0.01088844,0.000048783582,0.00011091103],"about_ca_topic_score_codex":0.007779019,"about_ca_topic_score_gemma":0.00010101064,"teacher_disagreement_score":0.88698846,"about_ca_system_score_codex":0.000024924424,"about_ca_system_score_gemma":0.00016808916,"threshold_uncertainty_score":0.9988283},"labels":[],"label_agreement":null},{"id":"W4403448788","doi":"10.1007/978-3-031-70300-3_20","title":"Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning Decisions","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"On the fly; Business; Computer science; Artificial intelligence; Operating system","score_opus":0.053308742019284594,"score_gpt":0.2749912044283917,"score_spread":0.2216824624091071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403448788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00078311004,0.01742369,0.8839565,0.0009614544,0.002270214,0.0008733481,0.000009279162,0.00015628917,0.09356613],"genre_scores_gemma":[0.9915238,0.0003226233,0.00013855228,0.00014311206,0.00037383748,0.000011172898,0.000014465809,0.00003845393,0.0074339854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816155,0.000098795914,0.00058400386,0.0005086872,0.00038251161,0.00026442634],"domain_scores_gemma":[0.99675065,0.0023118565,0.00027067875,0.00051921944,0.00009332994,0.000054259595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007344613,0.00030362527,0.0004254792,0.00027728907,0.00028164202,0.00032854054,0.0005621594,0.0003280881,0.000023438295],"category_scores_gemma":[0.00018394124,0.00020755787,0.000106672036,0.0002089123,0.00007828255,0.00009045385,0.0002105553,0.0009237073,0.00001334467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000383823,0.000005536455,0.000049742546,0.000033327247,0.000037619244,0.000043919048,0.0006323099,0.3140305,0.00003646149,0.68031067,0.00026737538,0.0045487387],"study_design_scores_gemma":[0.000055052806,0.00010975967,0.0000071958984,0.0023752546,0.000021381315,0.000026129781,0.000022897411,0.8826382,0.00009296754,0.100134596,0.014214138,0.0003024073],"about_ca_topic_score_codex":0.00026277936,"about_ca_topic_score_gemma":0.00036318297,"teacher_disagreement_score":0.9907407,"about_ca_system_score_codex":0.000091503025,"about_ca_system_score_gemma":0.000026318101,"threshold_uncertainty_score":0.84639645},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Health care; Data science; Computer science; Management science; Artificial intelligence; Engineering; Political science","score_opus":0.105293366208369,"score_gpt":0.36541360481908836,"score_spread":0.26012023861071937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403457107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02205643,0.04579627,0.90664214,0.019771652,0.00076435617,0.0018921845,0.000012783388,0.00027142375,0.0027927693],"genre_scores_gemma":[0.9848362,0.0068946145,0.0078066112,0.00025499897,0.000044754568,0.00012544438,0.000009301429,0.000010859085,0.000017212113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735767,0.00016361615,0.0014022205,0.00027032697,0.0004077825,0.00039841534],"domain_scores_gemma":[0.99792254,0.0010874517,0.00016043869,0.0005264085,0.00019291155,0.00011024738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034192237,0.00018680193,0.0004182084,0.0007197173,0.000050745617,0.000059105256,0.0006926072,0.00011680039,0.000009473817],"category_scores_gemma":[0.0005654348,0.00016771696,0.000020501757,0.0017889317,0.0003147786,0.0006851071,0.00020840629,0.00035600513,0.000027773516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009758169,0.00004456769,0.00041067402,0.0009586599,0.000006342401,0.000015098866,0.021713715,0.00023492266,0.000020744877,0.59346473,0.000058233723,0.38306254],"study_design_scores_gemma":[0.00017268043,0.0004921221,0.0026802588,0.0017817239,0.0000069640087,0.000032716758,0.018256929,0.7816449,0.0027253432,0.18576309,0.005971882,0.0004714039],"about_ca_topic_score_codex":0.0024129862,"about_ca_topic_score_gemma":0.0022167447,"teacher_disagreement_score":0.96277976,"about_ca_system_score_codex":0.00011683752,"about_ca_system_score_gemma":0.00021681092,"threshold_uncertainty_score":0.6839299},"labels":[],"label_agreement":null},{"id":"W4403458004","doi":"10.1016/j.ins.2024.121564","title":"Tree smoothing: Post-hoc regularization of tree ensembles for interpretable machine learning","year":2024,"lang":"en","type":"article","venue":"Information Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Austrian Science Fund","keywords":"Artificial intelligence; Regularization (linguistics); Smoothing; Tree (set theory); Computer science; Machine learning; Post hoc; Pattern recognition (psychology); Mathematics; Combinatorics; Medicine","score_opus":0.02549530159241103,"score_gpt":0.2852611363255154,"score_spread":0.2597658347331044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403458004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008243128,0.0002823919,0.97581387,0.0017753891,0.0005496253,0.00024823585,0.0000064378332,0.0002509225,0.012830012],"genre_scores_gemma":[0.96392864,0.00003075684,0.03515857,0.00030586042,0.000032500197,0.000027227179,0.000016852859,0.0000050791105,0.00049451157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851435,0.000044316574,0.0005249093,0.00021206903,0.00044708146,0.00025725216],"domain_scores_gemma":[0.99892396,0.00033055228,0.00018556557,0.00020161399,0.00030904432,0.00004924246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014424818,0.000114305025,0.00013737043,0.0005009473,0.0003170442,0.0009206681,0.0008297058,0.000054710472,0.00002200419],"category_scores_gemma":[0.000512339,0.00009538124,0.000078020465,0.0012025632,0.00014780542,0.0077934717,0.0001383225,0.00009503733,0.00006358843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019336332,0.000015501819,0.00010437702,0.00013678141,0.000011892935,7.756143e-7,0.016071439,0.008874127,0.005373507,0.3946871,0.0005217534,0.5741834],"study_design_scores_gemma":[0.000049314323,0.0003382511,0.00003716072,0.0000834915,0.0000043269424,0.000006474808,0.0011736788,0.92871124,0.03856662,0.012128675,0.018779399,0.000121368415],"about_ca_topic_score_codex":0.00008970698,"about_ca_topic_score_gemma":0.00006764442,"teacher_disagreement_score":0.9556855,"about_ca_system_score_codex":0.00003581252,"about_ca_system_score_gemma":0.00019514204,"threshold_uncertainty_score":0.88780236},"labels":[],"label_agreement":null},{"id":"W4403488183","doi":"10.3233/faia240601","title":"Locally-Minimal Probabilistic Explanations","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Probabilistic logic; Cornerstone; Computer science; Trustworthiness; Abductive reasoning; Artificial intelligence; Computation; Quality (philosophy); Machine learning; Cognition; Data science; Psychology; Epistemology; Algorithm; Computer security","score_opus":0.04014001326284693,"score_gpt":0.27440073486335786,"score_spread":0.23426072160051092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403488183","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040745467,0.0022957886,0.8254464,0.0014087593,0.00065286766,0.0011271249,0.0000414111,0.00024773277,0.16877583],"genre_scores_gemma":[0.07381814,0.009698251,0.2225346,0.0016858026,0.003525762,0.006439297,0.00040478335,0.0005781491,0.68131524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968674,0.00002069868,0.0009970638,0.0012356313,0.00038556405,0.00049361744],"domain_scores_gemma":[0.99830526,0.00017266237,0.00018955496,0.0009441749,0.00018627684,0.00020205225],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037178112,0.00046150127,0.00046404466,0.00075160275,0.00027333898,0.0004875117,0.0011996368,0.00038104612,0.0000797019],"category_scores_gemma":[0.00004954029,0.00049824186,0.00014491429,0.00049300323,0.00047060754,0.00038797437,0.00037165338,0.0007133957,0.0010672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042858164,0.000044950604,0.0000031876416,0.00005470206,0.000023195518,0.000021084863,0.00031695733,0.00043187212,0.000010734954,0.80559254,0.001637049,0.19185944],"study_design_scores_gemma":[0.0000068345485,0.000048517802,0.0000010632583,0.00013731158,0.000029656501,0.00001003953,0.00027934508,0.042844743,0.0004365402,0.8080002,0.14777736,0.00042840975],"about_ca_topic_score_codex":0.000036749167,"about_ca_topic_score_gemma":0.00021667793,"teacher_disagreement_score":0.60291183,"about_ca_system_score_codex":0.0002259392,"about_ca_system_score_gemma":0.00021874665,"threshold_uncertainty_score":0.9997469},"labels":[],"label_agreement":null},{"id":"W4403511510","doi":"10.1109/iv64223.2024.00053","title":"Towards Interpretable Emotion Classification: Evaluating LIME, SHAP, and Generative AI for Decision Explanations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Artificial intelligence; Generative grammar; Computer science; Machine learning","score_opus":0.10374473719291159,"score_gpt":0.4019556411696677,"score_spread":0.2982109039767561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403511510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006112178,0.0003186998,0.98094213,0.0076467013,0.00062730425,0.00040640938,0.0000055097835,0.0002648157,0.0036762697],"genre_scores_gemma":[0.7078038,0.000037276677,0.29002178,0.00058079313,0.00012836377,0.00015248207,0.000008809556,0.000012136826,0.0012545838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986342,0.000058056616,0.00028527895,0.000532606,0.00026695416,0.00022287354],"domain_scores_gemma":[0.9987245,0.0005320823,0.000041018142,0.0003051725,0.00031956463,0.00007763717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008123902,0.00012866543,0.00012224769,0.000200446,0.00029019342,0.00095746777,0.00034011653,0.00006559791,0.00008603486],"category_scores_gemma":[0.00042475836,0.000111628004,0.0000539333,0.00049974164,0.000037424434,0.0015399287,0.00014602307,0.0001038872,0.00011696177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005430413,0.000018476641,0.000012849313,0.000018142386,0.000014579301,0.0000015092371,0.0017526856,0.00037454144,0.005661353,0.5857266,0.005762395,0.40065143],"study_design_scores_gemma":[0.000038219343,0.00011033618,0.00009356749,0.00007467757,0.000009411403,0.000008593313,0.00040064976,0.90931135,0.015048694,0.071197025,0.0035794356,0.00012804761],"about_ca_topic_score_codex":0.000026787618,"about_ca_topic_score_gemma":0.00004710964,"teacher_disagreement_score":0.9089368,"about_ca_system_score_codex":0.000102966,"about_ca_system_score_gemma":0.00015751534,"threshold_uncertainty_score":0.92328835},"labels":[],"label_agreement":null},{"id":"W4403582422","doi":"10.1145/3627673.3679846","title":"Correcting Biases of Shapley Value Attributions for Informative Machine Learning Model Explanations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Concordia University","funders":"","keywords":"Attribution; Shapley value; Computer science; Artificial intelligence; Value (mathematics); Machine learning; Econometrics; Mathematics; Mathematical economics; Psychology; Game theory; Social psychology","score_opus":0.09731598112276447,"score_gpt":0.338583696414937,"score_spread":0.24126771529217256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403582422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049756304,0.00013630308,0.9900115,0.00059476786,0.00021164442,0.00023547756,0.00003791368,0.00036620515,0.0034305532],"genre_scores_gemma":[0.9316435,0.000011674186,0.06691878,0.00008622785,0.000024427425,0.000059263868,0.00003036739,0.000008156179,0.0012175916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998996,0.000030991312,0.0003487047,0.00020804364,0.0001750084,0.00024121153],"domain_scores_gemma":[0.99800605,0.0014484526,0.00007056564,0.00018657974,0.00023386601,0.00005446794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045646844,0.0001047557,0.00013022182,0.00024583188,0.00029158793,0.00017649919,0.00037408576,0.00003988789,0.000026247208],"category_scores_gemma":[0.0010630474,0.00009479305,0.000091710644,0.00068535807,0.000035922072,0.0012355004,0.00014634886,0.00014843055,0.00004145403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001976256,0.000019369201,0.00004408539,0.000027813625,0.000016560747,8.3403677e-7,0.003465398,0.42800352,0.00033386325,0.5556314,0.00041477627,0.012040441],"study_design_scores_gemma":[0.0000315184,0.000066261484,0.0000037809866,0.000065654356,0.0000072666767,0.0000067183423,0.0007939878,0.9447491,0.041174356,0.012350565,0.0006457931,0.00010496275],"about_ca_topic_score_codex":0.00022091033,"about_ca_topic_score_gemma":0.00010004485,"teacher_disagreement_score":0.92666787,"about_ca_system_score_codex":0.00006448324,"about_ca_system_score_gemma":0.00014573152,"threshold_uncertainty_score":0.38655484},"labels":[],"label_agreement":null},{"id":"W4403629161","doi":"10.1016/j.dim.2024.100082","title":"Trustworthy AI: AI developers’ lens to implementation challenges and opportunities","year":2024,"lang":"en","type":"article","venue":"Data and Information Management","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Trustworthiness; Lens (geology); Computer science; Through-the-lens metering; Data science; Engineering; Computer security","score_opus":0.12806200468131557,"score_gpt":0.3369980582022055,"score_spread":0.20893605352088995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403629161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009319253,0.0013818953,0.8979959,0.060889337,0.00037818373,0.0006799854,0.00010311669,0.0002765599,0.03736311],"genre_scores_gemma":[0.7350722,0.118689835,0.07072893,0.06979202,0.0002641623,0.00037341623,0.0031436407,0.000040438994,0.0018953702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920905,0.000017346994,0.0002425283,0.0001954029,0.00017711928,0.00015856641],"domain_scores_gemma":[0.9994742,0.000016600407,0.00002639685,0.0003795955,0.000043138185,0.00006005362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044763216,0.000089418485,0.00006559761,0.00026256288,0.000113452865,0.00075272174,0.00038278208,0.000017264114,0.000027352018],"category_scores_gemma":[0.0000056344893,0.00008363942,0.000006722587,0.00013679452,0.000017868058,0.011618811,0.0008767544,0.000045455767,0.00014213017],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.613603e-7,0.0000016167039,0.0000031616357,0.00007559729,0.000011689312,0.0000029877497,0.0032368489,0.000007364561,4.971304e-7,0.4102776,0.01610772,0.57027394],"study_design_scores_gemma":[0.000043865766,0.00003504588,0.0006239939,0.00002915154,0.000007790779,0.000004019265,0.0088083185,0.04604135,0.000046842233,0.0016403879,0.9426015,0.00011775139],"about_ca_topic_score_codex":0.000021182026,"about_ca_topic_score_gemma":0.000028515973,"teacher_disagreement_score":0.92649376,"about_ca_system_score_codex":0.000022035596,"about_ca_system_score_gemma":0.00002145277,"threshold_uncertainty_score":0.8423357},"labels":[],"label_agreement":null},{"id":"W4403674930","doi":"10.1109/tevc.2024.3476443","title":"Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Evolutionary computation; Computer science; Artificial intelligence; Computation; Human-based evolutionary computation; Evolutionary algorithm; Intelligent decision support system; Interactive evolutionary computation; Evolutionary programming; Algorithm","score_opus":0.031352900983911074,"score_gpt":0.2893085765388213,"score_spread":0.2579556755549102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403674930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002674549,0.0013865785,0.98622626,0.004064394,0.003124381,0.0009768932,0.000033782486,0.0010048021,0.0005083672],"genre_scores_gemma":[0.9691435,0.00008969829,0.029083483,0.00044219664,0.00012741036,0.0002000306,0.00002347844,0.000043788485,0.00084638305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966747,0.0002489008,0.0006800764,0.0010555476,0.0007564189,0.0005843216],"domain_scores_gemma":[0.9983469,0.000489435,0.00008412296,0.00035771469,0.00040653103,0.00031527743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046436983,0.0003837509,0.00030227573,0.0010667489,0.0008593757,0.000676644,0.00037961316,0.00016795246,0.00002393812],"category_scores_gemma":[0.00001583506,0.0004202179,0.00013352191,0.0018737011,0.00011596483,0.0020177783,0.000018579807,0.00040981063,0.0006254721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047831138,0.00018985932,0.000005021294,0.00012121292,0.000064049455,0.000044087898,0.0013453453,0.9268045,0.00031545924,0.035573073,0.005915033,0.02957452],"study_design_scores_gemma":[0.00014184469,0.00047174806,0.000093459086,0.00025645486,0.00002852812,0.0001751801,0.0007746816,0.9717089,0.0010020429,0.0212409,0.00366301,0.0004432471],"about_ca_topic_score_codex":0.0003989616,"about_ca_topic_score_gemma":0.000035173267,"teacher_disagreement_score":0.966469,"about_ca_system_score_codex":0.0011913341,"about_ca_system_score_gemma":0.00038025097,"threshold_uncertainty_score":0.99982494},"labels":[],"label_agreement":null},{"id":"W4403923053","doi":"10.1145/3686215.3688377","title":"Combining Generative and Discriminative AI for High-Stakes Interview Practice","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Integrity Testing Laboratory (Canada)","funders":"","keywords":"Discriminative model; Generative grammar; Computer science; Artificial intelligence; Natural language processing; Machine learning","score_opus":0.06798635015225182,"score_gpt":0.3544138994326959,"score_spread":0.2864275492804441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403923053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006489983,0.0012121515,0.95919025,0.032651648,0.00056186464,0.00031856945,0.000004055911,0.00022338993,0.005189076],"genre_scores_gemma":[0.82780963,0.0001114227,0.1647803,0.0041824626,0.00010109502,0.00013316529,0.0000040049813,0.000018160323,0.0028597708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876547,0.0001327808,0.00022697581,0.00047727727,0.00014752428,0.0002499547],"domain_scores_gemma":[0.99833685,0.0010844553,0.00004317129,0.0002421326,0.00022123885,0.000072136856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000669536,0.00014366549,0.00015437545,0.000098980614,0.0001689,0.000845116,0.00035114354,0.00003889624,0.000022327564],"category_scores_gemma":[0.00035076812,0.000114192866,0.00004150195,0.0003001239,0.000077368495,0.0023034858,0.0002203343,0.00013566985,0.000053119104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003516778,0.000033189703,0.0000010057354,0.00005336346,0.000030882184,0.000019186806,0.008122724,0.000016332804,0.00048576744,0.89943343,0.0031585468,0.08864205],"study_design_scores_gemma":[0.00015725616,0.0009383491,0.000020372405,0.00028214877,0.000060288257,0.000056279645,0.010570935,0.4604245,0.14521906,0.30684787,0.0748985,0.00052440946],"about_ca_topic_score_codex":0.0001275938,"about_ca_topic_score_gemma":0.00007519045,"teacher_disagreement_score":0.8271606,"about_ca_system_score_codex":0.000048213664,"about_ca_system_score_gemma":0.00006596025,"threshold_uncertainty_score":0.8149473},"labels":[],"label_agreement":null},{"id":"W4403938395","doi":"10.1109/iscc61673.2024.10733560","title":"Democratizing Predictive Analytics with Generative Artificial Intelligence towards AI-Native Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"CODE","keywords":"Predictive analytics; Computer science; Artificial intelligence; Analytics; Generative grammar; Machine learning; Data science","score_opus":0.04074836945255016,"score_gpt":0.2998189124251312,"score_spread":0.25907054297258103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403938395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064840564,0.0003735079,0.9823986,0.00427191,0.0007277416,0.00041927557,0.0000051131365,0.0007478627,0.010407559],"genre_scores_gemma":[0.92919284,0.000058970818,0.06837425,0.0009576758,0.00045580076,0.00006877871,0.000005902361,0.000035990786,0.00084979896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686056,0.00016264609,0.0005676523,0.0010593582,0.0006323936,0.0007174141],"domain_scores_gemma":[0.99817145,0.00034711976,0.00008888161,0.0006269936,0.0005373157,0.00022822146],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00063355814,0.00039370905,0.00032855428,0.00032827444,0.00036307736,0.001339489,0.0010270907,0.00014423879,0.00011216812],"category_scores_gemma":[0.00011035919,0.00030129147,0.00011644313,0.0024355666,0.00027739964,0.0018942124,0.00035376917,0.0006106002,0.00016897479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026952623,0.000058839458,0.00002263245,0.000012943251,0.00013708568,0.0003485517,0.003609511,0.1629141,0.00012454757,0.7147149,0.0007391527,0.11729077],"study_design_scores_gemma":[0.000013200225,0.00041266557,0.000019738867,0.00008087655,0.000027323924,0.00003191221,0.0011178826,0.86336154,0.051465422,0.082746476,0.00036374846,0.00035922],"about_ca_topic_score_codex":0.00013508431,"about_ca_topic_score_gemma":0.00036938296,"teacher_disagreement_score":0.9285444,"about_ca_system_score_codex":0.00027568723,"about_ca_system_score_gemma":0.00049603486,"threshold_uncertainty_score":0.9999439},"labels":[],"label_agreement":null},{"id":"W4404044133","doi":"10.1007/s13347-024-00819-8","title":"The Epistemic Role of AI Decision Support Systems: Neither Superiors, Nor Inferiors, Nor Peers","year":2024,"lang":"en","type":"article","venue":"Philosophy & Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Philosophy of technology; Epistemology; Philosophy of science; Philosophy; Psychology","score_opus":0.010697712110308186,"score_gpt":0.2620498178472189,"score_spread":0.25135210573691075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404044133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31595513,0.036763925,0.41729644,0.18058906,0.0098739965,0.003741149,0.00013028452,0.0071433103,0.028506704],"genre_scores_gemma":[0.9977302,0.00015912259,0.0014849463,0.00016505957,0.0001390913,0.00011494159,0.000002458259,0.000039777515,0.00016440247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973909,0.0000719627,0.0007560312,0.000712255,0.000459061,0.0006097445],"domain_scores_gemma":[0.997562,0.00037700188,0.00013096383,0.0015669909,0.000273168,0.00008987433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061492895,0.00029388806,0.00039435946,0.00060577155,0.00027549994,0.00028823,0.0024761783,0.00032242888,0.00002207327],"category_scores_gemma":[0.00022745381,0.00022138144,0.0001655295,0.0016972313,0.0005067794,0.0005506582,0.00068445405,0.00055830856,0.00060888997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015342008,0.0000404758,0.0011082039,0.000055148193,0.0000498223,0.00006256844,0.0003890124,0.000114769486,0.008879264,0.94823724,0.00044676015,0.04060141],"study_design_scores_gemma":[0.000106252985,0.00046003616,0.00006240933,0.00025811186,0.000026503818,0.00020588658,0.0004997851,0.025528328,0.034655366,0.82788455,0.109921634,0.00039110033],"about_ca_topic_score_codex":0.0001823703,"about_ca_topic_score_gemma":0.000057633886,"teacher_disagreement_score":0.6817751,"about_ca_system_score_codex":0.00015570903,"about_ca_system_score_gemma":0.0002752988,"threshold_uncertainty_score":0.90276736},"labels":[],"label_agreement":null},{"id":"W4404172818","doi":"10.1145/3686912","title":"Evaluating What Others Say: The Effect of Accuracy Assessment in Shaping Mental Models of AI Systems","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Psychology; Mental model; Artificial intelligence; Cognitive psychology; Computer science; Machine learning; Cognitive science","score_opus":0.13261406988109317,"score_gpt":0.4322873931486458,"score_spread":0.2996733232675526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404172818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98196435,0.00022067723,0.0119069,0.0020224904,0.0023541276,0.0009985348,0.000001152876,0.00007227122,0.000459519],"genre_scores_gemma":[0.9979181,0.000017142864,0.0017356642,0.00009987785,0.000121246536,0.0000629186,5.7885615e-7,0.000019378038,0.000025059457],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977428,0.0001085204,0.0007667209,0.0004478691,0.0006897271,0.000244402],"domain_scores_gemma":[0.9977987,0.0008414248,0.0005387489,0.00056359073,0.00023054174,0.000027012173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002136004,0.00021789613,0.00033651793,0.00030356017,0.0001328663,0.0006349299,0.0024421283,0.00006325183,0.0000058912387],"category_scores_gemma":[0.00018258023,0.00013812423,0.0001895037,0.00055868435,0.00007665035,0.0034673442,0.00096688716,0.0004779746,0.0000043770756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018728492,0.00030504097,0.0009719468,0.002342351,0.00035819312,0.0000029763332,0.03721262,0.17558321,0.45447418,0.15205008,0.0014453328,0.17506677],"study_design_scores_gemma":[0.00011339872,0.0005712928,0.00012319844,0.0030239732,0.000017528739,0.000010098203,0.00089127215,0.78334713,0.20499915,0.0067705144,0.000030038873,0.00010237841],"about_ca_topic_score_codex":0.00023908539,"about_ca_topic_score_gemma":0.0000055474497,"teacher_disagreement_score":0.60776395,"about_ca_system_score_codex":0.00029826452,"about_ca_system_score_gemma":0.000042597832,"threshold_uncertainty_score":0.6122644},"labels":[],"label_agreement":null},{"id":"W4404200915","doi":"10.1007/978-3-031-71452-8_11","title":"Applications in Bayesian Epistemology and Artificial Intelligence (AI)","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Artificial intelligence; Bayesian probability; Computer science; Bayesian network; Cognitive science; Machine learning; Psychology","score_opus":0.03269016147201561,"score_gpt":0.29062669753058024,"score_spread":0.25793653605856465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404200915","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022065988,0.0005892205,0.6067278,0.0025346358,0.00023320364,0.00041340466,0.0000044374037,0.00018108697,0.38931403],"genre_scores_gemma":[0.067943074,0.0005980836,0.026054315,0.0015977732,0.0005393088,0.00031119687,0.000030936244,0.0001522969,0.902773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975188,0.000021244688,0.00072322343,0.0010918564,0.00023911089,0.00040577273],"domain_scores_gemma":[0.99851865,0.00024828498,0.00010648196,0.00088067027,0.00009874155,0.00014720252],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033873893,0.00037884316,0.00040795107,0.00058603816,0.00010583899,0.00032060387,0.0010110888,0.00039984318,0.00024019867],"category_scores_gemma":[0.00002051864,0.00036775938,0.00009608658,0.00023776868,0.00026610037,0.00027800494,0.00060629804,0.00064697367,0.0014004307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017181217,0.000014500085,0.0000046559658,0.00004494952,0.000011213875,0.00007178198,0.0002340627,0.000022797356,0.000014523061,0.92851806,0.00015089296,0.07091082],"study_design_scores_gemma":[0.000004994425,0.00004848957,0.000001632941,0.00007014662,0.0000098450755,0.000033606775,0.000061982195,0.018630786,0.00074748666,0.90798587,0.072057515,0.00034762672],"about_ca_topic_score_codex":0.00013878992,"about_ca_topic_score_gemma":0.0011716877,"teacher_disagreement_score":0.58067346,"about_ca_system_score_codex":0.00012517355,"about_ca_system_score_gemma":0.00013397708,"threshold_uncertainty_score":0.99987745},"labels":[],"label_agreement":null},{"id":"W4404240381","doi":"10.1145/3696348.3696894","title":"Toward Trustworthy Learning-Enabled Systems with Concept-Based Explanations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Trustworthiness; Computer science; Data science; Computer security","score_opus":0.029004559784751492,"score_gpt":0.25582968335174555,"score_spread":0.22682512356699405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404240381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023247462,0.00055195694,0.970072,0.0022974245,0.0006528498,0.00029574975,0.0000017758862,0.0014332926,0.022370229],"genre_scores_gemma":[0.9853194,0.000006958752,0.0068739145,0.00022105558,0.000100977464,0.00008988831,0.0000081674025,0.000020933348,0.0073587243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982352,0.000114219605,0.00027559343,0.00054324936,0.00041609645,0.00041558943],"domain_scores_gemma":[0.99889517,0.00030896367,0.000047845944,0.00043120864,0.00017704855,0.00013977799],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003442557,0.00018609206,0.00018547676,0.00023585364,0.0002055216,0.0010635608,0.000652349,0.00006688846,0.00016659075],"category_scores_gemma":[0.000053001422,0.0001412406,0.00006107183,0.0011378597,0.00007507077,0.0008343349,0.0000713648,0.00025554153,0.00063167966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008809164,0.00004717162,0.00022733804,0.00007585826,0.000046937963,0.00031866343,0.002024569,0.16947645,0.00018739529,0.8173096,0.0041274056,0.0061497595],"study_design_scores_gemma":[0.00009467498,0.00023170728,0.000021257541,0.00010066122,0.000010752971,0.000031343065,0.0010636094,0.9437015,0.0058497395,0.0006641523,0.04795154,0.00027904514],"about_ca_topic_score_codex":0.00038921626,"about_ca_topic_score_gemma":0.00005593407,"teacher_disagreement_score":0.9829946,"about_ca_system_score_codex":0.00009861592,"about_ca_system_score_gemma":0.00030499755,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W4404244191","doi":"10.1080/07350015.2024.2421279","title":"A Neural Phillips Curve and a Deep Output Gap","year":2024,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Phillips curve; Output gap; Artificial neural network; Artificial intelligence; Computer science; Keynesian economics; Economics; Monetary policy","score_opus":0.038813939499320334,"score_gpt":0.26781719211030364,"score_spread":0.2290032526109833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404244191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079085454,0.0028108764,0.914891,0.001523198,0.0014290862,0.00004692058,0.00001783162,0.000016901828,0.00017870628],"genre_scores_gemma":[0.9676691,0.0013560676,0.030406155,0.00014684671,0.0003127851,0.0000011211666,8.035554e-7,0.000011701203,0.000095418385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991934,0.000021303387,0.0003834511,0.00016667023,0.000071017326,0.00016416267],"domain_scores_gemma":[0.9993012,0.00023644035,0.00013774284,0.00011022799,0.00011383546,0.000100550395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030399003,0.00010312319,0.00020197147,0.00014657168,0.00007181487,0.00056388916,0.00019328743,0.000032268865,0.00001867775],"category_scores_gemma":[0.000077622135,0.00008861655,0.000023333616,0.000100701705,0.00006909658,0.0006999933,0.00009431526,0.00012211825,0.00001827379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003421325,0.000041696796,0.002460315,0.00024481548,0.00010060429,0.0007965059,0.0024772256,0.0048818993,0.00007972617,0.3843975,0.005187947,0.5992975],"study_design_scores_gemma":[0.00013410795,0.000113513976,0.0074753785,0.00007562039,0.00002730847,0.0009100894,0.00014920945,0.9182234,0.00005058073,0.06425693,0.0083956495,0.00018821334],"about_ca_topic_score_codex":0.00006640518,"about_ca_topic_score_gemma":0.00005254434,"teacher_disagreement_score":0.9133415,"about_ca_system_score_codex":0.000045883546,"about_ca_system_score_gemma":0.000099172335,"threshold_uncertainty_score":0.54375964},"labels":[],"label_agreement":null},{"id":"W4404295096","doi":"10.1109/mmsp61759.2024.10743968","title":"KPCA-CAM: Visual Explainability of Deep Computer Vision Models Using Kernel PCA","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Kernel (algebra); Kernel principal component analysis; Computer vision; Pattern recognition (psychology); Computer graphics (images); Kernel method; Support vector machine; Mathematics","score_opus":0.0422627731121628,"score_gpt":0.33080447690206,"score_spread":0.2885417037898972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404295096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14506936,0.00020923367,0.8517153,0.00027103935,0.00069494586,0.00023059768,9.624114e-7,0.00036003563,0.0014484785],"genre_scores_gemma":[0.8627336,0.00000878506,0.13686344,0.00014135508,0.000109631124,0.0000068146323,0.0000012302588,0.000018597771,0.00011651573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743944,0.00013496216,0.00060503435,0.000810269,0.00051959563,0.00049070606],"domain_scores_gemma":[0.99850523,0.00027352138,0.00007598477,0.0007369195,0.00026000556,0.00014833207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007743026,0.00024222051,0.00030012248,0.00025397533,0.00014621546,0.00039062157,0.0009158905,0.00011963675,0.000091216876],"category_scores_gemma":[0.00002948767,0.00021320565,0.00017277052,0.0009186585,0.00014017048,0.002251603,0.00071217737,0.00019709239,0.000103508326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032632437,0.00046771896,0.00018941148,0.0003135534,0.000057844154,0.000118129465,0.0049915584,0.15669319,0.0119556645,0.5492761,0.0004577225,0.27544644],"study_design_scores_gemma":[0.00004246331,0.00017025738,0.00003969437,0.0000643778,0.000007148186,0.000022018374,0.00014430028,0.9058054,0.024934826,0.06836848,0.0001792998,0.00022174993],"about_ca_topic_score_codex":0.0003789824,"about_ca_topic_score_gemma":0.00004577352,"teacher_disagreement_score":0.7491122,"about_ca_system_score_codex":0.00017178239,"about_ca_system_score_gemma":0.0001400152,"threshold_uncertainty_score":0.86942744},"labels":[],"label_agreement":null},{"id":"W4404360535","doi":"10.1016/j.cobme.2024.100567","title":"Generalizable and explainable deep learning for medical image computing: An overview","year":2024,"lang":"en","type":"review","venue":"Current Opinion in Biomedical Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Image (mathematics); Artificial intelligence; Deep learning; Computer vision; Data science","score_opus":0.12411154117453861,"score_gpt":0.42196453021215125,"score_spread":0.29785298903761265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404360535","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.676753e-7,0.5877515,0.40707836,0.00006122279,0.0044851927,0.00038328627,0.0000030803408,0.00023195049,0.000004929057],"genre_scores_gemma":[0.0000033752556,0.98429644,0.014085865,0.000009829851,0.0011403826,0.00020719506,0.00016556472,0.000075890595,0.000015430582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602526,0.00014869268,0.0011484174,0.0011024661,0.0006953222,0.00087986386],"domain_scores_gemma":[0.9982392,0.00046216612,0.00015547736,0.0004631766,0.00006540424,0.0006145569],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016941117,0.00057626417,0.0012417408,0.0007869146,0.00012617579,0.0004240333,0.0012981982,0.00044406627,0.00002528007],"category_scores_gemma":[0.0007028335,0.00050623575,0.00025482188,0.0013913737,0.00010456839,0.00048256063,0.0008857808,0.0011856504,0.000049488055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.314943e-7,0.000077399876,3.1526477e-7,0.04666452,0.000024263802,0.000015746908,0.00020022478,0.00023364728,5.7245984e-7,0.02856704,0.00063681765,0.9235788],"study_design_scores_gemma":[0.00006089079,0.00005533017,1.4509828e-7,0.014587531,0.000019876547,0.00003899667,0.000009924729,0.43580008,5.0974e-7,0.00018526404,0.5489425,0.0002989362],"about_ca_topic_score_codex":0.00001561628,"about_ca_topic_score_gemma":9.450429e-7,"teacher_disagreement_score":0.9232799,"about_ca_system_score_codex":0.00022693555,"about_ca_system_score_gemma":0.00030024478,"threshold_uncertainty_score":0.99973893},"labels":[],"label_agreement":null},{"id":"W4404367352","doi":"10.1016/j.inffus.2024.102782","title":"XEdgeAI: A human-centered industrial inspection framework with data-centric Explainable Edge AI approach","year":2024,"lang":"en","type":"article","venue":"Information Fusion","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer vision","score_opus":0.08097701053706871,"score_gpt":0.30391192053378213,"score_spread":0.22293490999671342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404367352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010513533,0.00010637876,0.9733906,0.00078624487,0.0013689346,0.00064741046,0.000015713955,0.0011405901,0.012030639],"genre_scores_gemma":[0.98476666,0.00003822494,0.013416384,0.00058278313,0.0004902778,0.00006925584,0.0004099353,0.000019422529,0.00020705379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977991,0.00007842071,0.0005902854,0.0004510169,0.0006401329,0.00044102242],"domain_scores_gemma":[0.99824786,0.00008513871,0.0001619888,0.0011559351,0.00021674109,0.00013232841],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006896611,0.00023391284,0.00018815737,0.00060434476,0.00057416124,0.0016557227,0.0013061942,0.00022841578,0.00006409275],"category_scores_gemma":[0.00014723504,0.00019698666,0.000046595673,0.0020596045,0.000062027095,0.011545803,0.0006958031,0.00059961743,0.0007582927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001578444,0.00040410936,0.00046446867,0.00035683077,0.000084180814,0.00005387367,0.017591672,0.0042504775,0.00033180122,0.63189065,0.0857474,0.2586667],"study_design_scores_gemma":[0.00051759207,0.00031974728,0.00009691208,0.0003729221,0.000024628149,0.00008409745,0.0016077289,0.7636421,0.0030047894,0.005914283,0.22387163,0.00054361875],"about_ca_topic_score_codex":0.00015570161,"about_ca_topic_score_gemma":0.000010089984,"teacher_disagreement_score":0.9742531,"about_ca_system_score_codex":0.00024543487,"about_ca_system_score_gemma":0.00022102379,"threshold_uncertainty_score":0.99938065},"labels":[],"label_agreement":null},{"id":"W4404422782","doi":"10.6339/24-jds1134","title":"Rethinking Attention Weights as Bidirectional Coefficients","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Ministry of Education, India; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Statistics; Mathematics; Psychology","score_opus":0.08340618000620546,"score_gpt":0.3567068886842551,"score_spread":0.2733007086780496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404422782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12792991,0.0007594249,0.8607247,0.0025709933,0.0055993367,0.00008168304,0.00000728474,0.000099328034,0.0022273632],"genre_scores_gemma":[0.9493563,0.00009945274,0.049759574,0.00017449998,0.00032680534,5.693646e-7,0.0000021343428,0.0000065037884,0.0002741364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716824,0.00005583456,0.0004644907,0.0004930762,0.0014989631,0.0003194142],"domain_scores_gemma":[0.99823797,0.0001784307,0.00019302119,0.0007664149,0.00045718695,0.00016695034],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0043440755,0.00010012609,0.00012458413,0.00062281085,0.0003994261,0.001324823,0.0045846174,0.000035917918,0.000036463953],"category_scores_gemma":[0.0005199928,0.000078703204,0.00005763208,0.002487366,0.00037214858,0.0112764295,0.0009043847,0.00030987608,0.0002833696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001984576,0.00025900998,0.0006059245,0.000051468633,0.000048951122,0.0008319016,0.0033119605,0.0005635715,0.11229081,0.6261635,0.0069128657,0.24894018],"study_design_scores_gemma":[0.00015906074,0.00048048422,0.0018496297,0.00087811303,0.000036015852,0.0030122767,0.00028790385,0.6947091,0.05573184,0.15319404,0.08916653,0.00049498375],"about_ca_topic_score_codex":0.00002296984,"about_ca_topic_score_gemma":0.0000049293267,"teacher_disagreement_score":0.8214264,"about_ca_system_score_codex":0.00015939973,"about_ca_system_score_gemma":0.0009407223,"threshold_uncertainty_score":0.9997119},"labels":[],"label_agreement":null},{"id":"W4404444986","doi":"10.1609/aiide.v20i1.31885","title":"Evaluating the Effects of AI Directors for Quest Selection","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Canadian Institute for Advanced Research","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Psychology","score_opus":0.05483724577607038,"score_gpt":0.3546303239359725,"score_spread":0.2997930781599021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404444986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8216894,0.00025277416,0.15901864,0.0069831978,0.0024961391,0.0030185443,0.000026196054,0.00019478599,0.0063202805],"genre_scores_gemma":[0.99885494,0.000036577603,0.00032896127,0.00018796496,0.00006973603,0.00016174818,9.578669e-7,0.000016420132,0.0003426719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980618,0.000027507382,0.000592215,0.0005434809,0.0004513182,0.00032369533],"domain_scores_gemma":[0.9979784,0.0008943543,0.0002671986,0.00019292366,0.0006032702,0.00006386317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047143316,0.00025885666,0.0002633255,0.00015595362,0.0002024988,0.0008321531,0.0008950077,0.000060636008,0.000010743116],"category_scores_gemma":[0.0010887436,0.00016115094,0.00020022376,0.00047345765,0.00026214033,0.0012483236,0.00031379279,0.00029361248,0.000013135458],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015237437,0.00019424252,0.00012382882,0.00027206424,0.000085625106,3.9345764e-7,0.0039033678,0.00004755,0.08508871,0.605147,0.000104273524,0.30488056],"study_design_scores_gemma":[0.000020470834,0.001477653,0.000045667122,0.00088504446,0.000025294043,0.0000048030206,0.0009618982,0.1867799,0.73686445,0.07254388,0.00023931028,0.00015164271],"about_ca_topic_score_codex":0.0000442709,"about_ca_topic_score_gemma":0.0000072797347,"teacher_disagreement_score":0.6517757,"about_ca_system_score_codex":0.00011258882,"about_ca_system_score_gemma":0.00009265396,"threshold_uncertainty_score":0.80244714},"labels":[],"label_agreement":null},{"id":"W4404511583","doi":"10.1155/atr/7450495","title":"Evaluating Transit‐Oriented Development Performance: An Integrated Approach Using Multisource Big Data and Interpretable Machine Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai Jiao Tong University","keywords":"Computer science; Development (topology); Big data; Transit (satellite); Machine learning; Artificial intelligence; Data mining; Data science; Transport engineering; Engineering; Public transport; Mathematics","score_opus":0.09378594199378922,"score_gpt":0.3435304504647875,"score_spread":0.24974450847099827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404511583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47013018,0.00050992717,0.5289399,0.000016306905,0.00027295842,0.00007964372,0.0000025984436,0.000042208554,0.000006285925],"genre_scores_gemma":[0.65794283,0.0000780654,0.34183896,0.000011535264,0.000045677447,0.0000018148772,0.0000528037,0.000014202802,0.000014133935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980539,0.000116616306,0.0007508204,0.0003982599,0.00043951932,0.00024088855],"domain_scores_gemma":[0.9990252,0.000081797334,0.00024963726,0.00024817724,0.00027954977,0.00011559217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014916109,0.00018017789,0.00023662536,0.00029880123,0.00021368136,0.00018604544,0.0005089919,0.00005482954,0.000003934592],"category_scores_gemma":[0.000063189174,0.00015715406,0.000036355137,0.00064379274,0.0000370485,0.0034671645,0.000020703814,0.00047059747,0.0000011593856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065436325,0.000050479317,0.0004967479,0.000107966254,0.00003597822,0.000027069484,0.017885098,0.42957863,0.019032883,0.000087276174,4.3507129e-7,0.532632],"study_design_scores_gemma":[0.00023989865,0.00026872903,0.0012349309,0.00038488253,0.00004147255,0.00008027304,0.0021552162,0.9851993,0.0087747285,0.000042229807,0.0013991487,0.00017923195],"about_ca_topic_score_codex":0.000027929978,"about_ca_topic_score_gemma":0.000049053655,"teacher_disagreement_score":0.5556206,"about_ca_system_score_codex":0.00009481644,"about_ca_system_score_gemma":0.00024568813,"threshold_uncertainty_score":0.64085567},"labels":[],"label_agreement":null},{"id":"W4404720546","doi":"10.3390/info15120751","title":"Exploring the Impact of Image-Based Audio Representations in Classification Tasks Using Vision Transformers and Explainable AI Techniques","year":2024,"lang":"en","type":"article","venue":"Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transformer; Computer science; Artificial intelligence; Computer vision; Audio visual; Speech recognition; Multimedia; Engineering; Electrical engineering","score_opus":0.08433699312779384,"score_gpt":0.3697730099991448,"score_spread":0.28543601687135095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404720546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22152156,0.000026669735,0.7763247,0.00075470743,0.0000702072,0.00032826926,0.0000030379636,0.00011004098,0.0008608537],"genre_scores_gemma":[0.99046314,0.000043090964,0.009355333,0.000037487684,0.000012119826,0.000072507,0.000008605193,0.000004623192,0.00000312086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904335,0.00005335563,0.00041239295,0.00012700215,0.00019576121,0.0001681272],"domain_scores_gemma":[0.99940264,0.0001226515,0.00008245283,0.00023360943,0.00012844229,0.000030194205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006462006,0.00009295696,0.00008926898,0.00045140064,0.00012782247,0.00039045422,0.00020526363,0.000034271376,0.0000042617635],"category_scores_gemma":[0.000064304106,0.00007013737,0.000054901386,0.000936288,0.00006481686,0.010536517,0.000032907694,0.00013271616,0.000008929727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051415725,0.000071204595,0.00078544836,0.0003263267,0.00002674732,0.000006357402,0.032667134,0.03491288,0.102978736,0.039527345,0.00040588726,0.7882405],"study_design_scores_gemma":[0.000044561606,0.00007088943,0.0034778344,0.000119692384,0.0000036595834,0.000005116779,0.0012032752,0.89659315,0.09650873,0.0016823971,0.00020713404,0.0000835567],"about_ca_topic_score_codex":0.0011105402,"about_ca_topic_score_gemma":0.000020785074,"teacher_disagreement_score":0.86168027,"about_ca_system_score_codex":0.0001856483,"about_ca_system_score_gemma":0.00014293946,"threshold_uncertainty_score":0.7638721},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06259688310049519,"score_gpt":0.352237612523537,"score_spread":0.28964072942304186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404817209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020118007,0.9733206,0.017983526,0.00703695,0.00086514093,0.000730243,0.0000080995005,0.000022639135,0.000030788124],"genre_scores_gemma":[0.00009075991,0.99206406,0.007300196,0.0004196657,0.00005190849,0.000047043162,0.0000025741133,0.000016764556,0.000007011339],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997866,0.00028586524,0.0007296129,0.000706594,0.00014907845,0.00026284895],"domain_scores_gemma":[0.99897057,0.00022289471,0.00017946912,0.000444396,0.00008660032,0.00009609186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045344266,0.00032150096,0.0014478823,0.00033521297,0.000051292634,0.0000759192,0.0002862608,0.00019651184,3.4505268e-7],"category_scores_gemma":[0.00007811799,0.00026602214,0.00009896583,0.00045531956,0.000108695036,0.00030097135,0.0003294058,0.0007851187,6.7235004e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017325616,0.00003040606,0.0000033000315,0.054372262,0.000024343597,0.000010368917,0.0009707727,0.000047677786,3.961911e-8,0.01877128,0.00014787777,0.92561996],"study_design_scores_gemma":[0.00012117726,0.00033402303,0.000019922207,0.20859201,0.00030446108,0.000061339844,0.0006374249,0.056801602,0.0000035382968,0.09047274,0.641708,0.00094374386],"about_ca_topic_score_codex":0.00008392977,"about_ca_topic_score_gemma":0.00016354592,"teacher_disagreement_score":0.9246762,"about_ca_system_score_codex":0.00010444606,"about_ca_system_score_gemma":0.00014717173,"threshold_uncertainty_score":0.9999792},"labels":[],"label_agreement":null},{"id":"W4404878954","doi":"10.1016/j.nbsj.2024.100198","title":"Leveraging AI for enhanced alignment of national biodiversity targets with the global biodiversity goals","year":2024,"lang":"en","type":"article","venue":"Nature-Based Solutions","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Biodiversity; Environmental resource management; Computer science; Environmental science; Biology; Ecology","score_opus":0.02741503141704083,"score_gpt":0.283002027810236,"score_spread":0.25558699639319515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404878954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009012589,0.00072340464,0.9595364,0.028493848,0.0005821278,0.000438561,0.0005681891,0.00017538459,0.00046951862],"genre_scores_gemma":[0.9909314,0.000004636331,0.0067622536,0.0021790538,0.000032490847,0.000022388358,0.000038961574,0.0000019458564,0.000026852167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984706,0.00006384632,0.00015095017,0.00040774493,0.00055811537,0.00034871977],"domain_scores_gemma":[0.99882084,0.0002415861,0.00006813666,0.0002870071,0.00051147403,0.00007094543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053145504,0.00014286753,0.00012692666,0.00011799612,0.00070163957,0.00014333989,0.00071908813,0.00016244495,0.000017508515],"category_scores_gemma":[0.000073191,0.00010999885,0.00014018624,0.0008744277,0.00018822488,0.00039179664,0.00015285063,0.00032219398,0.00005998793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023059692,0.0006771928,0.0023830335,0.00024788748,0.0005196761,0.00003766338,0.0032963126,0.0427757,0.0102261435,0.6373258,0.2993441,0.0029358908],"study_design_scores_gemma":[0.0014680594,0.00080307445,0.0034418746,0.00026672686,0.00022640981,0.000016026283,0.0013475608,0.1850819,0.6398051,0.052482285,0.1136986,0.0013623995],"about_ca_topic_score_codex":0.00011151631,"about_ca_topic_score_gemma":0.000102197286,"teacher_disagreement_score":0.9819188,"about_ca_system_score_codex":0.00044843057,"about_ca_system_score_gemma":0.0005296092,"threshold_uncertainty_score":0.5396515},"labels":[],"label_agreement":null},{"id":"W4405166943","doi":"10.1016/j.engappai.2024.109678","title":"Quantifying the trustworthiness of explainable artificial intelligence outputs in uncertain decision-making scenarios","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Trustworthiness; Artificial intelligence; Machine learning; Computer security","score_opus":0.048322767260544054,"score_gpt":0.3265637760144577,"score_spread":0.2782410087539136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405166943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013980981,0.0016277649,0.98178357,0.00062017643,0.00065974984,0.00089916616,0.000009811882,0.00029325756,0.00012552906],"genre_scores_gemma":[0.9190083,0.000107867956,0.0803203,0.000025655161,0.00014561528,0.00033204534,0.0000030296362,0.000043533753,0.000013659951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956081,0.000087446264,0.0019355329,0.00092711893,0.00071819586,0.0007236179],"domain_scores_gemma":[0.9950383,0.0026638608,0.00028089844,0.0015130584,0.00039266655,0.00011127103],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020929063,0.0004112502,0.00051262125,0.0009918306,0.00023946488,0.00035649101,0.0026933053,0.00018787754,0.000046967732],"category_scores_gemma":[0.00088180293,0.00036856954,0.0002289636,0.0054098023,0.00027911604,0.00082017714,0.00046533364,0.0006326567,0.00013398453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011709689,0.00009011629,0.000021255853,0.00012542485,0.000014749232,0.000011888131,0.001652065,0.2786761,0.0022741111,0.45522973,0.000006562937,0.2618863],"study_design_scores_gemma":[0.0000051091074,0.000052942527,0.000028053639,0.00071797817,0.000013326988,0.00001357951,0.0014484396,0.7806717,0.102647185,0.11359441,0.0004832771,0.00032396486],"about_ca_topic_score_codex":0.00035287565,"about_ca_topic_score_gemma":0.00025366485,"teacher_disagreement_score":0.90502733,"about_ca_system_score_codex":0.00018474033,"about_ca_system_score_gemma":0.00027432162,"threshold_uncertainty_score":0.9998766},"labels":[],"label_agreement":null},{"id":"W4405220551","doi":"10.1016/j.ijhcs.2024.103434","title":"Human performance effects of combining counterfactual explanations with normative and contrastive explanations in supervised machine learning for automated decision assistance","year":2024,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Counterfactual thinking; Normative; Artificial intelligence; Machine learning; Computer science; Psychology; Cognitive psychology; Social psychology; Epistemology; Philosophy","score_opus":0.027921147982588577,"score_gpt":0.33543673881891234,"score_spread":0.30751559083632374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405220551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59921205,0.0011416746,0.39848134,0.00025026972,0.00061956554,0.00018927631,0.000006080384,0.00006335517,0.000036402336],"genre_scores_gemma":[0.9868635,0.00014410453,0.012795025,0.000046591183,0.0000923659,0.00002347333,0.0000051057586,0.00001185651,0.00001798369],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982817,0.00007942419,0.0007056898,0.00024114632,0.0005047196,0.00018729102],"domain_scores_gemma":[0.9969573,0.0014589229,0.0003393488,0.00009380976,0.001106269,0.00004432197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052358105,0.00018623512,0.00037548997,0.00068737025,0.00022509242,0.00022702063,0.000546165,0.00003669417,0.0000021006754],"category_scores_gemma":[0.00012749904,0.00014961883,0.0000656671,0.00026100455,0.0001291797,0.0013394192,0.00015558736,0.00025461573,0.000001281583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010710718,0.0018859006,0.038963724,0.0021490708,0.0087684635,0.0019153464,0.33372226,0.22575453,0.018350206,0.21630788,0.004226122,0.14688541],"study_design_scores_gemma":[0.0018067175,0.001996056,0.016409691,0.0034319712,0.000048938964,0.00013162584,0.0017037905,0.96214145,0.009088312,0.002786939,0.00015252073,0.00030200407],"about_ca_topic_score_codex":0.000017091756,"about_ca_topic_score_gemma":0.000118981065,"teacher_disagreement_score":0.7363869,"about_ca_system_score_codex":0.00017643892,"about_ca_system_score_gemma":0.00006311522,"threshold_uncertainty_score":0.6101279},"labels":[],"label_agreement":null},{"id":"W4405364999","doi":"10.2139/ssrn.5026257","title":"The heterogeneous impact of the EU-Canada agreement with causal machine learning&amp;nbsp;","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agreement; Chemistry; Psychology; Philosophy; Linguistics","score_opus":0.012033959195383378,"score_gpt":0.2570956432238825,"score_spread":0.24506168402849912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405364999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8341746,0.044727854,0.09687509,0.016609196,0.0042782244,0.0014514243,0.0000352061,0.00016551674,0.001682917],"genre_scores_gemma":[0.9943579,0.0022075763,0.00013574568,0.00007764645,0.00022397532,0.000015267045,0.0000024408118,0.00003937429,0.0029401165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948726,0.00040617186,0.00061958574,0.00051760924,0.0011121825,0.0024718137],"domain_scores_gemma":[0.9976342,0.00017237608,0.00064034376,0.0011321313,0.00028389698,0.00013705225],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021945909,0.00043258897,0.0003559111,0.000097884906,0.0006977194,0.0005126232,0.0033503692,0.00011737619,0.000021215856],"category_scores_gemma":[0.00010883779,0.00021421234,0.00039550063,0.00043648478,0.00013368398,0.00008532392,0.0018296017,0.0070704226,0.000024002993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0003028243,0.00023157698,0.003456124,0.00014096848,0.0057565584,0.00022688392,0.0027691987,0.639968,0.0008629864,0.25453812,0.0021281852,0.08961862],"study_design_scores_gemma":[0.00051034614,0.0030179555,0.00059016095,0.000776462,0.00041576667,0.0067887106,0.0010853182,0.112141274,0.006450279,0.8415756,0.02482168,0.0018264436],"about_ca_topic_score_codex":0.16046944,"about_ca_topic_score_gemma":0.83753896,"teacher_disagreement_score":0.6770695,"about_ca_system_score_codex":0.004086945,"about_ca_system_score_gemma":0.023168806,"threshold_uncertainty_score":0.9997362},"labels":[],"label_agreement":null},{"id":"W4405466521","doi":"10.1088/2632-2153/ada087","title":"Automation of quantum dot measurement analysis via explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Army Research Office; National Science Foundation","keywords":"Automation; Quantum dot; Computer science; Artificial intelligence; Engineering; Physics; Optoelectronics; Mechanical engineering","score_opus":0.017960715525358908,"score_gpt":0.2645482183081211,"score_spread":0.24658750278276217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405466521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12905842,0.0030039868,0.8610709,0.0043224255,0.00023809298,0.00020114247,9.408393e-7,0.0013037123,0.00080038584],"genre_scores_gemma":[0.9943298,0.00008913631,0.005288502,0.000030008037,0.00001385427,0.000020705851,0.0000022942684,0.000010895843,0.0002148185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704397,0.00011320385,0.0004390307,0.0008416971,0.0009845766,0.0005775488],"domain_scores_gemma":[0.9985766,0.00010478872,0.00017137559,0.00049157895,0.00056233275,0.00009332599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038886976,0.00021021954,0.0003439844,0.0029331017,0.00073102466,0.0003411917,0.0011266759,0.00012077808,0.000037643185],"category_scores_gemma":[0.0011795436,0.0001867789,0.000073576004,0.011307944,0.00063582085,0.00096374954,0.00058203493,0.000657893,0.000057451096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009096802,0.00011048529,0.030352283,0.00014996582,0.00020232669,0.000090267495,0.0022853478,0.02521483,0.18679567,0.45116568,0.000030014888,0.30359405],"study_design_scores_gemma":[0.000051642608,0.00028528995,0.00046513023,0.000039181912,0.00005181236,0.00002975982,0.00020920785,0.9462202,0.039640833,0.009339092,0.003474888,0.00019295678],"about_ca_topic_score_codex":0.000628422,"about_ca_topic_score_gemma":0.00008712302,"teacher_disagreement_score":0.92100537,"about_ca_system_score_codex":0.00017810846,"about_ca_system_score_gemma":0.00018707008,"threshold_uncertainty_score":0.7616622},"labels":[],"label_agreement":null},{"id":"W4405559952","doi":"10.1111/coin.70015","title":"Mining User Study Data to Judge the Merit of a Model for Supporting User‐Specific Explanations of <scp>AI</scp> Systems","year":2024,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Value (mathematics); Computer science; Focus (optics); User modeling; Artificial intelligence; Order (exchange); Machine learning; User interface","score_opus":0.20998704697061374,"score_gpt":0.3958272314168007,"score_spread":0.18584018444618697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405559952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025906693,0.00047506375,0.9707506,0.00056014356,0.00069447816,0.0012453581,0.000136005,0.00011133196,0.00012037757],"genre_scores_gemma":[0.9286919,0.000009906202,0.070532836,0.00012103892,0.00009060289,0.00015817973,0.00004545741,0.000025860449,0.0003241806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99671155,0.00012334186,0.001189995,0.00083174795,0.00074223016,0.0004011488],"domain_scores_gemma":[0.9938873,0.0036905138,0.00028545567,0.0011329026,0.0008921082,0.000111735455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017084477,0.00022714563,0.00034280494,0.00036088296,0.00023785696,0.00041558713,0.003028539,0.00005672059,0.0000051756306],"category_scores_gemma":[0.0007796657,0.00019564829,0.000099234574,0.0014903967,0.000116194904,0.0009888402,0.000783939,0.00016829945,0.000043035507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034968857,0.00013092121,0.000109778324,0.00006998507,0.00005838561,0.0000055629994,0.011348652,0.74039984,0.00022227255,0.23765662,0.0048916154,0.0051028673],"study_design_scores_gemma":[0.000028532351,0.00015376126,0.00006016812,0.00013091408,0.000021488573,0.000009630559,0.007663341,0.97684705,0.0033011085,0.009369201,0.0023151243,0.000099673925],"about_ca_topic_score_codex":0.000085308435,"about_ca_topic_score_gemma":0.000046006473,"teacher_disagreement_score":0.90278524,"about_ca_system_score_codex":0.00006549791,"about_ca_system_score_gemma":0.00035510992,"threshold_uncertainty_score":0.7978306},"labels":[],"label_agreement":null},{"id":"W4405698514","doi":"10.3390/ecsa-11-20472","title":"Enhancing Explainability in Convolutional Neural Networks Using Entropy-Based Class Activation Maps","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Class (philosophy); Entropy (arrow of time); Pattern recognition (psychology); Physics","score_opus":0.03219587176743669,"score_gpt":0.2862221775485913,"score_spread":0.2540263057811546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405698514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17227806,0.000065919565,0.82512414,0.0012277628,0.0006046303,0.00021141821,6.797357e-7,0.0002560697,0.00023131905],"genre_scores_gemma":[0.9839159,0.000001140658,0.0154366195,0.00041088715,0.00013833685,0.000023444745,0.0000062425343,0.000011192227,0.000056200817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998055,0.00016438845,0.00041257002,0.000578916,0.0003048059,0.00048432656],"domain_scores_gemma":[0.9989369,0.00044819573,0.000048928756,0.00037270781,0.00011011989,0.00008313937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070539187,0.0001673203,0.00015273891,0.00024240863,0.00014335432,0.00035654253,0.00042072724,0.00009802468,0.000071097034],"category_scores_gemma":[0.00012941172,0.0001638526,0.000078546465,0.001046161,0.0000695881,0.0013476904,0.00013589372,0.00029280427,0.000028378172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024676301,0.00010230081,0.0019764616,0.000064427106,0.0000093428425,0.00006037977,0.00048260274,0.62020457,0.02532239,0.34420308,0.00017646489,0.0073732967],"study_design_scores_gemma":[0.00005912072,0.000030279527,0.00037041353,0.000055987348,0.0000020073712,0.0000045626466,0.00011726151,0.94118094,0.050791092,0.006891962,0.00032662367,0.00016976053],"about_ca_topic_score_codex":0.00045263325,"about_ca_topic_score_gemma":0.00022789126,"teacher_disagreement_score":0.8116379,"about_ca_system_score_codex":0.00060841965,"about_ca_system_score_gemma":0.00024391021,"threshold_uncertainty_score":0.66817147},"labels":[],"label_agreement":null},{"id":"W4405788224","doi":"10.1109/iros58592.2024.10801529","title":"Explainable Artificial intelligence for Autonomous UAV Navigation","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision","score_opus":0.053197369344216164,"score_gpt":0.31937157796463617,"score_spread":0.26617420862042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405788224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019997868,0.00030503265,0.9853024,0.0028664807,0.0016152146,0.00056195614,0.00000422559,0.0011745668,0.006170348],"genre_scores_gemma":[0.8763344,0.000015325424,0.118986174,0.00027219878,0.00037423638,0.0002879232,0.000013965828,0.00003306551,0.0036826872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778694,0.000041433486,0.0005242244,0.00076541625,0.00028140482,0.0006005575],"domain_scores_gemma":[0.998587,0.0004328213,0.000049972925,0.0005989042,0.00019573062,0.00013554915],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000805535,0.00021640549,0.00017936915,0.0002266293,0.00029671748,0.0011475671,0.00097298925,0.00010897601,0.00011895948],"category_scores_gemma":[0.00012429326,0.00020378374,0.00014594938,0.00093102356,0.000073038645,0.0016515099,0.00018886055,0.00016879669,0.0012537352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049579658,0.00003658444,0.0000012979374,0.00006379227,0.000010209419,0.000028465123,0.0008830157,0.001325786,0.0017639162,0.80127287,0.0009868107,0.19362232],"study_design_scores_gemma":[0.000006954694,0.00010962414,0.000001108133,0.000047545465,0.0000047168555,0.000016351789,0.00032082258,0.5244254,0.15571727,0.30069357,0.018463232,0.00019338357],"about_ca_topic_score_codex":0.00011468287,"about_ca_topic_score_gemma":0.000033925113,"teacher_disagreement_score":0.87433463,"about_ca_system_score_codex":0.0001785001,"about_ca_system_score_gemma":0.0002280027,"threshold_uncertainty_score":0.9998893},"labels":[],"label_agreement":null},{"id":"W4406075475","doi":"10.2196/65923","title":"An Explainable AI Application (AF’fective) to Support Monitoring of Patients With Atrial Fibrillation After Catheter Ablation: Qualitative Focus Group, Design Session, and Interview Study","year":2025,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Atrial fibrillation; Preprint; Catheter ablation; Medicine; Cardiology; Cobra; Internal medicine; Ablation; Computer science; World Wide Web","score_opus":0.04361466294787439,"score_gpt":0.36821530696169635,"score_spread":0.32460064401382194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406075475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64941126,0.000012668475,0.34896088,0.000026199303,0.00007561825,0.0014418699,0.000002844343,0.00005140985,0.000017224747],"genre_scores_gemma":[0.99753225,7.632509e-7,0.0021712526,0.000017982029,0.00005285403,0.00016644843,0.000010112879,0.0000146204675,0.00003373571],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99784267,0.00049991213,0.00045558467,0.0005878501,0.0003677241,0.00024624565],"domain_scores_gemma":[0.99857986,0.00016445122,0.00019812226,0.00053425605,0.00042063344,0.00010264843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006638942,0.00022200478,0.0002752594,0.00033950078,0.00024299814,0.00018325957,0.00034771863,0.00006681447,0.000013558333],"category_scores_gemma":[0.000033906224,0.00018676341,0.0000538064,0.00064887165,0.00004659874,0.0013998413,0.00016157933,0.00010292775,0.0000056370686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020606656,0.00043029754,0.8523449,0.000068091416,0.000070184185,0.000001917492,0.12148695,0.0008414445,0.00043390255,0.001778546,0.000030339012,0.022307418],"study_design_scores_gemma":[0.00072241115,0.005202779,0.96760017,0.00015275819,0.000040707968,1.9972049e-7,0.010776138,0.0007938114,0.009892355,0.004180817,0.00018555185,0.000452322],"about_ca_topic_score_codex":0.00019457367,"about_ca_topic_score_gemma":0.00007688841,"teacher_disagreement_score":0.34812093,"about_ca_system_score_codex":0.00015741569,"about_ca_system_score_gemma":0.00004278321,"threshold_uncertainty_score":0.7615991},"labels":[],"label_agreement":null},{"id":"W4406156224","doi":"10.22329/il.v44i4.8461","title":"What are Deep Disagreements?","year":2025,"lang":"en","type":"article","venue":"Informal Logic","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Psychology","score_opus":0.024826827953520782,"score_gpt":0.2865627252349799,"score_spread":0.26173589728145913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406156224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019690128,0.0006914355,0.85782707,0.0044077947,0.0031998877,0.00035379716,9.3801583e-7,0.0004233071,0.11340564],"genre_scores_gemma":[0.9805902,0.0001387941,0.006179585,0.008414858,0.000055986882,0.0000387279,0.0000029912587,0.0000043947302,0.0045744283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988373,0.000021314852,0.00029865492,0.00022208177,0.00021753681,0.00040311887],"domain_scores_gemma":[0.9991187,0.00006674003,0.000091730166,0.0005521972,0.00010242713,0.00006820045],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022866814,0.0001315945,0.00013224437,0.0001406338,0.00019140237,0.0006681048,0.0011505974,0.000067746216,0.00007618763],"category_scores_gemma":[0.000083463754,0.00011328753,0.000053064286,0.000600353,0.000060197977,0.003913255,0.00054141344,0.00013123888,0.0009882649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009524047,0.00005898034,0.0024124163,0.000029043234,0.000019665531,0.000034922738,0.0010546839,0.0012631556,0.00008437161,0.8095558,0.001315792,0.18416162],"study_design_scores_gemma":[0.0007123029,0.00060651137,0.030378561,0.00048107462,0.00003117741,0.000037041835,0.0115975365,0.2633058,0.04771084,0.3308612,0.31273067,0.0015472638],"about_ca_topic_score_codex":0.00002446726,"about_ca_topic_score_gemma":0.00008049284,"teacher_disagreement_score":0.9609001,"about_ca_system_score_codex":0.00004981008,"about_ca_system_score_gemma":0.000047287973,"threshold_uncertainty_score":0.9997896},"labels":[],"label_agreement":null},{"id":"W4406229301","doi":"10.1371/journal.pcbi.1012711","title":"Eight quick tips for biologically and medically informed machine learning","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministero dell'Università e della Ricerca; European Commission; Dipartimenti di Eccellenza","keywords":"Machine learning; Computer science; Artificial intelligence; Domain (mathematical analysis); Informatics; Health informatics; Data science; Health care; Engineering","score_opus":0.030533655701941824,"score_gpt":0.30406151400940656,"score_spread":0.27352785830746473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406229301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023946512,0.00038659788,0.96727264,0.00636828,0.0002024637,0.00031263143,0.000011004923,0.00016263222,0.0013372363],"genre_scores_gemma":[0.83560896,0.000080728256,0.16043788,0.0033004228,0.000066676555,0.0000906921,0.00015530497,0.000006434874,0.0002529117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987334,0.00010924755,0.00035843687,0.00039476517,0.00010102371,0.00030313552],"domain_scores_gemma":[0.9973064,0.0021521933,0.00009852983,0.00013106978,0.0002327163,0.00007908288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031249272,0.00013814449,0.00021895615,0.00017737012,0.00025864746,0.00006572868,0.0004947817,0.00013394795,0.000023850964],"category_scores_gemma":[0.0011483587,0.00011193785,0.00004713898,0.00029651288,0.00020121418,0.00014983276,0.0002988656,0.00016938354,0.000034026118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004473449,0.00008574878,0.005796204,0.0000401964,0.000074533455,0.000003183062,0.0002209756,0.0019456766,0.0013226124,0.94418645,0.00069045863,0.045589205],"study_design_scores_gemma":[0.00029685645,0.00039260436,0.0013419917,0.000024398349,0.000007837148,0.000009733496,0.000024358042,0.65520215,0.00095129636,0.315082,0.026494246,0.00017253018],"about_ca_topic_score_codex":0.000016023278,"about_ca_topic_score_gemma":0.000019484643,"teacher_disagreement_score":0.81166244,"about_ca_system_score_codex":0.00003908596,"about_ca_system_score_gemma":0.00020720353,"threshold_uncertainty_score":0.4564693},"labels":[],"label_agreement":null},{"id":"W4406328136","doi":"10.3390/app15020672","title":"C-SHAP: A Hybrid Method for Fast and Efficient Interpretability","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Interpretability; Computer science; Scalability; Cluster analysis; Machine learning; Artificial intelligence; Matching (statistics); Random forest; Medicine","score_opus":0.020130910978303634,"score_gpt":0.324695480043387,"score_spread":0.30456456906508333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406328136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026188578,0.00010904175,0.95646775,0.0015228804,0.00030192468,0.00051287975,0.0000026535554,0.00012156592,0.014772741],"genre_scores_gemma":[0.7823864,0.0000021831238,0.21673338,0.00064012187,0.0000150103115,0.00011487561,2.8185204e-7,0.0000025858262,0.00010515668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818987,0.000050576124,0.00028057603,0.00081918866,0.0002420027,0.0004177861],"domain_scores_gemma":[0.9985856,0.0007713472,0.00007032852,0.00041535636,0.00007877696,0.000078617944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021457626,0.00014409344,0.00019660429,0.00018062643,0.0005447337,0.0004010317,0.0012218165,0.000033456367,0.000007052555],"category_scores_gemma":[0.00018806792,0.00012095654,0.000052255662,0.00084863236,0.0004416202,0.00020055023,0.0004895838,0.00008587201,0.000015142253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009850116,0.000050651593,0.000099533594,0.000024436798,0.000006399331,6.545514e-7,0.00081542035,0.0016185027,0.006179275,0.8006242,0.00024037002,0.19033071],"study_design_scores_gemma":[0.00008955751,0.00006986326,0.00014584896,0.000017661465,0.000006287238,0.0000031467455,0.0006229292,0.7439248,0.12527457,0.12755157,0.0021207633,0.00017300143],"about_ca_topic_score_codex":0.00004702673,"about_ca_topic_score_gemma":0.00002292335,"teacher_disagreement_score":0.7561978,"about_ca_system_score_codex":0.000041619398,"about_ca_system_score_gemma":0.00014898172,"threshold_uncertainty_score":0.49324644},"labels":[],"label_agreement":null},{"id":"W4406567827","doi":"10.1016/b978-0-44-323761-4.00027-4","title":"Interpretable AI for medical image analysis: methods, evaluation, and clinical considerations","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Image (mathematics); Computer science; Pattern recognition (psychology)","score_opus":0.05121775129253286,"score_gpt":0.4308372453972434,"score_spread":0.3796194941047105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406567827","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.260599e-7,0.0008972214,0.48064932,0.0015541743,0.00066991354,0.0008127096,0.000015359195,0.00008164167,0.5153189],"genre_scores_gemma":[0.00023912145,0.00015470576,0.3353469,0.0040273517,0.0002613066,0.00025085558,0.000029803805,0.000032454547,0.6596575],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99598897,0.00043413087,0.001413311,0.0011090388,0.0006982064,0.00035634454],"domain_scores_gemma":[0.99301296,0.003875597,0.00035467255,0.0012008521,0.001276307,0.00027961543],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0072190324,0.0003775312,0.00095832243,0.00050656375,0.00031259266,0.00047288503,0.0007807673,0.0005250551,0.0005821942],"category_scores_gemma":[0.004249552,0.00036368996,0.00056101015,0.00009596819,0.000371622,0.00025506708,0.00058537617,0.0006425675,0.000036034795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044020385,0.000012270511,0.000004767104,0.000025483165,0.0007276888,0.000008169429,0.00015040241,0.0000027516978,0.0000023054683,0.23793042,0.0017729839,0.75935835],"study_design_scores_gemma":[0.00017472838,0.00007647444,0.000005081456,0.00019920674,0.0017039126,0.000009108404,0.000013233146,0.16067408,0.00011549038,0.45213977,0.3845196,0.00036931733],"about_ca_topic_score_codex":0.000003366044,"about_ca_topic_score_gemma":0.00028734774,"teacher_disagreement_score":0.75898904,"about_ca_system_score_codex":0.00009757497,"about_ca_system_score_gemma":0.0014602288,"threshold_uncertainty_score":0.9998815},"labels":[],"label_agreement":null},{"id":"W4406864562","doi":"10.1016/j.csbj.2025.01.007","title":"Interpretability of AI race detection model in medical imaging with saliency methods","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; York University","funders":"Cooperative Research Centres, Australian Government Department of Industry; Canada First Research Excellence Fund; Commonwealth Scientific and Industrial Research Organisation; York University","keywords":"Interpretability; Race (biology); Artificial intelligence; Computer science; Computational biology; Machine learning; Pattern recognition (psychology); Biology","score_opus":0.007811310460108376,"score_gpt":0.3282956322248254,"score_spread":0.32048432176471703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406864562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2468478,0.0002572318,0.7418341,0.010833905,0.000114642,0.000050199425,4.1670077e-7,0.0000321149,0.000029579172],"genre_scores_gemma":[0.83152896,0.000013074004,0.16816354,0.00028058462,0.0000061785067,0.0000017252498,2.7945532e-7,0.0000019587862,0.0000037025131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883425,0.00012462141,0.00039772337,0.00025659992,0.00020304284,0.00018378922],"domain_scores_gemma":[0.9993418,0.00017565537,0.000116815936,0.00013606994,0.00017820699,0.000051454474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005931699,0.00010707746,0.00019529357,0.00039935924,0.00014583407,0.000053677963,0.0004747099,0.0001262432,0.0000060480443],"category_scores_gemma":[0.00022511686,0.000081793194,0.000032590142,0.00057957874,0.00036284898,0.00037386903,0.00020340043,0.00062840106,3.1870553e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004980653,0.00001925668,0.005136704,0.000019011812,0.000020660927,0.000022831988,0.0003925301,0.04225936,0.0037299367,0.15847391,0.000011318157,0.78986466],"study_design_scores_gemma":[0.000111320005,0.000029580204,0.0024832983,0.00003460534,0.0000023875484,0.0002988193,0.00006981363,0.6393378,0.015108124,0.34246385,0.000008117863,0.000052329964],"about_ca_topic_score_codex":0.000021913085,"about_ca_topic_score_gemma":0.000025062074,"teacher_disagreement_score":0.7898123,"about_ca_system_score_codex":0.00006662634,"about_ca_system_score_gemma":0.0002317695,"threshold_uncertainty_score":0.33354297},"labels":[],"label_agreement":null},{"id":"W4406882679","doi":"10.1007/s00423-025-03626-7","title":"Can surgeons trust AI? Perspectives on machine learning in surgery and the importance of eXplainable Artificial Intelligence (XAI)","year":2025,"lang":"en","type":"article","venue":"Langenbeck s Archives of Surgery","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Transparency (behavior); Artificial intelligence; Vascular surgery; Computer science; Machine learning; Medicine; Cardiac surgery; Surgery","score_opus":0.03252844417459558,"score_gpt":0.2682100963248586,"score_spread":0.23568165215026302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406882679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9475716,0.00537008,0.02996045,0.010993522,0.00049908384,0.00060918863,0.000026372518,0.00014764289,0.004822081],"genre_scores_gemma":[0.99752444,0.0013217245,0.0005635782,0.00022605354,0.000029509249,0.000046478246,0.000006186043,0.00001652111,0.00026552932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99698895,0.00052638294,0.0009980333,0.0006108452,0.00032130067,0.0005545125],"domain_scores_gemma":[0.9875639,0.011176074,0.0003804915,0.00070343405,0.00009317444,0.00008293368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018425473,0.00027563694,0.00080515735,0.00093416014,0.0002081372,0.00007894016,0.000629526,0.00007023867,0.00002237836],"category_scores_gemma":[0.0022722124,0.00022244763,0.0002759739,0.0012504796,0.0007943462,0.00027313293,0.0003455776,0.00043157768,0.0000031268742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006134429,0.00033712568,0.35634193,0.0002800921,0.00009487145,0.00008832387,0.013630436,0.0020226361,0.0006200148,0.5702409,0.00016980623,0.055560417],"study_design_scores_gemma":[0.00048420933,0.00022915653,0.15472166,0.0029962559,0.00008622467,0.000041991658,0.037689168,0.20006382,0.12750162,0.47299585,0.0014220048,0.0017680288],"about_ca_topic_score_codex":0.0025066568,"about_ca_topic_score_gemma":0.002722901,"teacher_disagreement_score":0.20162027,"about_ca_system_score_codex":0.00004152922,"about_ca_system_score_gemma":0.00036073354,"threshold_uncertainty_score":0.90711516},"labels":[],"label_agreement":null},{"id":"W4406979160","doi":"10.1016/j.engappai.2025.110132","title":"Insights into the application of explainable artificial intelligence for biological wastewater treatment plants: Updates and perspectives","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus","funders":"","keywords":"Computer science; Artificial intelligence; Wastewater; Machine learning; Environmental science","score_opus":0.03385176025905498,"score_gpt":0.2863440075056756,"score_spread":0.25249224724662067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406979160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04273631,0.0014416177,0.95308447,0.0010730573,0.000102223246,0.0013659132,0.000008504229,0.00011794738,0.00006995099],"genre_scores_gemma":[0.9507027,0.00037933447,0.047405932,0.000018789538,0.00006638971,0.0013785737,0.000010419865,0.000013504394,0.000024299627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978533,0.000047654954,0.00090776815,0.0006730375,0.00018247023,0.0003358051],"domain_scores_gemma":[0.9975142,0.0009176333,0.00022368561,0.0009372163,0.00033354657,0.000073724776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037742208,0.00028416092,0.0003666574,0.0003665795,0.00031970147,0.000103738326,0.0011024195,0.00013351427,0.0000044508943],"category_scores_gemma":[0.0002014581,0.00021914617,0.000120918165,0.0010208852,0.0003770247,0.00027992664,0.00022488041,0.00013361075,0.000014514058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002851621,0.00021319099,0.000010813208,0.000050198087,0.000040594114,2.5960495e-7,0.0043468033,0.013683335,0.04059019,0.77993304,0.000004237308,0.16109882],"study_design_scores_gemma":[0.00000968409,0.00014896062,0.00001622368,0.00003119867,0.000013253485,9.844075e-7,0.0044975663,0.25448608,0.5676356,0.17146082,0.0015490444,0.00015056696],"about_ca_topic_score_codex":0.00025971417,"about_ca_topic_score_gemma":0.000061768325,"teacher_disagreement_score":0.90796643,"about_ca_system_score_codex":0.00011316727,"about_ca_system_score_gemma":0.000088165005,"threshold_uncertainty_score":0.89365214},"labels":[],"label_agreement":null},{"id":"W4407027286","doi":"10.1080/14697688.2024.2436137","title":"Deep Learning: Foundations and Concepts","year":2024,"lang":"en","type":"article","venue":"Quantitative Finance","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Economics; Mathematical economics; Computer science; Artificial intelligence; Econometrics; Financial economics; Epistemology; Cognitive science; Philosophy; Psychology","score_opus":0.04817475332553689,"score_gpt":0.3629296290418366,"score_spread":0.31475487571629973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407027286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033528857,0.0035562294,0.9555713,0.0013889311,0.000414394,0.000115473245,0.0000010577236,0.00025193242,0.0051718284],"genre_scores_gemma":[0.94034,0.00040899665,0.056929074,0.00010010958,0.000028421853,0.00002850914,0.0000019568915,0.000010115998,0.0021528332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999,0.00007432172,0.00016240936,0.00040524008,0.00013261173,0.00022540045],"domain_scores_gemma":[0.9991687,0.00046774035,0.000038233415,0.00018959666,0.00009889254,0.0000368219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002310135,0.00010737597,0.00010845372,0.000092121234,0.00022697277,0.00036221073,0.0002867787,0.000029736952,0.000020935802],"category_scores_gemma":[0.00025466224,0.000105216895,0.00003312634,0.0006009011,0.00017110418,0.0009913746,0.00010751169,0.00017797285,0.0006909728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015055816,0.000009633213,0.000079030535,0.000014611862,0.000006702343,0.000029441546,0.0040058345,0.0007998224,0.0003488378,0.9440093,0.00024544692,0.050449807],"study_design_scores_gemma":[0.000037446833,0.00023647849,0.0015773476,0.00008439271,0.000004075044,0.000012963429,0.0004167463,0.8081925,0.0024123515,0.06625724,0.120550804,0.00021769002],"about_ca_topic_score_codex":0.00003217883,"about_ca_topic_score_gemma":0.000030682517,"teacher_disagreement_score":0.9068111,"about_ca_system_score_codex":0.0000310627,"about_ca_system_score_gemma":0.00005505689,"threshold_uncertainty_score":0.88812876},"labels":[],"label_agreement":null},{"id":"W4407147701","doi":"10.1007/978-3-031-81101-2_3","title":"Bayesian Uncertainty Estimation Improves nnU-Net Generalization to Unseen Sites for Stroke Lesion Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Generalization; Computer science; Segmentation; Bayesian probability; Artificial intelligence; Estimation; Pattern recognition (psychology); Machine learning; Mathematics; Management","score_opus":0.023513669516403952,"score_gpt":0.29481371833575276,"score_spread":0.2713000488193488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407147701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020134891,0.00008723555,0.99473625,0.0015677846,0.0012128989,0.0015094044,0.000023814762,0.00019189023,0.00046939033],"genre_scores_gemma":[0.050287638,0.00002875045,0.9455119,0.002325492,0.0003227367,0.00008935834,0.00010206701,0.000032938588,0.0012991233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630016,0.000050060946,0.00068145274,0.0015569138,0.00077719626,0.0006341987],"domain_scores_gemma":[0.9973738,0.0005818913,0.00031766357,0.0009907747,0.0005657127,0.00017013478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000885203,0.00049357803,0.00042537192,0.0011721619,0.0004658938,0.0008704846,0.0019896561,0.00028982514,0.000008533721],"category_scores_gemma":[0.00030881714,0.00049160357,0.00012265562,0.00088375155,0.00019330565,0.0010182585,0.0006603504,0.00028193652,0.000021501637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010959973,0.000015150673,0.000011621538,0.000051110135,0.000006182309,0.0000032114901,0.00060556084,0.42594945,0.0056690564,0.018778788,0.00008363902,0.54881525],"study_design_scores_gemma":[0.00011052147,0.00024898438,0.00002058211,0.00021469247,0.000010953834,0.0000031915654,0.0000010521453,0.8573618,0.040313065,0.100848846,0.00043280082,0.0004335031],"about_ca_topic_score_codex":0.00011369717,"about_ca_topic_score_gemma":0.00047855152,"teacher_disagreement_score":0.54838175,"about_ca_system_score_codex":0.00065465417,"about_ca_system_score_gemma":0.0005641937,"threshold_uncertainty_score":0.99975353},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Interpretability; Artificial intelligence; Pixel; Computer science; Medicine; Machine learning","score_opus":0.0202131925955474,"score_gpt":0.36563903158435757,"score_spread":0.3454258389888102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407192178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3046402,0.0015010663,0.69052494,0.0007190302,0.00015081032,0.00012587463,0.0000017048056,0.000065512,0.0022708443],"genre_scores_gemma":[0.9979629,0.00007457437,0.0017563015,0.000052710824,0.0000105374465,0.000015799886,0.0000045731776,0.0000042489637,0.00011836671],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977432,0.0005973587,0.00058517954,0.00061886566,0.0001958791,0.0002595417],"domain_scores_gemma":[0.998403,0.00086187915,0.00014854589,0.0002828472,0.00019569784,0.00010802123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019226046,0.0001906993,0.0005150593,0.0006898745,0.00015229578,0.00009338184,0.00026915479,0.00008734594,0.00002343398],"category_scores_gemma":[0.0007759744,0.00018302597,0.000095821124,0.0014485648,0.00019797632,0.0008186737,0.00034032282,0.0007230746,0.0000020347459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001581862,0.0006663212,0.5246098,0.00019571064,0.00024829793,0.000005814775,0.022936242,0.009740095,0.0022998182,0.01778678,0.000024689562,0.42132825],"study_design_scores_gemma":[0.00013976118,0.00004183576,0.03180299,0.00011197788,0.00006775525,0.00000486463,0.00077353383,0.96039563,0.0007410088,0.0053899866,0.00039332357,0.00013731538],"about_ca_topic_score_codex":0.0010229155,"about_ca_topic_score_gemma":0.0045425477,"teacher_disagreement_score":0.9506556,"about_ca_system_score_codex":0.00012700443,"about_ca_system_score_gemma":0.000118837575,"threshold_uncertainty_score":0.7463583},"labels":[],"label_agreement":null},{"id":"W4407266104","doi":"10.1007/978-3-031-82742-6_4","title":"Tools and Techniques","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science","score_opus":0.035570284437758365,"score_gpt":0.26680610549856976,"score_spread":0.2312358210608114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407266104","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4868552e-7,0.00021242238,0.24250555,0.00068803836,0.000100174,0.00016768875,0.0000029778976,0.0003608097,0.755962],"genre_scores_gemma":[0.00008352897,0.00031019282,0.05557856,0.0009831196,0.0000545202,0.00001106463,0.0000023497662,0.0000100668285,0.9429666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989979,0.0000068266268,0.00021984374,0.0004463831,0.0001588626,0.00017015195],"domain_scores_gemma":[0.9990314,0.00013119039,0.00006089513,0.0006218152,0.00009927682,0.000055386372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001504107,0.00019433146,0.0002073095,0.00017568492,0.00007488987,0.0003092691,0.0006978337,0.00020704567,0.00015198161],"category_scores_gemma":[0.00003213299,0.00017891085,0.000054540906,0.000041184787,0.000066547254,0.00036206425,0.00057959906,0.00019525008,0.00014802908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0713874e-7,0.0000017285521,5.1262003e-7,0.000010562656,0.0000056635886,0.000012305988,0.000020061696,5.4078303e-8,0.000027986587,0.72360194,0.007050082,0.26926872],"study_design_scores_gemma":[0.000006330946,0.000034750243,7.688257e-7,0.000090282105,0.0000043816963,0.000005493351,0.000003135292,0.00022194635,0.013224779,0.34818697,0.6380264,0.00019476068],"about_ca_topic_score_codex":0.000023495222,"about_ca_topic_score_gemma":0.000024547788,"teacher_disagreement_score":0.6309763,"about_ca_system_score_codex":0.000037007674,"about_ca_system_score_gemma":0.0000836681,"threshold_uncertainty_score":0.7295773},"labels":[],"label_agreement":null},{"id":"W4407393913","doi":"","title":"Strategic Foundation Models","year":2025,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Foundation (evidence); Management science; Business; Engineering; Political science; Law","score_opus":0.04417561890155596,"score_gpt":0.2680097348220251,"score_spread":0.22383411592046915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407393913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051170783,0.00036666112,0.78436524,0.009405173,0.00045573406,0.0004222686,0.000014171508,0.00048548708,0.19936818],"genre_scores_gemma":[0.75248706,0.00054312934,0.22630806,0.0002776061,0.00003641465,0.00016053313,0.00024008866,0.000032081072,0.019915009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99217474,0.004795023,0.00070336746,0.0012486615,0.0005755398,0.0005026633],"domain_scores_gemma":[0.9910058,0.0015091057,0.0004997369,0.0038163203,0.0029856153,0.0001834592],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0064522903,0.00040032153,0.00038904033,0.00036366403,0.0004830998,0.0015620174,0.0040169563,0.00035264107,0.00008163129],"category_scores_gemma":[0.0007367215,0.00045797153,0.00022873367,0.0008206716,0.00017919957,0.0007130607,0.003284444,0.0007721048,0.00015636349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034219192,0.00021594613,0.000031335265,0.00009333198,0.00003293413,0.0000044872327,0.0041906033,0.0035154144,0.000276814,0.95950794,0.00029363393,0.031834144],"study_design_scores_gemma":[0.0000899549,2.4078116e-7,0.000041331554,0.0007540295,0.000015219585,0.0000028853724,0.0000967403,0.58340573,0.027768316,0.3855037,0.0019717258,0.0003501288],"about_ca_topic_score_codex":0.0023582138,"about_ca_topic_score_gemma":0.0020163662,"teacher_disagreement_score":0.74737,"about_ca_system_score_codex":0.00024340973,"about_ca_system_score_gemma":0.0009426572,"threshold_uncertainty_score":0.9997872},"labels":[],"label_agreement":null},{"id":"W4407561110","doi":"10.3390/math13040626","title":"Interpreting Temporal Shifts in Global Annual Data Using Local Surrogate Models","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Multivariate statistics; Feature selection; Computer science; Econometrics; Artificial intelligence; Machine learning; Imputation (statistics); Feature (linguistics); Missing data; Mathematics","score_opus":0.07838102560972571,"score_gpt":0.3515058835743446,"score_spread":0.2731248579646189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407561110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031454116,0.000076485005,0.9635984,0.00039367622,0.00024349753,0.00017572418,0.000021386917,0.00011894393,0.0039178133],"genre_scores_gemma":[0.7646375,0.0000020730795,0.23512146,0.00016642995,0.000013285755,0.0000033492686,0.0000039746146,0.0000070353485,0.000044921057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824643,0.00007466623,0.00054464967,0.00046217404,0.00026417128,0.0004078818],"domain_scores_gemma":[0.99830043,0.00016765947,0.00011419121,0.0012716452,0.00008617659,0.000059868005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095739705,0.00017091417,0.0002569643,0.00012018317,0.000090304005,0.00020972737,0.0022371726,0.00008256669,0.00000498782],"category_scores_gemma":[0.00021239478,0.00017186963,0.000036234604,0.00090589473,0.00008727741,0.0013036596,0.0019718723,0.00015856289,0.00003200185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011332751,0.00037936156,0.0010763742,0.00024679233,0.00003259064,0.00013090052,0.008371664,0.06090656,0.0000732893,0.8981139,0.00079175294,0.029865496],"study_design_scores_gemma":[0.000053530755,0.000009436502,0.000010120734,0.00022836775,0.000004264291,0.000004500335,0.001416961,0.78270125,0.00028404084,0.21508527,0.00008343147,0.00011881969],"about_ca_topic_score_codex":0.00041030275,"about_ca_topic_score_gemma":0.00046266968,"teacher_disagreement_score":0.7331834,"about_ca_system_score_codex":0.00020746668,"about_ca_system_score_gemma":0.00019017998,"threshold_uncertainty_score":0.700864},"labels":[],"label_agreement":null},{"id":"W4408135273","doi":"10.3389/fnagi.2025.1542514","title":"Comparing machine learning classifier models in discriminating cognitively unimpaired older adults from three clinical cohorts in the Alzheimer’s disease spectrum: demonstration analyses in the COMPASS-ND study","year":2025,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women and Children’s Health Research Institute; University of Alberta","funders":"","keywords":"Random forest; Artificial intelligence; Machine learning; Naive Bayes classifier; Computer science; Cognitive impairment; Probabilistic classification; Cohort; Classifier (UML); Cognition; Psychology; Medicine; Support vector machine; Neuroscience; Pathology","score_opus":0.15308231202863382,"score_gpt":0.37279735505592854,"score_spread":0.21971504302729472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408135273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.738,0.00033892455,0.2580646,0.0017029978,0.00055461004,0.00096558785,0.000002091936,0.000043785232,0.00032741978],"genre_scores_gemma":[0.9976496,0.000020539825,0.001514469,0.000684295,0.000023599976,0.00008827263,0.0000034521313,0.000009339704,0.000006393664],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945361,0.0020034912,0.0010034,0.0011323418,0.0006907471,0.0006339],"domain_scores_gemma":[0.9979763,0.0010228329,0.00024053657,0.0006405384,0.00004349496,0.00007627585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031691378,0.0002821456,0.00046122083,0.0006700301,0.00036025382,0.00057839573,0.002299904,0.0000531347,9.379214e-7],"category_scores_gemma":[0.0006791195,0.00021496745,0.00007851344,0.0032612532,0.00037190813,0.0012691148,0.00039024962,0.0010971323,7.973296e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004556683,0.0006205607,0.93777514,0.0000057316847,0.000004270439,0.00025206828,0.009854307,0.04594607,0.000017928056,0.00067202596,0.000043090477,0.0047632554],"study_design_scores_gemma":[0.00028939534,0.00003307684,0.48400125,0.00013074341,0.000012564436,7.185229e-7,0.006376047,0.50516224,0.000022687631,0.0038578738,0.0000016830425,0.00011173493],"about_ca_topic_score_codex":0.002608754,"about_ca_topic_score_gemma":0.0113835,"teacher_disagreement_score":0.45921615,"about_ca_system_score_codex":0.000111029374,"about_ca_system_score_gemma":0.00016990128,"threshold_uncertainty_score":0.8766118},"labels":[],"label_agreement":null},{"id":"W4408549997","doi":"10.1029/2024wr037398","title":"On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis","year":2025,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Suncor Energy Incorporated","keywords":"Robustness (evolution); Explanatory power; Sensitivity (control systems); Machine learning; Artificial intelligence; Computer science; Engineering; Epistemology; Chemistry","score_opus":0.08346191017698525,"score_gpt":0.318397046788249,"score_spread":0.23493513661126375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408549997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6273084,0.00019375274,0.37056112,0.000210089,0.00004697049,0.0002051876,0.0000028085024,0.000028131679,0.0014434761],"genre_scores_gemma":[0.99634135,0.0000063120137,0.0023401533,0.00004902894,0.000026103737,0.00000955315,0.0000052772157,0.000014214955,0.0012080303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949241,0.002059482,0.0004769122,0.00069551007,0.0012399434,0.0006040537],"domain_scores_gemma":[0.9973028,0.00068075507,0.00011274612,0.0013205607,0.0004700684,0.00011311582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020953226,0.00020473538,0.00047167696,0.0012115645,0.0004966727,0.00018617019,0.0014524354,0.00013678521,0.00002459437],"category_scores_gemma":[0.00024133592,0.0001307695,0.00022256537,0.0030895288,0.00028917773,0.00047406778,0.0014352781,0.00078738853,0.000005059561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009253478,0.0001655516,0.00074805476,0.000042195836,0.00024624087,0.000014326985,0.017843325,0.9630841,0.010506647,0.006650103,0.000062982275,0.0005439594],"study_design_scores_gemma":[0.000106619096,0.000044537326,0.00010682701,0.000070634516,0.000030906827,7.8849104e-7,0.0013630497,0.84284306,0.14687918,0.008143902,0.0002931069,0.00011738057],"about_ca_topic_score_codex":0.015634554,"about_ca_topic_score_gemma":0.00041993542,"teacher_disagreement_score":0.3690329,"about_ca_system_score_codex":0.00014866874,"about_ca_system_score_gemma":0.00014490321,"threshold_uncertainty_score":0.9909204},"labels":[],"label_agreement":null},{"id":"W4408688463","doi":"10.1098/rsos.241038","title":"The reliability of replications: a study in computational reproductions","year":2025,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Simon Fraser University","funders":"Agencia Nacional de Investigación y Desarrollo","keywords":"Transparency (behavior); Replication (statistics); Computer science; Decimal; Reliability (semiconductor); Opacity; Workflow; Code (set theory); Reproduction; Group (periodic table); Statistics; Psychology; Mathematics; Arithmetic; Programming language; Computer security; Biology","score_opus":0.03172278573118792,"score_gpt":0.36568305970821435,"score_spread":0.33396027397702643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408688463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.538456,0.00014209843,0.4110756,0.031177612,0.0007119679,0.0034331025,0.0000027820242,0.00011472514,0.0148861185],"genre_scores_gemma":[0.9668198,0.0000049056525,0.03189549,0.000170162,0.000007208194,0.00012763006,2.3732665e-7,0.0000017610423,0.0009727738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786675,0.00011251613,0.00045795526,0.0008248949,0.0004734302,0.00026445073],"domain_scores_gemma":[0.99706215,0.0004796581,0.0001264428,0.0016865254,0.00060374814,0.00004146125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069401,0.00007687899,0.00012884666,0.0000505644,0.0011918619,0.0005264245,0.0052312333,0.000022445778,0.000004140047],"category_scores_gemma":[0.0015416335,0.00005985915,0.000055364133,0.0038184284,0.00083743397,0.0007685273,0.0020756705,0.0001472411,0.0000107885735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015403682,0.0015689037,0.097875156,0.000015158095,0.000018098921,0.0000010762368,0.012369834,0.17197035,0.00045295566,0.6866123,0.004351714,0.02474902],"study_design_scores_gemma":[0.0001875025,0.00010281731,0.28696108,0.000026831312,0.0000044691224,8.729029e-7,0.0071871057,0.56658655,0.002214441,0.13478415,0.0017887973,0.00015534037],"about_ca_topic_score_codex":0.0013070017,"about_ca_topic_score_gemma":0.00019598342,"teacher_disagreement_score":0.55182815,"about_ca_system_score_codex":0.00020305031,"about_ca_system_score_gemma":0.0009483813,"threshold_uncertainty_score":0.972102},"labels":[],"label_agreement":null},{"id":"W4409136955","doi":"10.1371/journal.pone.0320151","title":"Using artificial intelligence tools to automate data extraction for living evidence syntheses","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Python (programming language); Parsing; Data extraction; Artificial intelligence; Information extraction; Data science; Machine learning; MEDLINE; Programming language","score_opus":0.590885932505264,"score_gpt":0.42421923566740216,"score_spread":0.16666669683786184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409136955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027725186,0.00022509249,0.9680043,0.0021228828,0.00035973027,0.0008643871,0.00001597564,0.00037170772,0.0003107328],"genre_scores_gemma":[0.6666723,0.000041087333,0.33258346,0.00033771852,0.00013592567,0.00007970785,0.000001317575,0.000013639575,0.00013482194],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741906,0.00011745588,0.00056966225,0.0009189878,0.00043722568,0.00053759705],"domain_scores_gemma":[0.99217206,0.00541138,0.0001442577,0.001792977,0.00035911222,0.000120239165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014303565,0.00020071596,0.00029161156,0.0003014562,0.00040660304,0.00090055395,0.00255095,0.00007191114,0.00003665841],"category_scores_gemma":[0.019946268,0.000221487,0.00005024233,0.001048289,0.000053496828,0.0033586482,0.0012221421,0.00015325144,0.00016352154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073366755,0.0015978705,0.00026232252,0.0004842845,0.00018743184,0.000016992808,0.0011029601,0.0042842617,0.37595674,0.24715321,0.0002832058,0.36859733],"study_design_scores_gemma":[0.0000027870747,0.00005827824,0.000057105477,0.0032512392,0.000047961763,0.0000015507004,0.00016733291,0.6337525,0.35363883,0.008719475,0.00009519064,0.00020770798],"about_ca_topic_score_codex":0.00018043703,"about_ca_topic_score_gemma":0.00014512794,"teacher_disagreement_score":0.6389471,"about_ca_system_score_codex":0.00017995227,"about_ca_system_score_gemma":0.0002428385,"threshold_uncertainty_score":0.98830914},"labels":[],"label_agreement":null},{"id":"W4409202067","doi":"10.1016/j.eswa.2025.127553","title":"Feature Similarity Group-Class Activation Mapping (FSG-CAM): Clarity in deep learning models and Enhancement of visual explanations","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Shanxi Provincial Key Research and Development Project; National Natural Science Foundation of China","keywords":"CLARITY; Artificial intelligence; Class (philosophy); Similarity (geometry); Feature (linguistics); Computer science; Pattern recognition (psychology); Group (periodic table); Machine learning; Image (mathematics); Chemistry","score_opus":0.027184840549033456,"score_gpt":0.2890037241834583,"score_spread":0.26181888363442485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409202067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01252527,0.0005822473,0.98249036,0.0014256644,0.000054124106,0.0010450559,0.0000012913239,0.00009367698,0.0017823211],"genre_scores_gemma":[0.98275155,0.000070292845,0.015279907,0.000109288405,0.00003153677,0.0015240959,0.00001754497,0.000008643216,0.00020712854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847966,0.00012841495,0.00037271556,0.000496143,0.0002698938,0.00025318112],"domain_scores_gemma":[0.9988857,0.00021138306,0.00020371305,0.00042510327,0.00021185442,0.00006227073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040035037,0.00016455883,0.00025089047,0.00033159243,0.00032668794,0.00013498444,0.00037990737,0.00012652173,0.0000015840293],"category_scores_gemma":[0.000034117737,0.00015992147,0.000027726946,0.0011967535,0.00006688277,0.0007171829,0.0001385103,0.0002698384,0.0000028838263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026521606,0.0005720443,0.003411149,0.00025188696,0.00007544411,0.0000017953223,0.009446902,0.02636257,0.030626059,0.9111086,0.0003262747,0.017790742],"study_design_scores_gemma":[0.0002902792,0.00007660462,0.0013441879,0.0003120476,0.0000063760544,0.0000041372523,0.005683142,0.9653636,0.013631049,0.0040561897,0.008935707,0.00029668302],"about_ca_topic_score_codex":0.00063695706,"about_ca_topic_score_gemma":0.00025505683,"teacher_disagreement_score":0.9702263,"about_ca_system_score_codex":0.00018415839,"about_ca_system_score_gemma":0.000084099614,"threshold_uncertainty_score":0.65214086},"labels":[],"label_agreement":null},{"id":"W4409362925","doi":"10.1609/aaai.v39i21.34460","title":"Causally Consistent Normalizing Flow","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Flow (mathematics); Geology; Econometrics; Mathematics; Geometry","score_opus":0.061864180208544006,"score_gpt":0.2980902601648691,"score_spread":0.2362260799563251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409362925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105293505,0.0003354947,0.49342597,0.041407496,0.005254003,0.0026214279,0.000019756535,0.0009426409,0.35069972],"genre_scores_gemma":[0.98766494,0.000060662762,0.009555584,0.0010969243,0.000060274724,0.000057994937,5.039196e-7,0.00001571922,0.0014874027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99665076,0.00003955264,0.001052794,0.00084304134,0.0007098761,0.0007039705],"domain_scores_gemma":[0.99701786,0.0002406716,0.0004576705,0.0007408692,0.0014058249,0.00013711788],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009517808,0.00038753435,0.0004445881,0.0003586949,0.000496388,0.0005838015,0.003894279,0.00016466365,0.00010468491],"category_scores_gemma":[0.000942848,0.0003111686,0.00025005554,0.0018704378,0.0005080699,0.00078910636,0.001025868,0.00049841637,0.00021198248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044588094,0.00015967953,0.00020149519,0.00005239808,0.000032272317,0.0000017637396,0.000874889,0.00033201577,0.029389944,0.90661734,0.00086647103,0.061427113],"study_design_scores_gemma":[0.000021878588,0.00012244668,0.00008881649,0.0003749323,0.000019604751,0.0000051683974,0.0008271053,0.11495341,0.6455421,0.23684153,0.00092448364,0.00027853533],"about_ca_topic_score_codex":0.00014515186,"about_ca_topic_score_gemma":0.000060900937,"teacher_disagreement_score":0.8823714,"about_ca_system_score_codex":0.00014085998,"about_ca_system_score_gemma":0.00035700618,"threshold_uncertainty_score":0.999934},"labels":[],"label_agreement":null},{"id":"W4409373644","doi":"10.1016/b978-0-44-329135-7.00022-9","title":"Conclusions: a human-centric perspective","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"","keywords":"Perspective (graphical); Sociology; Psychology; Political science; Computer science; Artificial intelligence","score_opus":0.024601553048267194,"score_gpt":0.29118750399672333,"score_spread":0.26658595094845616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409373644","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002008023,0.0028338707,0.0031948977,0.00050541846,0.00094552414,0.000765468,0.000012399558,0.0003432172,0.9913972],"genre_scores_gemma":[0.0005116229,0.00012365401,0.002179778,0.00092819653,0.00027838838,0.000054462045,0.000005096711,0.00004486329,0.9958739],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704665,0.000060953476,0.00061631144,0.0011398721,0.0005748745,0.0005613188],"domain_scores_gemma":[0.99705225,0.00025839714,0.0003110092,0.0015899973,0.00060132693,0.00018703072],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034295884,0.000555841,0.00064332644,0.0005632909,0.00056904973,0.00026842926,0.0021291394,0.00039267744,0.00025792382],"category_scores_gemma":[0.00013006694,0.00056195696,0.0003686571,0.00009783304,0.00022341314,0.00018558312,0.0015830551,0.00076074287,0.0009273491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018723994,0.00001013342,3.978003e-7,0.000018446137,0.000047410645,0.00009544254,0.0006626094,9.82504e-7,0.000017754735,0.58334553,0.0006210801,0.41517833],"study_design_scores_gemma":[0.00007790955,0.000070334616,7.6919264e-7,0.00033251752,0.00004014305,0.000011229114,0.00007121835,0.00016596989,0.00029496764,0.3101684,0.68832654,0.0004400158],"about_ca_topic_score_codex":0.000009798927,"about_ca_topic_score_gemma":0.000049590202,"teacher_disagreement_score":0.68770546,"about_ca_system_score_codex":0.00066357007,"about_ca_system_score_gemma":0.0005349755,"threshold_uncertainty_score":0.9998506},"labels":[],"label_agreement":null},{"id":"W4409374188","doi":"10.1016/b978-0-443-15888-9.00002-9","title":"What’s it all about?","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Environmental science","score_opus":0.03252871179226258,"score_gpt":0.28120773321652065,"score_spread":0.24867902142425807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374188","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.4358405e-7,0.0028344013,0.002459816,0.0019717657,0.0048692427,0.00053454336,0.0000061641267,0.00029974466,0.9870236],"genre_scores_gemma":[0.000039809853,0.0009509368,0.0031184282,0.005805806,0.00032994398,0.000052083495,0.000009025377,0.000052419637,0.98964155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968332,0.00004769028,0.00075032143,0.0011128429,0.0006075363,0.00064840197],"domain_scores_gemma":[0.99687386,0.0002609779,0.00030156708,0.0020669047,0.00028111172,0.00021556563],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047221303,0.0006018419,0.00062660116,0.00035667387,0.00018904152,0.0009790956,0.0026556107,0.0004783516,0.00026718221],"category_scores_gemma":[0.000057799964,0.00061536935,0.00036644106,0.00004879618,0.00016493413,0.0006374757,0.0010273954,0.00072343927,0.0023959863],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002332258,0.000005861288,1.463153e-7,0.00004350476,0.00005691724,0.00008802656,0.0005267472,0.0000022207046,0.000008868998,0.306352,0.0045295223,0.6883839],"study_design_scores_gemma":[0.000046708246,0.00004665996,5.141236e-7,0.00089551223,0.000037744034,0.000010911852,0.000023278048,0.00032163472,0.00051115354,0.10543915,0.8921341,0.0005326909],"about_ca_topic_score_codex":0.0000028187053,"about_ca_topic_score_gemma":0.0001074981,"teacher_disagreement_score":0.88760453,"about_ca_system_score_codex":0.00019473195,"about_ca_system_score_gemma":0.00039288524,"threshold_uncertainty_score":0.99962974},"labels":[],"label_agreement":null},{"id":"W4409426170","doi":"10.1109/tts.2025.3558448","title":"Is Trust Correlated With Explainability in AI? A Meta-Analysis","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Technology and Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Canada Research Chairs","keywords":"Meta-analysis; Psychology; Medicine; Internal medicine","score_opus":0.024912999143146458,"score_gpt":0.2852242275704298,"score_spread":0.2603112284272834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409426170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04102966,0.00016368293,0.9465966,0.01144708,0.00005726583,0.00021413897,0.000005099705,0.00027362176,0.00021281773],"genre_scores_gemma":[0.9912459,0.000058327532,0.0063103624,0.0013899384,9.745833e-7,0.00013975108,2.8682504e-7,0.0000042739093,0.00085013435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986764,0.000060594124,0.00027390165,0.0005837137,0.00012356098,0.00028180526],"domain_scores_gemma":[0.99899524,0.00011907837,0.000048349673,0.0006952304,0.00010671088,0.000035369787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003466212,0.00017465999,0.0004696643,0.000598459,0.0003356805,0.00005129611,0.00042833938,0.00033721048,0.000055434277],"category_scores_gemma":[0.000006036773,0.00014417064,0.00040737377,0.0059591415,0.0003555981,0.00027569055,0.000006851854,0.00060335733,0.000008085908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035726445,0.0053122113,0.013817421,0.00028381645,0.21561539,0.00016614057,0.03861007,0.09247967,0.0017914271,0.52002287,0.0020783881,0.109465346],"study_design_scores_gemma":[0.0012415799,0.0007599227,0.0014539108,0.000029162959,0.03699304,0.00002597506,0.009765766,0.5289918,0.29842296,0.1196015,0.0015118135,0.001202516],"about_ca_topic_score_codex":0.00013367362,"about_ca_topic_score_gemma":0.00029266684,"teacher_disagreement_score":0.9502163,"about_ca_system_score_codex":0.00008501747,"about_ca_system_score_gemma":0.000077944926,"threshold_uncertainty_score":0.58791083},"labels":[],"label_agreement":null},{"id":"W4409654282","doi":"10.1117/1.jmi.12.2.024506","title":"Dimensionality reduction in 3D causal deep learning for neuroimage generation: an evaluation study","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Parkinson Association of Alberta; Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Medicine; Dimensionality reduction; Reduction (mathematics); Artificial intelligence; Deep learning; Pattern recognition (psychology); Machine learning","score_opus":0.06659836844666897,"score_gpt":0.4031126343954088,"score_spread":0.3365142659487398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409654282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3384723,0.00019875563,0.6535156,0.006237654,0.0012916463,0.00021613533,4.098586e-8,0.000015026574,0.000052841577],"genre_scores_gemma":[0.99234664,0.000012385354,0.006947015,0.00026077282,0.00039640602,0.000011872691,0.0000012131978,0.0000049526357,0.000018742403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970245,0.00066334434,0.0006559658,0.00024939657,0.001213733,0.0001931021],"domain_scores_gemma":[0.9986542,0.00018744297,0.00023106964,0.0001860356,0.0006274367,0.00011384395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008463024,0.00008797913,0.0001769121,0.00028496247,0.0001950111,0.00018132312,0.00048272053,0.000038854763,0.000028598422],"category_scores_gemma":[0.002346444,0.00008033105,0.00004761634,0.000439625,0.000042803287,0.0012324076,0.00010332002,0.00042765585,0.0000017245662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004125936,0.00073602126,0.0077754403,0.000014994284,0.000023735884,0.00013904767,0.002667687,0.025820196,0.008172639,0.0034156465,0.0005243673,0.950669],"study_design_scores_gemma":[0.00048709387,0.000105348765,0.004635387,0.000047066915,0.000019710807,0.0000683312,0.0012666648,0.9892638,0.0012698757,0.0025348654,0.00023375388,0.00006814326],"about_ca_topic_score_codex":0.000055882945,"about_ca_topic_score_gemma":0.00005714231,"teacher_disagreement_score":0.9634436,"about_ca_system_score_codex":0.0001659579,"about_ca_system_score_gemma":0.00038220896,"threshold_uncertainty_score":0.32758048},"labels":[],"label_agreement":null},{"id":"W4409720607","doi":"10.1145/3706599.3706736","title":"Designing and Developing User Interfaces with AI: Advancing Tools, Workflows, and Practices","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Workflow; Computer science; Human–computer interaction; User interface; Software engineering; World Wide Web; Programming language; Database","score_opus":0.03591963157330476,"score_gpt":0.3227527521372698,"score_spread":0.28683312056396504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409720607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101479635,0.00051935355,0.89011,0.004970569,0.000087322565,0.00014590223,7.6364195e-8,0.00013053232,0.0025565876],"genre_scores_gemma":[0.52255243,0.00009610506,0.47534013,0.001258789,0.000011954866,0.000011570239,1.5782628e-7,0.0000054151737,0.00072342076],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892575,0.000058221183,0.0001874539,0.00041944618,0.00012063173,0.0002885165],"domain_scores_gemma":[0.99897623,0.0005196522,0.000113911025,0.00022857728,0.00010629061,0.000055352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004177671,0.00013543897,0.00014126107,0.00012680382,0.000246582,0.00089493673,0.0003069123,0.000039969465,0.0000047448557],"category_scores_gemma":[0.00032245056,0.00010746901,0.000007618675,0.00046717827,0.00006147248,0.0028358384,0.00035649582,0.00013614565,0.00000570862],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079770296,0.000049044236,0.044607315,0.00020611554,0.000118581935,0.000082706385,0.004747651,0.0008329787,0.014268697,0.44286987,0.0015160291,0.49062124],"study_design_scores_gemma":[0.00043138702,0.0003316152,0.005355252,0.0015438499,0.000045066805,0.00010075006,0.01004362,0.06766795,0.8586145,0.02753383,0.027243044,0.0010891433],"about_ca_topic_score_codex":0.000107990985,"about_ca_topic_score_gemma":0.00042080352,"teacher_disagreement_score":0.8443458,"about_ca_system_score_codex":0.00003827424,"about_ca_system_score_gemma":0.00013240353,"threshold_uncertainty_score":0.86298954},"labels":[],"label_agreement":null},{"id":"W4409903669","doi":"10.1007/s43681-025-00731-7","title":"Ethical impacts of a NLP-based ML framework: the case of AI2","year":2025,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Psychology; Artificial intelligence","score_opus":0.044372627328819775,"score_gpt":0.38615585906674293,"score_spread":0.34178323173792313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409903669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09662505,0.0003740877,0.79851085,0.103282884,0.00024148881,0.00013691459,0.000003343611,0.00003569104,0.0007897088],"genre_scores_gemma":[0.981781,0.000047168236,0.0057062805,0.012414776,0.00001468143,0.000003639187,2.3823607e-7,0.0000032339854,0.000029003226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892884,0.00024499928,0.0002603931,0.0001897306,0.00018167288,0.00019438533],"domain_scores_gemma":[0.9957027,0.0033289718,0.00007997779,0.00054341485,0.00028962168,0.00005531781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019403298,0.00008525135,0.00015295639,0.0000738402,0.00018488904,0.00005737158,0.00043587649,0.00044853945,0.000007713827],"category_scores_gemma":[0.0026278228,0.00006061311,0.00005254679,0.0005331771,0.00038760042,0.00009614157,0.00018607045,0.0015516548,0.0000033729198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001210906,0.000040059404,0.0002301926,0.00012590025,0.000013249546,0.00007259895,0.007554658,0.00028716566,0.00045134153,0.98200834,0.00038100683,0.008823355],"study_design_scores_gemma":[0.00014597156,0.00026020638,0.0003456928,0.00046526408,0.00003129156,0.00004745618,0.0012242144,0.17466775,0.12186949,0.69886774,0.0018844919,0.00019045439],"about_ca_topic_score_codex":0.0009975102,"about_ca_topic_score_gemma":0.00043690673,"teacher_disagreement_score":0.8851559,"about_ca_system_score_codex":0.0000116894635,"about_ca_system_score_gemma":0.00041416808,"threshold_uncertainty_score":0.67412543},"labels":[],"label_agreement":null},{"id":"W4410034776","doi":"10.1007/978-981-96-2540-6_4","title":"Evolutionary Computation for Explainable Deep Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Natural computing series","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Cognitive science; Psychology","score_opus":0.01642144696102722,"score_gpt":0.26609782876718696,"score_spread":0.24967638180615975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410034776","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000062715684,0.0049982923,0.86765224,0.0010780883,0.0032261303,0.0009299603,0.000007038547,0.0011749812,0.12087055],"genre_scores_gemma":[0.084633425,0.00012256643,0.260362,0.00051992666,0.0008755787,0.00003315245,0.00027578452,0.00009700123,0.6530806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973115,0.000061197534,0.000636276,0.00092808384,0.00044931003,0.0006136403],"domain_scores_gemma":[0.99739414,0.00080774835,0.0004360385,0.00042502393,0.0008536379,0.000083403385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041141818,0.0005113642,0.0005380834,0.00039125676,0.0011485231,0.0004038376,0.0010521044,0.00037451976,0.000014032214],"category_scores_gemma":[0.00031052594,0.00055745064,0.00027693476,0.00020751932,0.00013830786,0.0008601358,0.0007081669,0.0009232926,0.00006743162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037371457,0.000011190083,0.000005711476,0.00022008167,0.00006554494,0.000023169396,0.0005331781,0.011252547,0.000036343677,0.87111473,0.004803957,0.11189616],"study_design_scores_gemma":[0.00016836994,0.0002781447,0.000023815113,0.00051759265,0.00003628959,0.00004891409,0.00016586193,0.5736487,0.0005383792,0.20844068,0.21526834,0.0008649228],"about_ca_topic_score_codex":0.000022374767,"about_ca_topic_score_gemma":0.000022462398,"teacher_disagreement_score":0.66267407,"about_ca_system_score_codex":0.00035236997,"about_ca_system_score_gemma":0.00022139851,"threshold_uncertainty_score":0.9996877},"labels":[],"label_agreement":null},{"id":"W4410089313","doi":"10.26443/law.v69i4.1645","title":"Reasonable Apprehension of AI Bias","year":2024,"lang":"en","type":"article","venue":"McGill Law Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Canada Research Chairs","keywords":"Apprehension; Psychology; Economics; Political science; Social psychology; Cognitive psychology","score_opus":0.051438074584039026,"score_gpt":0.2931065987156708,"score_spread":0.24166852413163176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410089313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019508943,0.0044470127,0.59364647,0.011430105,0.0071270415,0.00038097485,0.000021319123,0.00077369506,0.36266446],"genre_scores_gemma":[0.9881861,0.00007382648,0.01092567,0.00032582643,0.00013532347,0.000002112028,3.997789e-7,0.000014110682,0.00033663836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998516,0.00009314977,0.0003882422,0.00025650306,0.000418987,0.00032708715],"domain_scores_gemma":[0.9990688,0.00014302653,0.00008041074,0.00035189363,0.00021229434,0.00014359699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007373932,0.00012116915,0.00016812661,0.0001350537,0.0007363509,0.00028342055,0.0006701264,0.00006282945,0.00010178944],"category_scores_gemma":[0.00006451377,0.000099259756,0.00013297104,0.0005185873,0.00006705508,0.0011514181,0.00018758356,0.0004001925,0.0002642945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046608175,0.000035731715,0.00001542784,0.00002733389,0.000018898909,0.000226302,0.00012947258,0.00045620982,0.0021125237,0.9612573,0.0015587419,0.034157425],"study_design_scores_gemma":[0.000058950896,0.00015342348,0.000020699357,0.0002399962,0.0000107627575,0.0007824221,0.000080822814,0.048715632,0.13463931,0.06962141,0.745498,0.00017856325],"about_ca_topic_score_codex":0.000297109,"about_ca_topic_score_gemma":0.00018831676,"teacher_disagreement_score":0.96867716,"about_ca_system_score_codex":0.00006914408,"about_ca_system_score_gemma":0.000028187294,"threshold_uncertainty_score":0.56634897},"labels":[],"label_agreement":null},{"id":"W4410188329","doi":"10.4258/hir.2025.31.2.125","title":"Developing an Explainable Artificial Intelligence System for the Mobile-Based Diagnosis of Febrile Diseases Using Random Forest, LIME, and GPT","year":2025,"lang":"en","type":"article","venue":"Healthcare Informatics Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Random forest; Computer science; Artificial intelligence; Medicine; Bioinformatics; Biology","score_opus":0.2056067041650366,"score_gpt":0.4477474518351457,"score_spread":0.2421407476701091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410188329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057157382,0.0013480061,0.93670666,0.0015169083,0.00029011196,0.0027969428,0.000033411794,0.000097171695,0.000053415493],"genre_scores_gemma":[0.9609095,0.00020862423,0.03722965,0.00019703794,0.00005906893,0.0013596973,0.000010335805,0.0000152425555,0.000010882373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636537,0.00039677435,0.0012112389,0.00031441817,0.0008059977,0.00090619153],"domain_scores_gemma":[0.99185544,0.004994754,0.00024265051,0.000950084,0.0017360738,0.00022098472],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003890283,0.00020743092,0.0003957051,0.00067032326,0.001493531,0.00058582664,0.0013807743,0.00012778772,0.0000023537189],"category_scores_gemma":[0.001019371,0.00016563719,0.000090076865,0.0018710069,0.0003506073,0.0010161103,0.0005098268,0.00032668025,0.0000049820355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034787648,0.0001376222,0.0032578136,0.007909722,0.000049094873,0.0000073895017,0.0063596815,0.050647985,0.00002612815,0.72110444,0.00012704621,0.21002519],"study_design_scores_gemma":[0.00014394004,0.0002937518,0.000086732376,0.0008744754,0.000011523625,0.000003634101,0.018540343,0.9436113,0.018962003,0.016645012,0.00065472734,0.0001725551],"about_ca_topic_score_codex":0.0018479407,"about_ca_topic_score_gemma":0.0005772868,"teacher_disagreement_score":0.9037521,"about_ca_system_score_codex":0.00045586485,"about_ca_system_score_gemma":0.0018595927,"threshold_uncertainty_score":0.9998064},"labels":[],"label_agreement":null},{"id":"W4410235759","doi":"10.22399/ijcesen.1684","title":"Explainable AI for Decision-Making: A Hybrid Approach to Trustworthy Computing","year":2025,"lang":"en","type":"article","venue":"International Journal of Computational and Experimental Science and Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Trustworthiness; Computer science; Artificial intelligence; Data science; Knowledge management; Computer security","score_opus":0.009974384560608729,"score_gpt":0.3058716543275601,"score_spread":0.29589726976695135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410235759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19378895,0.0002010117,0.804342,0.00073356496,0.0005949553,0.00009518665,0.0000010168419,0.000015574753,0.0002277603],"genre_scores_gemma":[0.79195297,0.0000029894852,0.20735177,0.0006052072,0.000072279385,0.0000049005503,3.187128e-7,0.0000030593105,0.000006468027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986793,0.0000067351248,0.00033029864,0.00023920451,0.00054037827,0.00020411747],"domain_scores_gemma":[0.9987675,0.0002955825,0.0000798016,0.00006542646,0.000677607,0.000114106704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006639631,0.00010609753,0.0001392079,0.00051863084,0.00020652839,0.00038230064,0.0006806159,0.0000165748,0.0000010826086],"category_scores_gemma":[0.00028599935,0.0000984499,0.000040435705,0.00040027796,0.00006216248,0.0009505628,0.000307888,0.00007968468,7.537358e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007846499,0.00012551295,0.00014735562,0.000014187187,0.000043426324,0.0000130742565,0.0015251947,0.7105508,0.0042806882,0.21690084,0.00050258415,0.065817885],"study_design_scores_gemma":[0.00022967102,0.00010604095,0.000647425,0.00016731402,0.0000028243905,0.00017716683,0.00038047,0.97101223,0.009330659,0.016228018,0.0015827694,0.00013542011],"about_ca_topic_score_codex":0.000004455948,"about_ca_topic_score_gemma":1.2395904e-7,"teacher_disagreement_score":0.598164,"about_ca_system_score_codex":0.00014190009,"about_ca_system_score_gemma":0.00015389585,"threshold_uncertainty_score":0.40146703},"labels":[],"label_agreement":null},{"id":"W4410277248","doi":"10.1007/978-3-031-92747-8_2","title":"Triadic Patterns for Explainable Artificial Intelligence","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; McGill University","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.04308642014187211,"score_gpt":0.29385569214015267,"score_spread":0.2507692719982806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410277248","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002932557,0.00037508731,0.9890185,0.0017845391,0.0038249544,0.0014225045,0.00002446542,0.0002977047,0.0032228902],"genre_scores_gemma":[0.16129258,0.00022103128,0.8264511,0.0044739316,0.0020208359,0.00032653922,0.000031199266,0.0001365903,0.005046152],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934941,0.000059574504,0.0012540566,0.002642459,0.0010794057,0.0014704206],"domain_scores_gemma":[0.99440193,0.0018828347,0.00044422172,0.0023136188,0.000685305,0.00027206432],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002026517,0.0008379471,0.00089371356,0.0017467991,0.00066174596,0.0012227788,0.0063224337,0.0005384856,0.0000592543],"category_scores_gemma":[0.00063251203,0.0008434246,0.00033957267,0.0012702158,0.000672727,0.0010927166,0.0017686859,0.0009357398,0.00010521719],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018876115,0.000039046667,0.000008463074,0.00011013756,0.000012530753,0.000058211543,0.00046750405,0.014945208,0.00008605971,0.33016235,0.000037990605,0.6540536],"study_design_scores_gemma":[0.000056460663,0.00024026923,0.0000033315232,0.0005372829,0.0000115094945,0.000015730828,0.000001566796,0.41692516,0.020443503,0.55899304,0.0021049124,0.00066719216],"about_ca_topic_score_codex":0.00009446482,"about_ca_topic_score_gemma":0.0003476643,"teacher_disagreement_score":0.6533864,"about_ca_system_score_codex":0.0006887859,"about_ca_system_score_gemma":0.0013902308,"threshold_uncertainty_score":0.99981403},"labels":[],"label_agreement":null},{"id":"W4410453527","doi":"10.3389/fncom.2025.1560064","title":"Interpretable machine learning for precision cognitive aging","year":2025,"lang":"en","type":"article","venue":"Frontiers in Computational Neuroscience","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fraser Health; Royal Columbian Hospital; Simon Fraser University","funders":"Mitacs","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Cognition; Support vector machine; Random forest; Logistic regression; Regression; Artificial neural network; Gradient boosting; Predictive modelling; Psychology","score_opus":0.018632827392424087,"score_gpt":0.30121367618407924,"score_spread":0.2825808487916551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410453527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030174858,0.0002038992,0.99186385,0.0010225397,0.002091087,0.00038518116,0.000004044185,0.00010685937,0.0013050428],"genre_scores_gemma":[0.84610796,0.000013577074,0.15118514,0.0012535936,0.00001690106,0.000054790118,0.000004155096,0.000006921608,0.001356954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998187,0.00010889204,0.00033169973,0.0006803635,0.00031163837,0.00038040974],"domain_scores_gemma":[0.9987738,0.00071288605,0.00009819571,0.00016311306,0.0001944075,0.000057606427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061175856,0.00014384028,0.00017956278,0.0005148735,0.00036345504,0.000291469,0.00093591464,0.00003892339,0.0000032158373],"category_scores_gemma":[0.0011695983,0.00015434656,0.000058944413,0.0014697118,0.00013998318,0.0009157502,0.0003256088,0.00022153753,0.000003394963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007694651,0.00018803458,0.02385694,0.00004457499,0.000007654207,0.000023329832,0.0009311935,0.7882858,0.00071384694,0.047750425,0.004944789,0.13317648],"study_design_scores_gemma":[0.00017967122,0.00007055715,0.0022960203,0.00009565042,0.0000023209132,0.0000030020494,0.00008454246,0.92131865,0.0013213604,0.07183764,0.0026613146,0.00012929183],"about_ca_topic_score_codex":0.000018170918,"about_ca_topic_score_gemma":0.000005288097,"teacher_disagreement_score":0.8430905,"about_ca_system_score_codex":0.00009660843,"about_ca_system_score_gemma":0.00017820562,"threshold_uncertainty_score":0.629407},"labels":[],"label_agreement":null},{"id":"W4410462350","doi":"10.1007/978-3-031-88042-1_6","title":"Traffic Crash Severity Prediction Using eXplainable AI","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Crash; Computer science; Artificial intelligence; Operating system","score_opus":0.04871422867016001,"score_gpt":0.30994382602247306,"score_spread":0.26122959735231305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410462350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022579225,0.00024178729,0.8547525,0.0011510085,0.00063012575,0.00053510675,0.000018272609,0.00020974567,0.1422357],"genre_scores_gemma":[0.21907538,0.007244972,0.7497322,0.008559199,0.00023970929,0.00015911668,0.0001930624,0.000045325512,0.014751056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978498,0.000048150283,0.0008504817,0.00039846302,0.00050637807,0.0003466879],"domain_scores_gemma":[0.9962758,0.00019313696,0.00029713873,0.0024356763,0.00068465207,0.00011360704],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013355829,0.0002569746,0.0002752978,0.0014064724,0.0009894116,0.0010775593,0.0037587837,0.00018172686,0.000010329616],"category_scores_gemma":[0.00007734248,0.00028547723,0.000057635163,0.00092479936,0.0007800149,0.013105939,0.0028216639,0.00057524524,0.000046020825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020496482,0.000026833663,0.000035865392,0.00005307792,0.000006439378,8.781449e-7,0.001990971,0.008420208,0.000006585501,0.7167402,0.0006420813,0.27207482],"study_design_scores_gemma":[0.00008340806,0.000030462435,0.00014583502,0.00022808556,0.0000053821345,0.00001766474,0.000038076694,0.9027919,0.000041565338,0.009873782,0.08650575,0.00023805273],"about_ca_topic_score_codex":0.00003677665,"about_ca_topic_score_gemma":0.000023588782,"teacher_disagreement_score":0.89437175,"about_ca_system_score_codex":0.0004198651,"about_ca_system_score_gemma":0.0007697685,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W4410478524","doi":"10.26434/chemrxiv-2024-bpd53-v3","title":"Leveraging our Teacher’s Experience to Improve Machine Learning: Application to pKa Prediction","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; Compute Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Mathematics education; Psychology","score_opus":0.032055462620229146,"score_gpt":0.30482587793324545,"score_spread":0.2727704153130163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410478524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061346117,0.00007766702,0.928758,0.004048569,0.0013060976,0.0011213501,0.0000032598764,0.00072677986,0.0026121323],"genre_scores_gemma":[0.9656919,0.000017372537,0.025545444,0.0007226889,0.00037720837,0.00128037,0.000023892979,0.000026204556,0.006314875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967949,0.000084537394,0.00052962056,0.0016154129,0.00043622058,0.00053934497],"domain_scores_gemma":[0.99755883,0.000044553333,0.00019708759,0.001631713,0.00027003046,0.0002978038],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058778276,0.0003914878,0.00034618692,0.00033904176,0.00026876645,0.00040797621,0.002268868,0.00026133496,0.000010779555],"category_scores_gemma":[0.00041021005,0.0004408211,0.00012390398,0.0007913611,0.000019223167,0.00029490088,0.002860646,0.0008968117,0.0002957119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094015544,0.00062911835,0.010312398,0.00062186806,0.00014254052,0.000032420387,0.08791854,0.18876824,0.24834132,0.011641123,0.007536042,0.44396237],"study_design_scores_gemma":[0.0000894438,0.000112689806,0.0006195897,0.00022088792,0.00001803459,0.000003526214,0.0013261446,0.568535,0.3926718,0.0029966717,0.032646187,0.000760032],"about_ca_topic_score_codex":0.0005935531,"about_ca_topic_score_gemma":0.000023688683,"teacher_disagreement_score":0.9043458,"about_ca_system_score_codex":0.0004477342,"about_ca_system_score_gemma":0.00020361887,"threshold_uncertainty_score":0.9998044},"labels":[],"label_agreement":null},{"id":"W4410529380","doi":"10.2139/ssrn.5257280","title":"Mitigating Data Center Bias in Cancer Classification: Transfer Bias Unlearning and Feature Size Reduction Via Conflict-of-Interest Free Multi-Objectiveoptimization","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Ontario Institute of Technology","funders":"","keywords":"Feature (linguistics); Transfer (computing); Reduction (mathematics); Center (category theory); Cancer; Computer science; Statistics; Mathematics; Chemistry; Medicine; Crystallography; Internal medicine; Philosophy","score_opus":0.1787134963249332,"score_gpt":0.3531412666520983,"score_spread":0.17442777032716508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410529380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08093666,0.004297175,0.908723,0.004114089,0.0010916452,0.0005710636,0.000046957935,0.00007541742,0.00014400278],"genre_scores_gemma":[0.9754224,0.009993898,0.013465257,0.00006202451,0.0002685509,0.000034668094,0.000052808868,0.000029752153,0.00067063404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962151,0.00054305955,0.0007778234,0.00095181307,0.00030502473,0.0012071715],"domain_scores_gemma":[0.99765855,0.00024744926,0.0004912005,0.0010987698,0.00041492275,0.000089129164],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024673839,0.00035289288,0.00044720687,0.0004065409,0.0002702166,0.00031803656,0.0020980195,0.00036522697,0.0000107381065],"category_scores_gemma":[0.000664473,0.00035957014,0.00010237438,0.0006206456,0.00011860869,0.0008657847,0.0009147179,0.004475015,0.0000014324494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005779147,0.0015016444,0.034253605,0.0011705649,0.00192148,0.000047351656,0.035208628,0.1342415,0.020104267,0.22080792,0.00062898675,0.5495361],"study_design_scores_gemma":[0.0015679735,0.00027894884,0.0034678676,0.0024922309,0.00013618666,0.00035270824,0.0065103974,0.9264718,0.009157418,0.04791227,0.0006387466,0.0010134343],"about_ca_topic_score_codex":0.0011431244,"about_ca_topic_score_gemma":0.008374603,"teacher_disagreement_score":0.8952577,"about_ca_system_score_codex":0.0011236921,"about_ca_system_score_gemma":0.0026920415,"threshold_uncertainty_score":0.9998856},"labels":[],"label_agreement":null},{"id":"W4410779587","doi":"10.1080/17483107.2025.2507684","title":"Towards inclusive explainable artificial intelligence: a thematic analysis and scoping review on tools for persons with disabilities","year":2025,"lang":"en","type":"article","venue":"Disability and Rehabilitation Assistive Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Thematic analysis; Psychology; Assistive technology; Inclusion (mineral); Learning disability; Applied psychology; Computer science; Developmental psychology; Human–computer interaction; Qualitative research; Sociology; Social psychology","score_opus":0.03324337348501218,"score_gpt":0.3535082027358191,"score_spread":0.32026482925080696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410779587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15594825,0.0016369394,0.7901283,0.047730744,0.00007747052,0.0035511348,0.000026412017,0.00030236636,0.0005983931],"genre_scores_gemma":[0.9529964,0.00020805953,0.04480715,0.00035591619,0.00001057595,0.0015661772,0.000008472991,0.00000888156,0.00003837622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975492,0.00022184018,0.0006525495,0.0009853094,0.00021777653,0.00037335747],"domain_scores_gemma":[0.9928578,0.0057182275,0.00017929079,0.00079334417,0.0003795211,0.000071810384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012085089,0.00027918207,0.00069680955,0.00046452865,0.0005882768,0.00019027544,0.00041488573,0.00016903663,0.000016027021],"category_scores_gemma":[0.009328588,0.00022035063,0.0001502433,0.002625341,0.002331071,0.00056895654,0.00029127992,0.00020791667,0.000002897382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009827165,0.0004072203,0.012847333,0.006163682,0.00020076163,8.276776e-7,0.0018227275,0.00008404443,0.0000345124,0.7679959,0.000021309384,0.2103234],"study_design_scores_gemma":[0.00038367894,0.0044854917,0.026579853,0.027656138,0.0010566885,0.000009655475,0.1146882,0.026168877,0.006565362,0.7909083,0.00014019891,0.0013575832],"about_ca_topic_score_codex":0.00005636979,"about_ca_topic_score_gemma":0.00045396463,"teacher_disagreement_score":0.79704815,"about_ca_system_score_codex":0.00024930626,"about_ca_system_score_gemma":0.00016953085,"threshold_uncertainty_score":0.9990163},"labels":[],"label_agreement":null},{"id":"W4410941362","doi":"10.1007/978-3-031-92578-8_8","title":"User-Centered Trustworthy AI Metrics in the Metaverse","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Trustworthiness; Computer science; Metaverse; Human–computer interaction; World Wide Web; Artificial intelligence; Data science; Computer security; Virtual reality","score_opus":0.029542235487232324,"score_gpt":0.27834485297094075,"score_spread":0.2488026174837084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410941362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000086821514,0.0005033747,0.9856859,0.0033623567,0.00222586,0.0006842156,0.000005196766,0.000118671254,0.007327643],"genre_scores_gemma":[0.49224573,0.00045473676,0.46296093,0.039272934,0.0009826533,0.000089989706,0.000017056012,0.0000973743,0.003878595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99469537,0.0001587253,0.0008413115,0.0017952448,0.001500572,0.0010088081],"domain_scores_gemma":[0.99525297,0.0015015305,0.00028764812,0.0024854024,0.00034134559,0.00013108627],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002611364,0.000626128,0.00066452555,0.0023854345,0.0003310593,0.0011590943,0.008562728,0.00036208163,0.000031828895],"category_scores_gemma":[0.00048056254,0.0004892183,0.0002302271,0.0040367306,0.0006474565,0.0010648415,0.0018644991,0.0015325552,0.00010402804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013053814,0.00011856204,0.00030945177,0.000054808675,0.00002354412,0.00052409084,0.0027231674,0.03518911,0.000029717125,0.25555888,0.00039235072,0.7050633],"study_design_scores_gemma":[0.0003139333,0.00023761297,0.00019046551,0.0005020498,0.000026634956,0.000065402965,0.0000046394744,0.6721565,0.0026247634,0.28603327,0.036721326,0.0011233906],"about_ca_topic_score_codex":0.000164767,"about_ca_topic_score_gemma":0.0008261149,"teacher_disagreement_score":0.70393986,"about_ca_system_score_codex":0.00047696967,"about_ca_system_score_gemma":0.00083113654,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W4410987418","doi":"10.1080/00330124.2025.2478075","title":"Generative AI in Undergraduate Education: An Early View of Developments, Prospects, and Challenges of the AI Revolution","year":2025,"lang":"en","type":"article","venue":"The Professional Geographer","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Okanagan College; Simon Fraser University","funders":"","keywords":"Generative grammar; Engineering ethics; Artificial intelligence; Mathematics education; Political science; Sociology; Engineering; Computer science; Psychology","score_opus":0.023114739807746167,"score_gpt":0.307659104524953,"score_spread":0.28454436471720684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410987418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7744487,0.034234855,0.0102256695,0.1716376,0.002147579,0.002293951,0.00000384758,0.0000659667,0.0049418393],"genre_scores_gemma":[0.994779,0.0007932549,0.0023186668,0.0008964453,0.00001519448,0.0000815448,5.950593e-7,0.000004031023,0.0011112603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987926,0.00031443482,0.00028437588,0.00023276825,0.00022383292,0.00015199734],"domain_scores_gemma":[0.9991683,0.00006938431,0.00012302234,0.00038843625,0.00022693843,0.000023950217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049123296,0.00009925181,0.00013415488,0.000103939215,0.00017456118,0.000020491982,0.0006022912,0.000048646536,0.000005102108],"category_scores_gemma":[0.000032834294,0.000057706617,0.000034518904,0.00080322084,0.0001886699,0.00031489067,0.00029881566,0.00016777466,0.0000015428972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014116697,0.0002587755,0.028988902,0.00009313883,0.000023519096,1.9836149e-7,0.0032444082,0.000023323279,0.0010170471,0.9204242,0.00020296311,0.045709364],"study_design_scores_gemma":[0.00011170679,0.000054130636,0.5610106,0.0007111963,0.000008507181,0.0000011554972,0.0011186989,0.0008548373,0.011841141,0.42300984,0.0011554216,0.00012273762],"about_ca_topic_score_codex":0.00015207121,"about_ca_topic_score_gemma":0.00029720285,"teacher_disagreement_score":0.5320217,"about_ca_system_score_codex":0.000022559032,"about_ca_system_score_gemma":0.00042266352,"threshold_uncertainty_score":0.23532075},"labels":[],"label_agreement":null},{"id":"W4411448155","doi":"10.1007/978-981-96-2124-8_4","title":"Enhancing AI Capabilities to Improve Cybersecurity","year":2025,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Becton Dickinson (Canada)","funders":"","keywords":"Computer security; Computer science","score_opus":0.016162437667236455,"score_gpt":0.24999222262198123,"score_spread":0.23382978495474477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411448155","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028935743,0.0061119013,0.62051064,0.017930998,0.008550764,0.004558487,0.00014771253,0.008589431,0.3307065],"genre_scores_gemma":[0.39919862,0.0005030666,0.014767668,0.0012588318,0.00038133646,0.00077272934,0.000041395113,0.00010005907,0.5829763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753594,0.000015773683,0.0009068421,0.0008464341,0.00031470155,0.00038031684],"domain_scores_gemma":[0.9971854,0.00015273379,0.00031002946,0.0012254623,0.0010987597,0.000027580227],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006658998,0.00040939907,0.0005402602,0.0012123985,0.00030691767,0.00046044405,0.0009504135,0.0005988039,0.0000049139276],"category_scores_gemma":[0.00056598266,0.000381222,0.00005359391,0.00075271993,0.0002145183,0.00046088177,0.0009122997,0.00049153174,0.000050490944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017021333,0.0000058349247,0.00003332225,0.00025627704,0.000033800607,0.000005968297,0.00032960318,0.0000034522327,0.0004558136,0.976935,0.003829445,0.01810976],"study_design_scores_gemma":[0.000059021295,0.00017302258,0.000009524049,0.00089065614,0.000013798325,0.000013555885,0.0020433904,0.00043018284,0.022855856,0.5001258,0.47266993,0.00071523443],"about_ca_topic_score_codex":0.0004829484,"about_ca_topic_score_gemma":0.00027258822,"teacher_disagreement_score":0.60574293,"about_ca_system_score_codex":0.00018701731,"about_ca_system_score_gemma":0.00022455175,"threshold_uncertainty_score":0.999864},"labels":[],"label_agreement":null},{"id":"W4411534299","doi":"10.1145/3698061.3728392","title":"Explainable AI for the Arts 3 (XAIxArts3)","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; The arts; Artificial intelligence; Visual arts; Art","score_opus":0.02823487514792491,"score_gpt":0.31793263124887566,"score_spread":0.2896977561009508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411534299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019213496,0.00023205928,0.92192703,0.035801943,0.00081333943,0.0005003716,6.4248013e-7,0.00022628435,0.040306166],"genre_scores_gemma":[0.78392535,0.000057107758,0.06020701,0.032655995,0.00023795836,0.0008462794,0.0000020862967,0.000022729573,0.122045465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987504,0.000026105054,0.0002394046,0.0003752807,0.00016217181,0.0004466781],"domain_scores_gemma":[0.9980759,0.0007055119,0.000037836544,0.0009233399,0.00020658357,0.00005082381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056492933,0.00012880214,0.00012561906,0.00010338662,0.0005623861,0.00040695953,0.0013927368,0.00005184171,0.000066797766],"category_scores_gemma":[0.00020946715,0.00008717324,0.00009660807,0.00061318226,0.00006534191,0.0006089055,0.00030768407,0.0001055254,0.00017541129],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004881173,0.000028068976,0.000030692845,0.000009992753,0.000013263796,0.0000023279101,0.00021653758,0.0004065126,0.00025059495,0.8835369,0.080297805,0.03520247],"study_design_scores_gemma":[0.00008670582,0.000046384528,0.00004948055,0.000013113402,0.000007350062,0.000002308679,0.00044881259,0.15787943,0.07186175,0.16809584,0.6013718,0.00013700353],"about_ca_topic_score_codex":0.00015906623,"about_ca_topic_score_gemma":0.00013034104,"teacher_disagreement_score":0.86172,"about_ca_system_score_codex":0.000049887843,"about_ca_system_score_gemma":0.00013103918,"threshold_uncertainty_score":0.4325476},"labels":[],"label_agreement":null},{"id":"W4411599948","doi":"10.1109/mnet.2025.3582407","title":"Chain-of-Trust: A Progressive Trust Evaluation Framework Enabled by Generative AI","year":2025,"lang":"en","type":"article","venue":"IEEE Network","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Computer science; Chain (unit); Artificial intelligence","score_opus":0.022427336815485425,"score_gpt":0.3204009277819989,"score_spread":0.2979735909665135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411599948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03248851,0.0033917148,0.94823056,0.0025995064,0.0063167843,0.0013657033,0.000004415087,0.00020078095,0.005402009],"genre_scores_gemma":[0.9554997,0.000060097358,0.035903927,0.003977582,0.0021647676,0.00060305046,0.000012678784,0.000030078343,0.0017481192],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972341,0.00038482877,0.00052698975,0.0006433882,0.00058767706,0.0006229882],"domain_scores_gemma":[0.9977615,0.00038430144,0.00027095564,0.0008520083,0.0006324595,0.000098795994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011681614,0.0002527338,0.00034552158,0.00012689873,0.00033447638,0.00021226022,0.0010270681,0.0002246109,0.000053629927],"category_scores_gemma":[0.00029529285,0.00024510373,0.000109114626,0.001880328,0.00013867089,0.00045031167,0.00016998654,0.0003652311,0.000055470216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017211877,0.00046337934,0.0023328664,0.000091179216,0.00032701716,0.000040053554,0.006257478,0.16650024,0.003012094,0.29241726,0.39157176,0.13681455],"study_design_scores_gemma":[0.0002710303,0.00021042183,0.00015907684,0.00037313264,0.00005595592,0.000002909114,0.00016310593,0.561538,0.09561961,0.32682618,0.0143747805,0.00040577468],"about_ca_topic_score_codex":0.000037733367,"about_ca_topic_score_gemma":0.000016253716,"teacher_disagreement_score":0.9230112,"about_ca_system_score_codex":0.00017031147,"about_ca_system_score_gemma":0.00037810783,"threshold_uncertainty_score":0.999504},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Generative grammar; Harm; Computer science; Artificial intelligence; TUTOR; Productivity; Machine learning; Psychology; Social psychology","score_opus":0.06691070461142205,"score_gpt":0.34903961635866027,"score_spread":0.2821289117472382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411627694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92729086,0.00038495206,0.0064977217,0.059114866,0.0001438095,0.0005565066,0.000010001706,0.000100206664,0.0059010736],"genre_scores_gemma":[0.95301574,0.00003746061,0.044882935,0.0011270965,0.00006492039,0.00002064545,6.259768e-8,0.0000035070525,0.00084760465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997315,0.000022771717,0.00051608006,0.00047195764,0.0014244815,0.0002497434],"domain_scores_gemma":[0.9980874,0.0004641439,0.0005323322,0.000030780255,0.0008249636,0.000060354327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017695555,0.00015049808,0.0002409024,0.0002575573,0.00045224975,0.00022285614,0.0030689805,0.00009334527,0.000020743704],"category_scores_gemma":[0.0036618891,0.00010726644,0.00008080063,0.0018267599,0.0007576513,0.0015752788,0.0005914354,0.00036208358,0.000009357683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008134942,0.000068257075,0.012965401,0.0000620997,0.00003867902,2.5363782e-8,0.0022060461,0.0020954225,0.3386229,0.64138585,0.0016788399,0.00086835946],"study_design_scores_gemma":[0.00004483434,0.000033540833,0.0072334297,0.000318997,0.000009334774,0.0000011335266,0.0004211312,0.037885472,0.62125015,0.3326238,0.00008407104,0.00009405284],"about_ca_topic_score_codex":0.00012140106,"about_ca_topic_score_gemma":0.0000010983613,"teacher_disagreement_score":0.308762,"about_ca_system_score_codex":0.000107104424,"about_ca_system_score_gemma":0.00023047715,"threshold_uncertainty_score":0.570298},"labels":[],"label_agreement":null},{"id":"W4411724417","doi":"10.2196/66200","title":"A Responsible Framework for Assessing, Selecting, and Explaining Machine Learning Models in Cardiovascular Disease Outcomes Among People With Type 2 Diabetes: Methodology and Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Random forest; Population; Predictive modelling; Decision tree; Medicine","score_opus":0.06321971599335918,"score_gpt":0.36083763451017237,"score_spread":0.2976179185168132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411724417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5085503,0.00013220646,0.49064246,0.00011291544,0.000051926,0.00041440135,2.6320927e-7,0.00005578654,0.00003974497],"genre_scores_gemma":[0.8665985,0.000026794012,0.13293245,0.00020753179,0.000011390624,0.00018861471,0.000003708236,0.000009183065,0.000021803206],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801964,0.000414413,0.0005049383,0.00024954777,0.0004593581,0.0003521159],"domain_scores_gemma":[0.99696565,0.0022288768,0.00013886612,0.00035297673,0.00013337267,0.00018026387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034434278,0.00017173395,0.00044930604,0.0003153007,0.00024499698,0.0002824223,0.00030996633,0.00012681795,0.000002661454],"category_scores_gemma":[0.003508516,0.00013940423,0.00004374644,0.00083690096,0.000084848245,0.0011702877,0.0002969645,0.000457006,6.5982914e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006423727,0.00013854218,0.89168686,0.0003260973,0.00023118638,0.000013787725,0.041233394,0.014553604,0.000001612283,0.017966377,0.000012904309,0.03377139],"study_design_scores_gemma":[0.000433265,0.00021490322,0.028812086,0.0002525712,0.00005242557,0.000001753486,0.0073072705,0.9499367,0.00006624674,0.01267752,0.000063659245,0.0001816384],"about_ca_topic_score_codex":0.00008496558,"about_ca_topic_score_gemma":0.00010365068,"teacher_disagreement_score":0.9353831,"about_ca_system_score_codex":0.00004357413,"about_ca_system_score_gemma":0.0002624484,"threshold_uncertainty_score":0.568474},"labels":[],"label_agreement":null},{"id":"W4412494397","doi":"10.1177/10711813251358254","title":"Inverse Counterfactual for AI-Assisted Decision Support: Enhancing Knowledge Elicitation for Capturing Aircraft Pilot Decisions","year":2025,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada); Université Laval","funders":"Mitacs","keywords":"Counterfactual thinking; Inverse; Computer science; Decision support system; Operations research; Artificial intelligence; Human–computer interaction; Engineering; Psychology; Mathematics; Social psychology","score_opus":0.03608528499541347,"score_gpt":0.29847489038652264,"score_spread":0.26238960539110917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412494397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88962317,0.00004468277,0.10887033,0.00018988003,0.00042297904,0.0005883179,0.000026587048,0.000064089494,0.00016998852],"genre_scores_gemma":[0.96842676,0.000018395898,0.030991651,0.00023295525,0.000068230416,0.00005220576,0.0000034840104,0.000019101766,0.00018718898],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99831635,0.000008022602,0.0006380966,0.0004945957,0.00013988808,0.00040302752],"domain_scores_gemma":[0.9975468,0.0010887607,0.00034981687,0.00016221135,0.00077417376,0.000078239515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010088724,0.00023782384,0.00031357433,0.00010249435,0.001231338,0.0002905704,0.0007846953,0.00011878777,0.0000010573593],"category_scores_gemma":[0.0009359537,0.00019826338,0.00027400316,0.00027911455,0.00012555592,0.00087828573,0.00051335234,0.00015582221,7.1306715e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075838016,0.0009488699,0.02067778,0.0019103981,0.0006099035,1.9922604e-7,0.25365418,0.0020867933,0.4407565,0.18714653,0.052231107,0.03921934],"study_design_scores_gemma":[0.0020391368,0.00110767,0.011416535,0.0020332648,0.00022720362,0.0000033707684,0.06565129,0.14453205,0.7065281,0.056201927,0.009025157,0.0012342389],"about_ca_topic_score_codex":0.000058993108,"about_ca_topic_score_gemma":0.00018379294,"teacher_disagreement_score":0.26577163,"about_ca_system_score_codex":0.00020360255,"about_ca_system_score_gemma":0.00011409327,"threshold_uncertainty_score":0.9470581},"labels":[],"label_agreement":null},{"id":"W4412505466","doi":"10.1016/j.system.2025.103784","title":"Automated scoring in the era of artificial intelligence: An empirical study with Turkish essays","year":2025,"lang":"en","type":"article","venue":"System","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Leuphana Universität Lüneburg","keywords":"Turkish; Artificial intelligence; Computer science; Empirical research; Natural language processing; Mathematics education; Psychology; Linguistics; Statistics; Mathematics; Philosophy","score_opus":0.04233942530495005,"score_gpt":0.3434102288782708,"score_spread":0.3010708035733207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412505466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8097694,0.000039306036,0.1855207,0.00035908504,0.00039440024,0.000900202,9.847431e-7,0.00043715973,0.0025787964],"genre_scores_gemma":[0.99801135,5.1221025e-7,0.001767682,0.00007230485,0.000039529637,0.000082967934,6.58323e-7,0.000007917981,0.000017077598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739707,0.00058797374,0.0006707735,0.0005006471,0.0004896128,0.00035389996],"domain_scores_gemma":[0.99837357,0.00023941672,0.00013875008,0.0010146269,0.0001846455,0.00004899154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017983464,0.00017709701,0.00030999575,0.0002215883,0.00016862655,0.00025165855,0.0016281679,0.00005753729,0.0000025467193],"category_scores_gemma":[0.00006814057,0.00011933529,0.00004163153,0.0022971928,0.00008128235,0.0004464181,0.00017623811,0.00029768958,0.00002511009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025735324,0.0035133895,0.11810152,0.0005518548,0.00015390824,0.0009580637,0.09372596,0.025145527,0.0010242837,0.6816358,0.00032223546,0.07461009],"study_design_scores_gemma":[0.0001465777,0.0013175227,0.014465846,0.00070169976,0.00003008563,0.000046005418,0.12519774,0.8380796,0.015000395,0.00455941,0.000047061345,0.00040808963],"about_ca_topic_score_codex":0.0007655458,"about_ca_topic_score_gemma":0.0011510542,"teacher_disagreement_score":0.81293404,"about_ca_system_score_codex":0.00011925617,"about_ca_system_score_gemma":0.00020243599,"threshold_uncertainty_score":0.48663518},"labels":[],"label_agreement":null},{"id":"W4412604524","doi":"10.2196/64482","title":"The Right to Explanation in AI: In a Lonely Place","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Preprint; Psychology; World Wide Web; Computer science","score_opus":0.060514001336983446,"score_gpt":0.44444921087689493,"score_spread":0.3839352095399115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412604524","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35332638,0.0009528313,0.22915483,0.4071739,0.001512996,0.00043336087,2.5731046e-7,0.000017115748,0.007428354],"genre_scores_gemma":[0.9957642,0.00017074426,0.00046618585,0.0011448343,0.00009610116,0.0000148984645,1.0125405e-7,0.0000038502744,0.0023391007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955524,0.0007419536,0.0007405423,0.0002060769,0.0022702124,0.0004887663],"domain_scores_gemma":[0.9967528,0.0021747602,0.00007225249,0.00029600484,0.0004746662,0.00022953223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015654664,0.000075666794,0.00018007164,0.0010517918,0.00006261222,0.00032928606,0.0032628006,0.000118169846,0.000078373334],"category_scores_gemma":[0.0063734674,0.000048822694,0.0000474354,0.0018788562,0.00012844571,0.00037633828,0.0006592277,0.0015903761,0.00008848464],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049256894,0.0005722468,0.0031112365,0.000044224398,0.00004203662,0.0031261449,0.007106063,0.0005256683,0.0006733726,0.47811034,0.26233482,0.24386127],"study_design_scores_gemma":[0.001400898,0.0012499958,0.009051548,0.0031556129,0.0000032864439,0.00020507879,0.0030708197,0.43174165,0.037178673,0.114671,0.3979564,0.00031503307],"about_ca_topic_score_codex":0.0007224266,"about_ca_topic_score_gemma":0.006319528,"teacher_disagreement_score":0.6424378,"about_ca_system_score_codex":0.0004316373,"about_ca_system_score_gemma":0.0007645172,"threshold_uncertainty_score":0.76300967},"labels":[],"label_agreement":null},{"id":"W4412703901","doi":"10.1145/3696630.3728522","title":"Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hessian matrix; Computer science; Fault (geology); Artificial intelligence; Machine learning; Geology; Mathematics; Applied mathematics","score_opus":0.02732413311328661,"score_gpt":0.2758546596971958,"score_spread":0.2485305265839092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412703901","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0984393,0.000059534534,0.86063373,0.01444847,0.0004751899,0.00047910973,0.0000035401265,0.00036886008,0.02509225],"genre_scores_gemma":[0.9850065,0.0000066477396,0.009285059,0.004099212,0.00001622941,0.00024453286,0.000010717171,0.000011034967,0.0013200686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978093,0.00012347099,0.0005089019,0.00068469264,0.00036298748,0.00051066786],"domain_scores_gemma":[0.99840933,0.00033893887,0.00008033855,0.0008645274,0.00017818826,0.00012868892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002947499,0.0002305557,0.00026002628,0.0006176934,0.0001754464,0.0002565239,0.0011448221,0.00012367328,0.00010526381],"category_scores_gemma":[0.00007743405,0.00021647387,0.00011844685,0.0016761838,0.00007854474,0.00060806295,0.00012775816,0.00019460426,0.00011882068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002734915,0.0010787762,0.053449478,0.00010787584,0.000029292903,0.000263112,0.0007349502,0.17231664,0.00083056296,0.7368367,0.0064620725,0.027863234],"study_design_scores_gemma":[0.00027635734,0.00006517598,0.0025367716,0.00009048527,0.000005931722,3.1805746e-7,0.00014584321,0.9292612,0.030967591,0.03518688,0.0011771411,0.00028629426],"about_ca_topic_score_codex":0.0024988195,"about_ca_topic_score_gemma":0.0075600757,"teacher_disagreement_score":0.8865672,"about_ca_system_score_codex":0.00023093726,"about_ca_system_score_gemma":0.00067706936,"threshold_uncertainty_score":0.88275486},"labels":[],"label_agreement":null},{"id":"W4412819187","doi":"10.1016/j.fsidi.2025.301924","title":"Bridging knowledge gaps in digital forensics using unsupervised explainable AI","year":2025,"lang":"en","type":"article","venue":"Forensic Science International Digital Investigation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Zayed University","keywords":"Bridging (networking); Computer science; Digital forensics; Data science; Computer security","score_opus":0.030857431709078568,"score_gpt":0.30428076468537685,"score_spread":0.2734233329762983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412819187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63267165,0.0000618911,0.33313006,0.0018216018,0.0022169403,0.00032232748,0.000013903528,0.0001997424,0.029561896],"genre_scores_gemma":[0.9917103,0.0000031645557,0.006483924,0.0006916614,0.00009663503,0.000020973113,0.00003052732,0.000012620405,0.0009502029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969709,0.000018762694,0.0006643395,0.0008771127,0.0008097862,0.0006591363],"domain_scores_gemma":[0.9979677,0.00014084202,0.00015644256,0.0005359016,0.0010121807,0.0001868839],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0006177376,0.00026720544,0.00021994942,0.0013321183,0.00034294123,0.0034353088,0.0019242206,0.000084059415,0.000009369897],"category_scores_gemma":[0.0015152079,0.00028525127,0.00009083961,0.0038260939,0.0010422405,0.0145418,0.0008267973,0.00024124362,0.00013043563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017647699,0.0001286323,0.026297376,0.00003299541,0.000021672553,0.000040134277,0.0020813243,0.0086287325,0.007160324,0.80027634,0.0010779243,0.1542369],"study_design_scores_gemma":[0.00019069742,0.000032367665,0.0022039476,0.00024611095,0.0000026802816,0.000019508068,0.00030924086,0.6924771,0.054443136,0.24908534,0.0007050755,0.00028481844],"about_ca_topic_score_codex":0.00016264891,"about_ca_topic_score_gemma":0.000054798642,"teacher_disagreement_score":0.6838484,"about_ca_system_score_codex":0.00090787385,"about_ca_system_score_gemma":0.0009731132,"threshold_uncertainty_score":0.99995995},"labels":[],"label_agreement":null},{"id":"W4412874171","doi":"10.1007/978-3-031-98459-4_5","title":"Math Education With Large Language Models: Peril or Promise?","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Mathematics education; Programming language; Theoretical computer science; Mathematics","score_opus":0.018829410463367082,"score_gpt":0.272015009528283,"score_spread":0.25318559906491594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412874171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015077273,0.00051172957,0.9779186,0.00080144114,0.0010897238,0.00078547996,0.0000065760323,0.00023334003,0.018502291],"genre_scores_gemma":[0.16030963,0.000091052934,0.8137011,0.0050263754,0.0007143018,0.00016379429,0.000015861957,0.00007582555,0.019902054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620026,0.000036520887,0.00044924265,0.001609345,0.00087881734,0.00082578795],"domain_scores_gemma":[0.9972021,0.00027124974,0.0002354307,0.0017294595,0.0003824422,0.00017930233],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007341769,0.0005260151,0.0004635518,0.0008228536,0.00033196027,0.0007905732,0.0033697437,0.00025764745,0.00003635058],"category_scores_gemma":[0.000096945165,0.0003960748,0.00008291051,0.0010147466,0.00037147856,0.0011885702,0.0011027959,0.00065871683,0.000046330675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026437412,0.00010518012,0.000011267526,0.00010124811,0.000011861874,0.00011523424,0.0040740226,0.014485475,0.000033092554,0.33897492,0.00007460669,0.64198667],"study_design_scores_gemma":[0.0001431676,0.00021349605,0.000011021982,0.00079384807,0.000011778356,0.00007909794,0.000008044095,0.8493162,0.0020288532,0.14379993,0.0028796666,0.0007149172],"about_ca_topic_score_codex":0.00008788573,"about_ca_topic_score_gemma":0.0006163591,"teacher_disagreement_score":0.8348307,"about_ca_system_score_codex":0.0004406617,"about_ca_system_score_gemma":0.003259305,"threshold_uncertainty_score":0.99984914},"labels":[],"label_agreement":null},{"id":"W4412906363","doi":"10.1007/978-3-031-98284-2_13","title":"Neuromorphic Knowledge Representation: SNN-Based Relational Inference and Explainability in Knowledge Graphs","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University; Athabasca University","funders":"","keywords":"Neuromorphic engineering; Computer science; Inference; Knowledge representation and reasoning; Representation (politics); Knowledge graph; Artificial intelligence; Artificial neural network","score_opus":0.05698086356223504,"score_gpt":0.30898778781963887,"score_spread":0.25200692425740384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412906363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013912029,0.0012173839,0.9867207,0.0012262487,0.0013235807,0.00070980715,0.000005165379,0.00015552672,0.0072504226],"genre_scores_gemma":[0.9022758,0.00007451408,0.096171744,0.000650318,0.0001522177,0.000062867344,0.000010032891,0.000028536806,0.00057397655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951988,0.0002015538,0.0009121976,0.0023090974,0.0006636563,0.00071471446],"domain_scores_gemma":[0.99389106,0.0033923269,0.00027099097,0.0016193938,0.00062686467,0.0001993899],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015435278,0.00058597216,0.0006209716,0.0019028742,0.00037134887,0.0004777072,0.002418226,0.00038632264,0.000026310669],"category_scores_gemma":[0.0010155044,0.0006115343,0.00012407308,0.0023786074,0.001310399,0.0009878884,0.0014742573,0.0011427708,0.000038586382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021877147,0.00019080844,0.0047636153,0.00018246216,0.000008543881,0.00013477913,0.0025987322,0.038300183,0.0001000991,0.6384239,0.000037231828,0.31523776],"study_design_scores_gemma":[0.00018907805,0.00011004024,0.0026123736,0.00044976868,0.0000048892034,0.000011902602,8.2720703e-7,0.6240407,0.0011753103,0.37054372,0.0003791277,0.0004822736],"about_ca_topic_score_codex":0.00009087261,"about_ca_topic_score_gemma":0.0010150212,"teacher_disagreement_score":0.90088457,"about_ca_system_score_codex":0.00046232328,"about_ca_system_score_gemma":0.00196591,"threshold_uncertainty_score":0.9996336},"labels":[],"label_agreement":null},{"id":"W4413069729","doi":"10.1007/978-3-031-98414-3_29","title":"Personalizing Explanations of AI-Driven Hints to Users’ Characteristics: An Empirical Evaluation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Empirical research; Human–computer interaction; Information retrieval; Epistemology","score_opus":0.06512646958833557,"score_gpt":0.3558005587983916,"score_spread":0.29067408921005605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413069729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019729908,0.000050966544,0.992395,0.0021604586,0.001317509,0.0006409738,0.000016193408,0.00009218202,0.0013537196],"genre_scores_gemma":[0.6581281,0.000012012258,0.33661577,0.004497362,0.00036306563,0.00004052186,0.000028253184,0.000030091087,0.00028484056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995687,0.00013319551,0.00071630976,0.00141549,0.0015146983,0.000533294],"domain_scores_gemma":[0.996352,0.0006019586,0.0002853504,0.0013381689,0.0011985566,0.00022397416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018561247,0.00039815964,0.00051429734,0.0013908084,0.00027340697,0.0004299666,0.0030717955,0.0002534962,0.000059034963],"category_scores_gemma":[0.000568376,0.00040608668,0.00011223312,0.0010377789,0.00033172403,0.0009897659,0.00074030075,0.0005744759,0.00004856637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021514443,0.00012386813,0.0013352504,0.00007549613,0.000028335311,0.00004697687,0.012667557,0.05464603,0.001510585,0.04876282,0.00014659224,0.88063496],"study_design_scores_gemma":[0.000086214626,0.00022606022,0.0011228059,0.0004754078,0.00001831246,0.000010926223,0.0000031160944,0.94142884,0.004329453,0.05116665,0.0006475451,0.0004846683],"about_ca_topic_score_codex":0.00007195498,"about_ca_topic_score_gemma":0.00025211487,"teacher_disagreement_score":0.8867828,"about_ca_system_score_codex":0.0005917292,"about_ca_system_score_gemma":0.0013796091,"threshold_uncertainty_score":0.9998391},"labels":[],"label_agreement":null},{"id":"W4413123235","doi":"10.1002/9781394240821.ch11","title":"Explainability of Algorithms","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Algorithm","score_opus":0.03996740359971307,"score_gpt":0.31953589839239865,"score_spread":0.2795684947926856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413123235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002938603,0.0001598242,0.9405296,0.001139719,0.0012536681,0.00042257403,0.00001181869,0.00027397074,0.053270236],"genre_scores_gemma":[0.43932942,0.00010608555,0.5479133,0.00050007086,0.00014090232,0.0001895199,0.000011430553,0.000014974676,0.011794299],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997719,0.00012791717,0.00062063476,0.00083726115,0.00036638882,0.000328816],"domain_scores_gemma":[0.9967355,0.00024725313,0.00020737898,0.0022521038,0.00047598858,0.00008178304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007334247,0.00024715718,0.00043285845,0.00022626713,0.00006439925,0.00011152077,0.0028841547,0.00026178604,0.000065994325],"category_scores_gemma":[0.00025638874,0.00023656036,0.00021304179,0.000452124,0.00011252418,0.00023150812,0.0044052745,0.00042238808,0.0000407888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074507984,0.00032605306,0.000501896,0.0006680051,0.000066001325,0.000018963592,0.0021474115,0.0062855477,0.00012000079,0.850415,0.0030544964,0.1363892],"study_design_scores_gemma":[0.00006610479,0.000063514526,0.00032912358,0.00020518855,0.000016414637,0.0000021693525,0.00030884615,0.25442928,0.21839443,0.520303,0.005328767,0.00055317715],"about_ca_topic_score_codex":0.0010994468,"about_ca_topic_score_gemma":0.00006336185,"teacher_disagreement_score":0.43639082,"about_ca_system_score_codex":0.00012538982,"about_ca_system_score_gemma":0.00055567705,"threshold_uncertainty_score":0.9646652},"labels":[],"label_agreement":null},{"id":"W4413159440","doi":"10.1016/j.techsoc.2025.103039","title":"A decision architecture for epistemic prioritization: Machine learning at the intersection of technology and society","year":2025,"lang":"en","type":"article","venue":"Technology in Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Intersection (aeronautics); Prioritization; Architecture; Artificial intelligence; Computer science; Epistemology; Sociology; Management science; Engineering; Philosophy; History","score_opus":0.00782827762250512,"score_gpt":0.26972253970525367,"score_spread":0.2618942620827486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413159440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27650043,0.0010995752,0.706245,0.015298026,0.00013851335,0.00037384822,0.0000016487047,0.00025665216,0.00008627219],"genre_scores_gemma":[0.93166876,0.00018944633,0.06753346,0.000194931,0.000008893641,0.00009750043,0.0000018948011,0.0000074590503,0.0002976709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892193,0.000025893904,0.000315072,0.00039072445,0.000093232826,0.0002531169],"domain_scores_gemma":[0.9989986,0.0003163033,0.00012855163,0.00042375253,0.00012101955,0.000011786587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516236,0.00012584018,0.00020392054,0.0001961093,0.00032742033,0.000021386353,0.000630198,0.0004053874,0.0000023900127],"category_scores_gemma":[0.0002731209,0.000103352,0.000116898525,0.0023306026,0.0005871611,0.00008834327,0.0007226065,0.00048782802,0.0000013679673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031135045,0.00007326286,0.022951998,0.00013612892,0.00007973901,0.0000016140249,0.004957682,0.0012188894,0.043186594,0.58769995,0.0010677867,0.3385952],"study_design_scores_gemma":[0.00053757767,0.00022561126,0.00056890637,0.00021340341,0.000018126813,0.00004675814,0.0051244344,0.15942621,0.09174288,0.73367417,0.008218041,0.00020391606],"about_ca_topic_score_codex":0.000019363732,"about_ca_topic_score_gemma":0.00013953132,"teacher_disagreement_score":0.6551683,"about_ca_system_score_codex":0.00020658357,"about_ca_system_score_gemma":0.000058432004,"threshold_uncertainty_score":0.42145723},"labels":[],"label_agreement":null},{"id":"W4413298069","doi":"10.1007/978-3-031-92602-0_30","title":"Evaluation of Local Explainability Methods in Turkish Text Classification Tasks","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Turkish; Computer science; Artificial intelligence; Natural language processing; Linguistics; Philosophy","score_opus":0.06882309600957642,"score_gpt":0.35437643214738457,"score_spread":0.28555333613780814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413298069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008664561,0.01117929,0.96902186,0.00015240231,0.0009554132,0.0010597286,0.0000025716117,0.00003343379,0.01750863],"genre_scores_gemma":[0.993286,0.00024714114,0.005362408,0.0000622383,0.00017984756,0.00012550403,0.000016412714,0.000020999407,0.0006994618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962026,0.0009615284,0.0010580291,0.0008260002,0.00062474725,0.00032708893],"domain_scores_gemma":[0.996619,0.0014549078,0.00042290657,0.0008742731,0.00057174184,0.00005719737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0075208214,0.00033268868,0.0006898052,0.0003864238,0.000064929125,0.00012587261,0.00055484707,0.0007761233,0.000012166868],"category_scores_gemma":[0.00049405696,0.00031249545,0.000090445916,0.00036606158,0.00015577735,0.00018209068,0.00017860299,0.00067058986,0.0000015432397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010494427,0.000021147162,0.00013376947,0.0001472357,0.000020197622,0.0000037033465,0.00040539436,0.29585665,0.000023121254,0.089530654,0.000044912507,0.61380273],"study_design_scores_gemma":[0.00011652032,0.000049917653,0.0002138307,0.0007148524,0.000033210592,0.0000043041655,0.000045560904,0.9267866,0.000121467376,0.070236,0.0014327575,0.00024499398],"about_ca_topic_score_codex":0.00053501077,"about_ca_topic_score_gemma":0.0011518742,"teacher_disagreement_score":0.99319935,"about_ca_system_score_codex":0.0005303792,"about_ca_system_score_gemma":0.00027646933,"threshold_uncertainty_score":0.9999327},"labels":[],"label_agreement":null},{"id":"W4413360578","doi":"10.1109/sse67621.2025.00015","title":"XAIpipeline: Automated Orchestration of Explainable AI Services for Cloud AI and Open-source Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Orchestration; Cloud computing; Open source; Computer science; Data science; World Wide Web; Artificial intelligence; Operating system; Software","score_opus":0.0277955154908664,"score_gpt":0.32224598026560286,"score_spread":0.29445046477473646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413360578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013924818,0.000117278,0.97521937,0.004589181,0.00017309886,0.0007335259,0.000002896762,0.0004202546,0.0048195925],"genre_scores_gemma":[0.9446832,0.000023917755,0.04831292,0.002615678,0.00003117233,0.00009948385,0.000007794478,0.000011544082,0.004214275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985888,0.000049695533,0.00043836245,0.00045965952,0.00015539484,0.0003080982],"domain_scores_gemma":[0.99870765,0.00015744116,0.00010889048,0.0005211192,0.00043695862,0.0000679315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059714424,0.00015602657,0.0002520161,0.00015318287,0.00021050697,0.0005196327,0.0012188436,0.000098490375,0.000008631159],"category_scores_gemma":[0.000041721625,0.00014580209,0.00003947549,0.00063141034,0.00005027168,0.0022497522,0.00058822444,0.00008307141,0.000006534796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054051332,0.00014098137,0.00012439811,0.00032162695,0.000029359247,0.0000014203196,0.0015968151,0.04100431,0.004789608,0.9295362,0.00583123,0.016570002],"study_design_scores_gemma":[0.00018674809,0.000082590865,0.00001933977,0.000056975954,0.0000077819195,0.0000015337145,0.0005173541,0.8288871,0.08333768,0.08387783,0.0029001639,0.00012488675],"about_ca_topic_score_codex":0.0013119193,"about_ca_topic_score_gemma":0.0003070134,"teacher_disagreement_score":0.9307584,"about_ca_system_score_codex":0.00003601926,"about_ca_system_score_gemma":0.00018172913,"threshold_uncertainty_score":0.59456366},"labels":[],"label_agreement":null},{"id":"W4413405229","doi":"10.64628/aam.ccg3dc6ty","title":"Is AI coming for your creative job? Maybe not – with some human intervention","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Intervention (counseling); Business; Management; Psychology; Economics","score_opus":0.05667200901917933,"score_gpt":0.3686632251858567,"score_spread":0.31199121616667735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413405229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032751646,0.00002392738,0.95002526,0.00561846,0.00017427123,0.00040277635,0.0000028275947,0.0001629303,0.010837883],"genre_scores_gemma":[0.9353185,0.0000017866417,0.022606945,0.0040213466,0.00004690253,0.00009934674,0.0000026308758,0.000010050957,0.037892472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881357,0.00004002579,0.0002773978,0.00041613547,0.00015822121,0.00029467884],"domain_scores_gemma":[0.999133,0.000089265624,0.00007844121,0.00042352284,0.0002264661,0.00004928953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031622523,0.00013991717,0.00017102895,0.0001792776,0.0003175944,0.00028808293,0.00065374665,0.00005114419,0.0000750155],"category_scores_gemma":[0.00004107915,0.00011774815,0.00010314569,0.00034220086,0.000060346458,0.00095490005,0.00020884804,0.00010363693,0.000050211296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031333635,0.00009475066,0.00038646028,0.000045807003,0.000050819635,0.000004466775,0.002124767,0.000054829936,0.0024180368,0.97700924,0.005634395,0.012145106],"study_design_scores_gemma":[0.00070142513,0.00078315224,0.0022279106,0.0003323031,0.00003660362,0.000003867022,0.0034135636,0.0836966,0.73109895,0.16991258,0.0073256213,0.00046742294],"about_ca_topic_score_codex":0.0005765593,"about_ca_topic_score_gemma":0.00015316343,"teacher_disagreement_score":0.92741835,"about_ca_system_score_codex":0.00008819055,"about_ca_system_score_gemma":0.00004616188,"threshold_uncertainty_score":0.48016304},"labels":[],"label_agreement":null},{"id":"W4413602392","doi":"10.1177/25152459261424825","title":"Models as Prediction Machines: How to Convert Confusing Coefficients Into Clear Quantities","year":2025,"lang":"en","type":"preprint","venue":"Advances in Methods and Practices in Psychological Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Econometrics; Mathematics","score_opus":0.10721877304379691,"score_gpt":0.5487022649902978,"score_spread":0.44148349194650094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413602392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03793602,0.0027305256,0.93496907,0.003299953,0.0032361955,0.0007370722,0.0000049658124,0.000111760324,0.016974468],"genre_scores_gemma":[0.33129367,0.004084547,0.6630298,0.0013432199,0.000045378092,0.000091337046,0.0000013947805,0.0000061048086,0.00010455882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944178,0.0012952848,0.00066905963,0.002223719,0.0007056835,0.0006884856],"domain_scores_gemma":[0.99577034,0.0020862143,0.0006494675,0.0010333396,0.0002502776,0.00021036042],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010099723,0.0003680907,0.0005330504,0.00082819414,0.00037293974,0.0011250115,0.0029658265,0.0002944095,0.000020135638],"category_scores_gemma":[0.006512325,0.00031577595,0.000058586233,0.0027481786,0.0009827707,0.0045155557,0.0026837585,0.0011987877,0.000008254288],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015959685,0.00028619482,0.0019921868,0.000115601586,0.0000052309283,0.000042852484,0.004877429,0.04552217,0.0009802283,0.16578008,0.000026160476,0.7802123],"study_design_scores_gemma":[0.0001263885,0.00034787928,0.0005826257,0.0003029159,0.0000060816797,0.000019741987,0.0010003606,0.5448464,0.0008024848,0.4446151,0.0069679404,0.0003820953],"about_ca_topic_score_codex":0.00059453206,"about_ca_topic_score_gemma":0.00016732185,"teacher_disagreement_score":0.77983016,"about_ca_system_score_codex":0.00019959004,"about_ca_system_score_gemma":0.0001603476,"threshold_uncertainty_score":0.9999294},"labels":[],"label_agreement":null},{"id":"W4413848206","doi":"10.1007/s11229-025-05228-8","title":"Strong novelty regained: high-impact outcomes of machine learning for science","year":2025,"lang":"en","type":"article","venue":"Synthese","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"German Academic Exchange Service; Social Sciences and Humanities Research Council","keywords":"Novelty; Philosophy of science; Metaphysics; Philosophy of language; Science learning; Philosophy of technology; Epistemology; Psychology; Artificial intelligence; Computer science; Philosophy; Cognitive science; Mathematics education; Science education; Social psychology","score_opus":0.026417350455345812,"score_gpt":0.3335360793258481,"score_spread":0.3071187288705023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413848206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19507205,0.00010222777,0.7995615,0.0014651117,0.00044074465,0.0003540635,0.000009348606,0.00015040005,0.0028445423],"genre_scores_gemma":[0.9778002,0.0000044025605,0.020903762,0.00007285187,0.000016904376,0.000023154196,9.788679e-7,0.000008229385,0.0011695059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983265,0.000051646013,0.00033821625,0.00045517832,0.00034038108,0.00048808765],"domain_scores_gemma":[0.9979822,0.0007987975,0.00014938525,0.00070084375,0.00028206466,0.00008668822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012632111,0.00016314095,0.00029895082,0.00040090407,0.00029072975,0.0001485532,0.0015398588,0.000045787878,0.00002151494],"category_scores_gemma":[0.002753565,0.00013096437,0.00012822264,0.001186361,0.00026451584,0.0007135584,0.00039547138,0.00014291471,0.000017128215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050471346,0.00022103879,0.037121475,0.0000767037,0.00008193345,0.000005746742,0.00081063225,0.012604088,0.03948016,0.8260478,0.0001593562,0.08334061],"study_design_scores_gemma":[0.0002806628,0.00031427827,0.017245447,0.0001288208,0.00002320857,0.0000027105416,0.00037675226,0.5068877,0.44616824,0.02670048,0.0014883304,0.0003833943],"about_ca_topic_score_codex":0.0008688748,"about_ca_topic_score_gemma":0.000067222514,"teacher_disagreement_score":0.7993473,"about_ca_system_score_codex":0.00013424111,"about_ca_system_score_gemma":0.00031926695,"threshold_uncertainty_score":0.5340572},"labels":[],"label_agreement":null},{"id":"W4413855449","doi":"10.1007/978-3-032-02813-6_9","title":"ODExAI: A Comprehensive Object Detection Explainable AI Evaluation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Computer vision","score_opus":0.03221410776637678,"score_gpt":0.29514409120506346,"score_spread":0.2629299834386867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413855449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015230701,0.000781371,0.98513174,0.00090508116,0.0032117125,0.0012177668,0.0000033418848,0.0003056816,0.008290973],"genre_scores_gemma":[0.75814325,0.00016965021,0.2296109,0.007688873,0.0010948558,0.00021816473,0.000021298038,0.00010012112,0.002952862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937748,0.00015942678,0.0008149944,0.002304445,0.0019311038,0.0010152332],"domain_scores_gemma":[0.99484247,0.00082969654,0.00038298115,0.002067633,0.0016888824,0.00018835618],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017873609,0.0007197255,0.0006794317,0.0018283824,0.0006873637,0.001042975,0.003447554,0.0004914953,0.000054529624],"category_scores_gemma":[0.00038393796,0.0007370837,0.00020978836,0.0017586404,0.00060605526,0.0015598537,0.0015582294,0.0011821974,0.00015406247],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012400794,0.00003377572,0.000008716346,0.00006160266,0.000017458704,0.0000617733,0.0008202333,0.09213904,0.0009891121,0.0189584,0.00005384399,0.8868436],"study_design_scores_gemma":[0.00015952245,0.00019077043,0.00003301209,0.0003534017,0.000018841176,0.000040491937,0.00000147225,0.7394938,0.027165348,0.22909278,0.002838475,0.0006120995],"about_ca_topic_score_codex":0.00021938585,"about_ca_topic_score_gemma":0.0005650847,"teacher_disagreement_score":0.88623154,"about_ca_system_score_codex":0.0014009099,"about_ca_system_score_gemma":0.0017384725,"threshold_uncertainty_score":0.99999404},"labels":[],"label_agreement":null},{"id":"W4413932834","doi":"10.3390/technologies13090390","title":"Classifying XAI Methods to Resolve Conceptual Ambiguity","year":2025,"lang":"en","type":"article","venue":"Technologies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Ambiguity; Computer science; Geography","score_opus":0.06582860507179016,"score_gpt":0.3999974973214919,"score_spread":0.33416889224970175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413932834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005183159,0.0005169331,0.96046853,0.013201436,0.00049679226,0.00027260225,0.0000011196804,0.008302596,0.011556853],"genre_scores_gemma":[0.37301347,0.00002612374,0.625494,0.00073716894,0.000011611679,0.00008134834,3.186414e-7,0.0000067183087,0.0006292506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982499,0.000097117525,0.00032349778,0.00061169855,0.0001886378,0.0005291845],"domain_scores_gemma":[0.99805534,0.00036717975,0.00006913263,0.0013259023,0.00014226543,0.00004020833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007410736,0.0001856427,0.00025722716,0.00043458494,0.00026537446,0.00020160322,0.0026154618,0.00022207356,0.000005504773],"category_scores_gemma":[0.0020327647,0.00017421057,0.00006949041,0.001961469,0.00038099522,0.0003728623,0.0020140975,0.00034781813,0.0001804424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038320754,0.000021858743,0.00015800497,0.000006975635,0.000011484695,0.000011703498,0.00048238097,0.0000604302,0.012325468,0.6410137,0.008787995,0.33711615],"study_design_scores_gemma":[0.000057596182,0.00010263635,0.00024200174,0.000054382203,0.000005514817,0.0000027225542,0.0060248454,0.0076866634,0.7598057,0.14746515,0.07829141,0.0002613817],"about_ca_topic_score_codex":0.00009987103,"about_ca_topic_score_gemma":0.000049478793,"teacher_disagreement_score":0.7474802,"about_ca_system_score_codex":0.00015007518,"about_ca_system_score_gemma":0.00010066389,"threshold_uncertainty_score":0.71041006},"labels":[],"label_agreement":null},{"id":"W4414030788","doi":"10.1016/j.iheduc.2025.101052","title":"Exploring undergraduate students' perceptions of AI vs. human scoring and feedback","year":2025,"lang":"en","type":"article","venue":"The Internet and Higher Education","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton","funders":"Concordia University of Edmonton","keywords":"Perception; Mathematics education; Psychology; Computer science; Medical education; Medicine; Neuroscience","score_opus":0.060950287689757854,"score_gpt":0.3483979434367106,"score_spread":0.28744765574695275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414030788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98439574,0.00016154574,0.0062721097,0.006324736,0.0006696763,0.00011134149,1.6177077e-7,0.00003244715,0.0020322443],"genre_scores_gemma":[0.9906764,0.000076841956,0.00026161975,0.00027273904,0.000056834182,0.000033464446,7.588175e-7,0.0000038023068,0.008617561],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9993983,0.0000394726,0.00016646765,0.00018353356,0.00010299699,0.00010923342],"domain_scores_gemma":[0.9995703,0.000044581375,0.000045696466,0.00024331517,0.00006703739,0.000029072982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001519925,0.00007513906,0.00008461572,0.00010267425,0.000121095574,0.00020531999,0.0003929021,0.000017753773,0.000016702177],"category_scores_gemma":[0.000005934921,0.00006111444,0.00001863533,0.00018595137,0.00008256219,0.000462584,0.00023519802,0.000096058284,0.000011095874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006865025,0.00013143601,0.048528258,0.000047645983,0.000031321833,3.0857072e-7,0.0069426,0.0000104658775,0.0027004296,0.92099476,0.0013018241,0.019304106],"study_design_scores_gemma":[0.0001395272,0.00011391714,0.85134774,0.00038845165,0.000039158018,0.000004556901,0.0024830722,0.00048124953,0.015894296,0.124719106,0.004176652,0.00021229826],"about_ca_topic_score_codex":0.0007683007,"about_ca_topic_score_gemma":0.00007247036,"teacher_disagreement_score":0.80281943,"about_ca_system_score_codex":0.000033404212,"about_ca_system_score_gemma":0.000036265144,"threshold_uncertainty_score":0.24921745},"labels":[],"label_agreement":null},{"id":"W4414083005","doi":"10.1007/s43503-025-00066-6","title":"Bridging AI and explainability in civil engineering: the Yin-Yang of predictive power and interpretability","year":2025,"lang":"en","type":"article","venue":"AI in Civil Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Alberta","funders":"","keywords":"Interpretability; Bridging (networking); Decision tree; SAFER; Predictive power; Transparency (behavior); Feature engineering","score_opus":0.0053382760105264385,"score_gpt":0.23131831921004856,"score_spread":0.2259800431995221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414083005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43401304,0.00064995553,0.56301135,0.0012535751,0.00027500096,0.00033892982,0.0000018709981,0.0000955558,0.00036073432],"genre_scores_gemma":[0.99909294,0.00002516179,0.0006622621,0.00012843782,0.000012987126,0.000058096506,2.926376e-7,0.000011612736,0.000008229852],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998342,0.0000636289,0.0004941976,0.0005116246,0.00017747114,0.0004111058],"domain_scores_gemma":[0.9986842,0.0005367343,0.000048070302,0.0005873568,0.000080613216,0.00006297942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011880399,0.00022064422,0.00031424384,0.00033922418,0.000045831748,0.00009466009,0.00049809297,0.00009202472,0.000004551868],"category_scores_gemma":[0.0008989627,0.00020728304,0.000046766087,0.0009128887,0.00009621174,0.00066984893,0.00054384704,0.00047331463,5.96057e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091988346,0.0003883307,0.23451859,0.0015513763,0.00012776,0.00007835806,0.036763404,0.5467178,0.018614376,0.13580571,0.00019465866,0.025147613],"study_design_scores_gemma":[0.00013246805,0.000046217596,0.08200282,0.0003174079,0.0000044539784,0.000004904888,0.00022280026,0.90889096,0.006275562,0.0018146739,0.00011079535,0.00017694848],"about_ca_topic_score_codex":0.00027957212,"about_ca_topic_score_gemma":0.00085159374,"teacher_disagreement_score":0.56507987,"about_ca_system_score_codex":0.0001744109,"about_ca_system_score_gemma":0.00006343044,"threshold_uncertainty_score":0.8452757},"labels":[],"label_agreement":null},{"id":"W4414182515","doi":"10.1061/jtepbs.teeng-8808","title":"From Opacity to Clarity: Employing Explainable AI to Interpret CNN Predictions on Winter Road Conditions","year":2025,"lang":"en","type":"article","venue":"Journal of Transportation Engineering Part A Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Convolutional neural network; Transparency (behavior); Deep learning; Limiting; Feature (linguistics); Scrutiny","score_opus":0.016915501461020516,"score_gpt":0.27876223759781155,"score_spread":0.26184673613679105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414182515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16152439,0.000051694307,0.83292264,0.0016019729,0.0033165517,0.00030100963,0.00005653574,0.00011552861,0.00010966734],"genre_scores_gemma":[0.9951234,0.000003683343,0.0038408546,0.00043633924,0.0002521322,0.00006916269,0.000010749612,0.000015318297,0.0002483462],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808836,0.000052468757,0.0008991937,0.00028405688,0.00038182386,0.00029411758],"domain_scores_gemma":[0.99870974,0.00016604032,0.00012514916,0.00036414643,0.00038606534,0.00024885294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004380915,0.00019234183,0.0003472257,0.00066303805,0.00013698735,0.00026510694,0.0005711866,0.000087881235,0.000015283887],"category_scores_gemma":[0.00013977147,0.00019753004,0.00014638797,0.0007710411,0.000010822542,0.0008257641,0.000015824126,0.00034729703,0.000043762862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033879147,0.000089695524,0.000611216,0.000052033192,0.00012530356,0.00005691223,0.0074381162,0.97195977,0.0037260994,0.007902424,0.0077298013,0.00027476833],"study_design_scores_gemma":[0.0013916938,0.0021117823,0.038818408,0.012113927,0.00031686836,0.000073263414,0.008043874,0.67138666,0.04699772,0.001970653,0.2150266,0.0017485423],"about_ca_topic_score_codex":0.00025491865,"about_ca_topic_score_gemma":0.00005411207,"teacher_disagreement_score":0.83359903,"about_ca_system_score_codex":0.00020376172,"about_ca_system_score_gemma":0.000103122344,"threshold_uncertainty_score":0.8055041},"labels":[],"label_agreement":null},{"id":"W4414270260","doi":"10.1109/tkde.2025.3611170","title":"A Multi-Objective Explanation Framework for Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Focus (optics); Graph; Artificial neural network; Attribution; Graph theory; Data modeling; Pareto principle","score_opus":0.03820802667668711,"score_gpt":0.31086400128210495,"score_spread":0.27265597460541785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414270260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004255495,0.00046807982,0.99702805,0.0001143496,0.0014124787,0.0002754677,0.0000314306,0.00020979681,0.00003481373],"genre_scores_gemma":[0.8816484,0.00008853819,0.11792479,0.00006971006,0.000059377762,0.00010843858,0.000011203786,0.000012680737,0.00007682874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990443,0.000018791929,0.00018412464,0.00044845795,0.000058381833,0.00024592676],"domain_scores_gemma":[0.9987405,0.00046896408,0.000023686493,0.00063138775,0.000073938136,0.000061512066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019014745,0.00014759063,0.00013439603,0.0002709238,0.00021023258,0.00012904395,0.00057548296,0.00009416127,0.0000019992926],"category_scores_gemma":[0.000033545584,0.0001562859,0.000042586056,0.00060493307,0.000019289482,0.00069703936,0.0000140318225,0.0002282175,0.000004452833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039480445,0.00029886243,0.000015157056,0.00012334577,0.00012713067,0.0000043672803,0.0012827717,0.68198305,0.0007488523,0.038183395,0.00038263257,0.27681094],"study_design_scores_gemma":[0.000130812,0.000041153147,0.000045703353,0.000070103175,0.000017284241,0.000001964727,0.00005617071,0.9925686,0.005579655,0.00069356605,0.0006490982,0.00014587912],"about_ca_topic_score_codex":0.000015608488,"about_ca_topic_score_gemma":0.00005618711,"teacher_disagreement_score":0.8812229,"about_ca_system_score_codex":0.000035611673,"about_ca_system_score_gemma":0.00002448309,"threshold_uncertainty_score":0.6373154},"labels":[],"label_agreement":null},{"id":"W4414359765","doi":"10.24963/ijcai.2025/1254","title":"Veracity: An Open-Source AI Fact-Checking System","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Misinformation; Key (lock); Interface (matter); Generative grammar; User interface; Literacy","score_opus":0.037225030564280316,"score_gpt":0.3278267452876916,"score_spread":0.2906017147234113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414359765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016086327,0.000031098298,0.87534183,0.001419696,0.00051931146,0.00028727227,4.6957564e-7,0.0006234623,0.10569054],"genre_scores_gemma":[0.9750011,0.0000016446301,0.0133547755,0.0024877223,0.000036900707,0.000025662854,0.0000011230285,0.000009846058,0.009081247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983305,0.00012534253,0.00031923194,0.00059192535,0.0002341219,0.0003989068],"domain_scores_gemma":[0.9984471,0.000100775345,0.0000615819,0.0011130498,0.0001591751,0.00011827361],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000605922,0.00015824115,0.00021175896,0.00016054869,0.00037625383,0.001585492,0.0031206878,0.00006229675,0.000040224135],"category_scores_gemma":[0.00005740815,0.00014767399,0.000039192022,0.0007900403,0.00003543063,0.0022713013,0.0013127195,0.00017100164,0.00037889637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060123566,0.000071725706,0.00047738486,0.00003249108,0.000015220118,0.000025827509,0.0007062076,0.0007517499,0.001499894,0.93826264,0.0018391992,0.05631163],"study_design_scores_gemma":[0.00023399497,0.0001935457,0.0004872397,0.0002282027,0.000013510214,0.0000284914,0.0033125032,0.67675835,0.2003492,0.013215893,0.104551196,0.00062786497],"about_ca_topic_score_codex":0.0016514504,"about_ca_topic_score_gemma":0.00030661176,"teacher_disagreement_score":0.95891476,"about_ca_system_score_codex":0.00015914078,"about_ca_system_score_gemma":0.00015183735,"threshold_uncertainty_score":0.999451},"labels":[],"label_agreement":null},{"id":"W4414374339","doi":"10.1007/s11571-025-10343-w","title":"Towards a transparent and interpretable AI model for medical image classifications","year":2025,"lang":"en","type":"review","venue":"Cognitive Neurodynamics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Specific Research Project of Guangxi for Research Bases and Talents; National Natural Science Foundation of China","keywords":"Field (mathematics); Perspective (graphical); Process (computing); Health care; Code (set theory)","score_opus":0.07865176444160218,"score_gpt":0.3995446975993969,"score_spread":0.32089293315779477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414374339","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.191613e-7,0.3309486,0.66589415,0.0004475065,0.00027487907,0.001049909,0.00027656247,0.00011087638,0.0009971064],"genre_scores_gemma":[0.00015631046,0.9908453,0.006412055,0.0008174192,0.000045529003,0.0009072726,0.00013802912,0.00004446711,0.00063361484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705505,0.00019366742,0.00077003404,0.0011113033,0.00037570187,0.0004942192],"domain_scores_gemma":[0.99722373,0.0012840334,0.00020623971,0.00056032394,0.00048303514,0.00024263636],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040369167,0.0004781561,0.0010823944,0.0003363309,0.0002279014,0.00033918637,0.0013650286,0.00033091084,0.000007970689],"category_scores_gemma":[0.0012778715,0.00044824643,0.00038411008,0.0006262553,0.00024696594,0.00043816114,0.00045542486,0.000658098,0.000020000662],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004619995,0.00008992388,1.6305465e-7,0.0050797598,0.000058557096,0.000016153737,0.00018390143,0.000016280024,4.7454915e-7,0.035952557,0.00014200012,0.9584556],"study_design_scores_gemma":[0.0000965776,0.00006302493,6.2570507e-7,0.006684435,0.00043090194,0.000023847702,0.000021335594,0.9498136,0.0000032090268,0.00611348,0.03635744,0.00039152155],"about_ca_topic_score_codex":0.0000071058716,"about_ca_topic_score_gemma":0.000059502105,"teacher_disagreement_score":0.9580641,"about_ca_system_score_codex":0.00010634838,"about_ca_system_score_gemma":0.0017581466,"threshold_uncertainty_score":0.9997969},"labels":[],"label_agreement":null},{"id":"W4414519225","doi":"10.1016/j.forsciint.2025.112669","title":"Unsupervised machine learning for the detection and interpretation of key features in drip patterns","year":2025,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Pattern recognition (psychology); Unsupervised learning; Feature (linguistics); Ranking (information retrieval); Observable; Interpretation (philosophy)","score_opus":0.012555615195986296,"score_gpt":0.28141470304691973,"score_spread":0.26885908785093343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414519225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22570978,0.00009563047,0.7708146,0.0017316109,0.00092076237,0.00021127306,0.0000021079206,0.000024854215,0.00048938877],"genre_scores_gemma":[0.99667376,0.00002054331,0.0029370394,0.00016885593,0.00002182023,0.00003248655,0.0000015502253,0.0000024964759,0.0001414309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990094,0.000026129548,0.00022242594,0.00028517365,0.00029324944,0.00016364276],"domain_scores_gemma":[0.9990644,0.0003850462,0.00008354406,0.00016801275,0.00027724472,0.000021778587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075149914,0.00007570717,0.00008346244,0.00038205896,0.0001743573,0.00018111175,0.00081266207,0.000027247854,0.0000046261157],"category_scores_gemma":[0.0007016568,0.000058135334,0.00003456718,0.0006207468,0.00023654327,0.0006349723,0.00021367699,0.00011902593,0.0000010708292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009445938,0.000041933614,0.02491534,0.000022511567,0.00002036013,0.0000015591695,0.005305734,0.010565679,0.018132182,0.12728228,0.000022298364,0.81359565],"study_design_scores_gemma":[0.000122006,0.00005889948,0.032628935,0.000052210013,0.0000025838417,0.0000036301924,0.00037882285,0.89353305,0.06290768,0.010029907,0.00022772244,0.000054536013],"about_ca_topic_score_codex":0.0004151126,"about_ca_topic_score_gemma":0.0014032203,"teacher_disagreement_score":0.8829674,"about_ca_system_score_codex":0.00008518779,"about_ca_system_score_gemma":0.00006867029,"threshold_uncertainty_score":0.23706901},"labels":[],"label_agreement":null},{"id":"W4414564075","doi":"10.2196/77482","title":"Explainable AI-Driven Analysis of Radiology Reports Using Text and Image Data: Experimental Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Component (thermodynamics); Medical imaging; Image (mathematics); Health care; MEDLINE; Patient care","score_opus":0.11961170000099647,"score_gpt":0.4806930035276018,"score_spread":0.36108130352660534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414564075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9121959,0.00026140807,0.08447553,0.00018282881,0.00011630302,0.00079598324,0.00000906036,0.00003966829,0.0019233235],"genre_scores_gemma":[0.9968932,0.000011885881,0.0028241065,0.000029820178,0.00001280587,0.000080218066,0.000011631593,0.000005957926,0.00013032238],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968543,0.00070687337,0.00061312644,0.00066375005,0.00059681264,0.0005651025],"domain_scores_gemma":[0.99720114,0.0004218018,0.00015936325,0.0016026126,0.0005186249,0.00009643646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028020744,0.0001490937,0.00044929297,0.0015798126,0.0004663252,0.00024833952,0.0012716586,0.000065159926,0.000032386644],"category_scores_gemma":[0.00020630709,0.00013555912,0.00005969983,0.004084495,0.0004181038,0.002493129,0.00304124,0.0003335895,0.000007985671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005586027,0.014702655,0.17514247,0.0006486448,0.0080493,0.0027820356,0.44985417,0.005284193,0.18366842,0.10951279,0.027354307,0.022442404],"study_design_scores_gemma":[0.0003300974,0.0011109816,0.012873958,0.000056864137,0.00008393167,0.00004958041,0.06457897,0.85166436,0.06613475,0.0022966983,0.00051315635,0.00030663752],"about_ca_topic_score_codex":0.00072815735,"about_ca_topic_score_gemma":0.000059152484,"teacher_disagreement_score":0.8463802,"about_ca_system_score_codex":0.00019703533,"about_ca_system_score_gemma":0.00022420188,"threshold_uncertainty_score":0.55279404},"labels":[],"label_agreement":null},{"id":"W4414641939","doi":"10.1177/10944281251377154","title":"Generative Artificial Intelligence in Qualitative Data Analysis: Analyzing—Or Just Chatting?","year":2025,"lang":"en","type":"article","venue":"Organizational Research Methods","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Transformative learning; Generative grammar; Qualitative research; sort; Interpretation (philosophy); Qualitative property; Thematic analysis; Artifact (error); Generative model","score_opus":0.5143227817647522,"score_gpt":0.6391483870820126,"score_spread":0.12482560531726039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414641939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056494685,0.00028332128,0.98904294,0.007526314,0.00019351205,0.000366721,0.000022337992,0.00008509883,0.0019148153],"genre_scores_gemma":[0.114988185,0.000107229156,0.8827335,0.000322615,0.00012260463,0.000050784543,0.00012334163,0.000020102876,0.0015316036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889188,0.006806341,0.0009413463,0.0014417277,0.0010890107,0.0008028158],"domain_scores_gemma":[0.98701304,0.008459878,0.00015714447,0.0020223265,0.0021635327,0.00018410527],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.024099296,0.00023744802,0.00046693813,0.0027999915,0.0006038548,0.00067589706,0.004164733,0.00014969915,0.00053264864],"category_scores_gemma":[0.029096536,0.00021531919,0.000065908716,0.031452924,0.00039215258,0.0012131217,0.0026058361,0.000703268,0.00013477787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039541486,0.00022052263,0.0004304271,0.000023280127,0.0002638122,0.000030061323,0.010617216,0.0031974774,0.0026249199,0.91486555,0.00048458134,0.06720258],"study_design_scores_gemma":[0.000041068713,0.000067747555,0.00048172055,0.000044425975,0.000043364398,0.0000014289016,0.011060363,0.6250614,0.061899178,0.3002338,0.00078395364,0.0002815346],"about_ca_topic_score_codex":0.0003796197,"about_ca_topic_score_gemma":0.0011102202,"teacher_disagreement_score":0.62186396,"about_ca_system_score_codex":0.00039475106,"about_ca_system_score_gemma":0.0015198514,"threshold_uncertainty_score":0.989134},"labels":[],"label_agreement":null},{"id":"W4414662698","doi":"10.2139/ssrn.5468868","title":"Communicating Uncertainty Can Increase AI Adoption","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Set (abstract data type); Range (aeronautics); Outcome (game theory); Recommender system; Uncertainty reduction theory; Cheap talk","score_opus":0.019366530064028095,"score_gpt":0.2935442126060599,"score_spread":0.2741776825420318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414662698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016019793,0.004885967,0.95963955,0.012887518,0.0011263486,0.00047768085,0.000012830981,0.00031875476,0.0046315854],"genre_scores_gemma":[0.9836915,0.006786363,0.0060970844,0.0012167924,0.0003599569,0.000044602883,0.000026085932,0.00002530602,0.0017522785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99446636,0.0006676255,0.0007854244,0.00063182856,0.00053193694,0.0029168408],"domain_scores_gemma":[0.99666643,0.00023041088,0.0006002422,0.001786927,0.00052823796,0.00018773189],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0044395076,0.00040990047,0.00044712238,0.00039889256,0.0007345492,0.0006773455,0.0048851524,0.00032635054,0.000011839251],"category_scores_gemma":[0.00036487228,0.000417105,0.0002914984,0.00053939,0.000094824776,0.00039469462,0.0027900757,0.0096532935,0.00003336891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000022938837,0.00010929987,0.00023190017,0.00004953138,0.00018457836,0.00001447289,0.000992514,0.018796928,0.000072448565,0.8772252,0.00019804253,0.10210211],"study_design_scores_gemma":[0.00015513158,0.00013768273,0.000032428397,0.0003931657,0.00004675115,0.0001909092,0.0011714333,0.09447195,0.00036306772,0.90046054,0.002079103,0.0004978309],"about_ca_topic_score_codex":0.006035909,"about_ca_topic_score_gemma":0.012346649,"teacher_disagreement_score":0.96767175,"about_ca_system_score_codex":0.004064399,"about_ca_system_score_gemma":0.0132002765,"threshold_uncertainty_score":0.9998281},"labels":[],"label_agreement":null},{"id":"W4414758275","doi":"10.1109/tvcg.2025.3616811","title":"Seeing What Matters: Attentional (MIS-) Alignment between Humans and AI in VR-Simulated Prediction of Driving Accidents","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Department of Artificial Intelligence, Korea University; National Research Foundation of Korea; Korea University; Ministry of Science and ICT, South Korea; Indian Institute of Technology, Patna","keywords":"Focus (optics); Point (geometry); Event (particle physics); Path (computing); Key (lock); Virtual reality; Time point; Accident (philosophy)","score_opus":0.022246144017442602,"score_gpt":0.3014032026101051,"score_spread":0.2791570585926625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414758275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17787057,0.00003990292,0.8211317,0.0002512593,0.00041932618,0.00020343185,0.0000029844834,0.00007386785,0.0000069553844],"genre_scores_gemma":[0.99828035,0.0002531232,0.00041388086,0.0009796491,0.000018286035,0.000010123763,0.000007976371,0.000008942048,0.000027653186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850667,0.00012831033,0.0004892853,0.00041394428,0.00027162675,0.00019013947],"domain_scores_gemma":[0.9993536,0.00013470506,0.00009750302,0.00022327818,0.00012886632,0.00006205418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002748324,0.00016199723,0.00020100603,0.0007415571,0.00023243937,0.000327308,0.00021013185,0.0001065782,0.00000472426],"category_scores_gemma":[0.0000022130314,0.00018308981,0.000054472966,0.000940891,0.00007533471,0.0012273594,0.000011997067,0.00015252313,0.0000014142572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006582417,0.0016263411,0.14025526,0.00058060605,0.0005951858,0.000020086965,0.014511634,0.056818858,0.0017679379,0.65712005,0.00036084236,0.1262774],"study_design_scores_gemma":[0.0004421751,0.000131887,0.03290834,0.0005897345,0.00003121981,0.0000022966033,0.00023585717,0.9544295,0.0076750843,0.003217058,0.00016491236,0.00017195058],"about_ca_topic_score_codex":0.0000474954,"about_ca_topic_score_gemma":0.000054471824,"teacher_disagreement_score":0.8976106,"about_ca_system_score_codex":0.000046458492,"about_ca_system_score_gemma":0.000029842657,"threshold_uncertainty_score":0.74661857},"labels":[],"label_agreement":null},{"id":"W4415160834","doi":"10.48550/arxiv.2504.10397","title":"Can LLMs Assist Expert Elicitation for Probabilistic Causal Modeling?","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Expert elicitation; Bayesian network; Probabilistic logic; Entropy (arrow of time); Robustness (evolution); Bayesian probability; Causal model; Causal inference; Transparency (behavior)","score_opus":0.11320324584762353,"score_gpt":0.3423743979090132,"score_spread":0.22917115206138966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415160834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15979913,0.00021577923,0.8311848,0.004067849,0.0021934044,0.0012472989,0.000034496657,0.00037552047,0.0008817185],"genre_scores_gemma":[0.96767294,0.00003424452,0.028543621,0.0010230211,0.00036460947,0.0010968439,0.0000771689,0.000031229665,0.0011563286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969308,0.00011590603,0.00070065097,0.0012800351,0.0003626532,0.00060996827],"domain_scores_gemma":[0.9970893,0.00034372037,0.0002375138,0.0014845849,0.00069572433,0.00014914559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005549116,0.00041673632,0.0004444518,0.00024038412,0.00032062404,0.0003180345,0.0018241666,0.0003429541,0.000009575458],"category_scores_gemma":[0.0008848385,0.00043555044,0.00022179811,0.0003695663,0.000078850004,0.00027822342,0.0011139557,0.00046785153,0.000053801865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012161826,0.000867918,0.013245178,0.0015815735,0.00036398994,0.000063603504,0.019803863,0.58416516,0.0025004195,0.3283413,0.0053387806,0.043606628],"study_design_scores_gemma":[0.00010272009,0.00007666556,0.0003745347,0.0002365602,0.000026784955,0.0000016265628,0.00019114239,0.91163224,0.00421028,0.08173033,0.0009036477,0.00051347585],"about_ca_topic_score_codex":0.0020554685,"about_ca_topic_score_gemma":0.0010685935,"teacher_disagreement_score":0.8078738,"about_ca_system_score_codex":0.00041722806,"about_ca_system_score_gemma":0.0007923336,"threshold_uncertainty_score":0.9998096},"labels":[],"label_agreement":null},{"id":"W4415230910","doi":"10.21203/rs.3.rs-7623811/v1","title":"Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Benchmark (surveying); Pipeline (software); Language model; Limiting; Textual entailment; Identification (biology); Security token; Framing (construction)","score_opus":0.19359360646665327,"score_gpt":0.439637199761039,"score_spread":0.24604359329438572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415230910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05380762,0.004399191,0.9214541,0.0077470336,0.0007778135,0.0054456196,0.005664467,0.00020491482,0.0004992503],"genre_scores_gemma":[0.9191444,0.007605615,0.05733796,0.00066254,0.00057324633,0.0027961351,0.0058502527,0.000102394166,0.0059274463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623674,0.0008607895,0.00047135644,0.0011632129,0.00059814873,0.00066974404],"domain_scores_gemma":[0.99672174,0.0012163353,0.00009605898,0.001183929,0.00062324904,0.00015867974],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035150065,0.00026275695,0.00033715036,0.001307219,0.00043596982,0.0009437887,0.0009935704,0.00031760146,0.000016209013],"category_scores_gemma":[0.0017071378,0.00027298965,0.00004385432,0.0012063707,0.00018517197,0.00057538686,0.0029951355,0.000783699,0.000008188515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016264793,0.0011242739,0.026922608,0.014589694,0.00032821423,0.0002634883,0.007993824,0.026003016,0.006204152,0.336396,0.21097666,0.3675716],"study_design_scores_gemma":[0.0007892519,0.00074254646,0.015374791,0.002346006,0.000029422605,0.000024620553,0.0009976493,0.56610525,0.036526762,0.24014592,0.13564727,0.0012704916],"about_ca_topic_score_codex":0.0029061255,"about_ca_topic_score_gemma":0.009761413,"teacher_disagreement_score":0.8653368,"about_ca_system_score_codex":0.00021977998,"about_ca_system_score_gemma":0.00088896265,"threshold_uncertainty_score":0.9999722},"labels":[],"label_agreement":null},{"id":"W4415269798","doi":"10.48550/arxiv.2510.12141","title":"MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Interpretability; Set (abstract data type); Computational model; Similarity (geometry); Psychophysics; Attribution; Object (grammar); Artificial neural network","score_opus":0.09027916531824774,"score_gpt":0.34702892350412506,"score_spread":0.2567497581858773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415269798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19698563,0.00004331551,0.80012727,0.0015186912,0.00017858522,0.0005691691,0.00008657023,0.00014207329,0.00034871194],"genre_scores_gemma":[0.8687176,0.0000030756137,0.13044782,0.00041064847,0.00004101361,0.00015697976,0.0001079367,0.000011358251,0.00010356754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997681,0.00011238913,0.0006403027,0.00081809534,0.00039295593,0.00035523716],"domain_scores_gemma":[0.9977862,0.00046371747,0.00027391058,0.0007964662,0.0005477304,0.00013196403],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044443095,0.0002993262,0.00038455307,0.00040728698,0.00030774227,0.00025503334,0.0010810075,0.0002713741,0.000011585656],"category_scores_gemma":[0.00014659937,0.00034013708,0.000108041,0.0005997262,0.00010395726,0.0003126643,0.0008629067,0.0004797255,0.000020846928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045827587,0.00006867246,0.0031712668,0.00011278744,0.000028227973,0.0000037631296,0.0011894992,0.6627167,0.00028432542,0.33212233,0.00014330001,0.00015456315],"study_design_scores_gemma":[0.00008563581,0.000055366225,0.00211443,0.0005651232,0.000020589774,5.7778516e-7,0.00023328066,0.685511,0.0038630415,0.30716625,0.000050725128,0.00033396523],"about_ca_topic_score_codex":0.00020771765,"about_ca_topic_score_gemma":0.00006853634,"teacher_disagreement_score":0.67173195,"about_ca_system_score_codex":0.00015696074,"about_ca_system_score_gemma":0.0009632234,"threshold_uncertainty_score":0.99990505},"labels":[],"label_agreement":null},{"id":"W4415282304","doi":"10.3390/info16100904","title":"Can We Trust AI Content Detection Tools for Critical Decision-Making?","year":2025,"lang":"en","type":"article","venue":"Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Government of Manitoba","funders":"","keywords":"Government (linguistics); Robustness (evolution); Precision and recall; Recall; Reliability (semiconductor); Content analysis","score_opus":0.03774558943092063,"score_gpt":0.3273950318151122,"score_spread":0.28964944238419155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415282304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045433785,0.000018562676,0.98652446,0.005451624,0.0010660259,0.00036560957,0.0000059406884,0.00014177554,0.001882628],"genre_scores_gemma":[0.9766305,0.0000044068306,0.020522675,0.0026658212,0.000033956243,0.00010045681,0.000003136794,0.0000024552828,0.000036558617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902034,0.000018139783,0.00041977895,0.00012722374,0.00019295707,0.00022154344],"domain_scores_gemma":[0.9984218,0.000740489,0.000066168606,0.00029514107,0.0004349838,0.000041456227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031680166,0.00009124717,0.00010168778,0.0002269465,0.00025389213,0.00075746904,0.00038157875,0.0000771598,0.000008336473],"category_scores_gemma":[0.0024064141,0.0000884745,0.00006166479,0.00038379707,0.00003268217,0.00446609,0.00009130458,0.000093095034,0.00009030242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021190312,0.00001002447,0.000013450729,0.000023769657,0.0000034900397,3.4241714e-7,0.0004938686,0.00033128713,0.00012579396,0.30901143,0.000479988,0.6894854],"study_design_scores_gemma":[0.00019426827,0.00014453915,0.0004515331,0.00018015085,0.000009139117,0.0000071479517,0.0010020618,0.62470335,0.045193538,0.28684968,0.04106124,0.00020336169],"about_ca_topic_score_codex":0.000033424436,"about_ca_topic_score_gemma":0.000074995405,"teacher_disagreement_score":0.97208714,"about_ca_system_score_codex":0.00015755149,"about_ca_system_score_gemma":0.00009743066,"threshold_uncertainty_score":0.7304291},"labels":[],"label_agreement":null},{"id":"W4415556168","doi":"10.1016/j.apr.2025.102792","title":"Understanding the agriculture sectors of greenhouse gas emissions prediction in the global scenario: Insights from explainable artificial intelligence (XAI)","year":2025,"lang":"en","type":"article","venue":"Atmospheric Pollution Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Greenhouse gas; Artificial neural network; Agriculture; Convolutional neural network; Nitrous oxide; Methane; Carbon dioxide; Greenhouse effect","score_opus":0.11313121731718716,"score_gpt":0.3404388848123226,"score_spread":0.22730766749513542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415556168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11816924,0.0007612366,0.8646174,0.008229207,0.000618615,0.0010350756,0.000017578706,0.00013566254,0.0064159743],"genre_scores_gemma":[0.9976074,0.0001265553,0.0016295172,0.00020793935,0.000082621365,0.00008589381,0.000005187376,0.0000076081765,0.00024729702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995591,0.0011848132,0.0006535663,0.00062217173,0.0012144475,0.0007339892],"domain_scores_gemma":[0.9975675,0.00088204676,0.00013735206,0.0010134683,0.00029198933,0.00010764493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017865021,0.00021972637,0.00023299466,0.000051518273,0.0012118475,0.0003717891,0.0022796325,0.00020310568,0.00005131777],"category_scores_gemma":[0.00070413697,0.00013349412,0.00011178421,0.0075279814,0.0005053717,0.0006249661,0.00052922464,0.0007665778,0.00004464744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087583,0.000446732,0.0019548207,0.000030557574,0.0000522846,0.00004021521,0.008382882,0.022562714,0.0028951827,0.9483168,0.004969803,0.010260432],"study_design_scores_gemma":[0.00012084382,0.0002615087,0.0062950156,0.00030629226,0.00001727855,0.000008267158,0.04605551,0.2512486,0.009275728,0.68342906,0.002727096,0.00025478343],"about_ca_topic_score_codex":0.009348509,"about_ca_topic_score_gemma":0.005116485,"teacher_disagreement_score":0.87943816,"about_ca_system_score_codex":0.0011542817,"about_ca_system_score_gemma":0.0005267015,"threshold_uncertainty_score":0.99724835},"labels":[],"label_agreement":null},{"id":"W4415620636","doi":"10.3390/informatics12040119","title":"Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis","year":2025,"lang":"en","type":"article","venue":"Informatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; London Health Sciences Centre; Lawson Health Research Institute; Western University","funders":"","keywords":"Workflow; Interpretability; Usability; Key (lock); USable; Trustworthiness; Interface (matter); Decision support system","score_opus":0.0760906994569553,"score_gpt":0.438377455874188,"score_spread":0.36228675641723274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415620636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012367537,0.030419724,0.9496917,0.0037169962,0.0013203009,0.0021916286,0.000024947423,0.00019531972,0.011202631],"genre_scores_gemma":[0.058276355,0.35268438,0.5491302,0.024494246,0.0006929344,0.0027423427,0.00006395864,0.00008899706,0.011826582],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970112,0.00020534138,0.0013926473,0.00027148725,0.00055115373,0.0005681902],"domain_scores_gemma":[0.99354905,0.0038501471,0.0001796951,0.0010396208,0.0012204379,0.00016103906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007943784,0.00017560528,0.00043850334,0.00037872302,0.0004125174,0.0009877493,0.0011906767,0.00020156772,0.000007197791],"category_scores_gemma":[0.0060759047,0.00014648489,0.000106692176,0.0012710931,0.00012173606,0.0017736935,0.0006064209,0.00044194298,0.000115144314],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004013002,0.00009151412,0.00024711766,0.007733461,0.000039766957,0.000025281443,0.0025511337,0.0000641453,0.0000047623475,0.21540375,0.5699107,0.20388824],"study_design_scores_gemma":[0.00016635082,0.0002171541,0.000030757496,0.010208645,0.000022776492,0.000038663715,0.0010252569,0.11343751,0.00083479396,0.012540857,0.86121905,0.0002581573],"about_ca_topic_score_codex":0.000010305533,"about_ca_topic_score_gemma":0.0000040546815,"teacher_disagreement_score":0.4005615,"about_ca_system_score_codex":0.00008715625,"about_ca_system_score_gemma":0.00031319878,"threshold_uncertainty_score":0.95248896},"labels":[],"label_agreement":null},{"id":"W4415682779","doi":"10.18280/mmep.120905","title":"XGRL-TCP: An Explainable Graph-Based Reinforcement Learning Framework for Test Case Prioritization in CI","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Prioritization; Reinforcement learning; Key (lock); Action (physics); Matching (statistics)","score_opus":0.03517078771299631,"score_gpt":0.27179511827953307,"score_spread":0.23662433056653676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415682779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009417181,0.0005395075,0.9877228,0.0003454935,0.00022600027,0.001323617,0.0000023446255,0.00027129462,0.00015177282],"genre_scores_gemma":[0.70657545,0.00008409858,0.2927189,0.0000464629,0.00004453768,0.0003088933,0.000005971107,0.000042852236,0.00017285044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653,0.00006119368,0.0011698793,0.00089449936,0.0003082809,0.0010361682],"domain_scores_gemma":[0.9971155,0.0016346748,0.00015594006,0.0006073547,0.00022752017,0.00025900485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001605348,0.000500746,0.00059013464,0.0006208839,0.0005027521,0.0007507237,0.00042789822,0.0003644126,0.000012863428],"category_scores_gemma":[0.00094903586,0.00055535923,0.00011567268,0.0012280969,0.000081301405,0.0006379322,0.00014847967,0.00070533494,0.000008383943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010594311,0.00019296915,0.000020760877,0.0025550872,0.000014287361,0.000049998103,0.0020968376,0.7285076,0.00009061546,0.26463208,0.000002396587,0.001826807],"study_design_scores_gemma":[0.00026269225,0.000326515,5.0402576e-7,0.0028962868,0.000033885062,0.000028064132,0.00030022924,0.81078255,0.001287235,0.1835138,0.00012390569,0.0004443123],"about_ca_topic_score_codex":0.000094938674,"about_ca_topic_score_gemma":0.000007224098,"teacher_disagreement_score":0.6971583,"about_ca_system_score_codex":0.00016911303,"about_ca_system_score_gemma":0.00012484431,"threshold_uncertainty_score":0.9996898},"labels":[],"label_agreement":null},{"id":"W4415743958","doi":"10.1109/iv68685.2025.00047","title":"A Solution for Explainable AI and Visual Knowledge Discovery","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Mitacs","keywords":"Sign (mathematics); Waterfall; Waterfall model; Value (mathematics); Bar (unit)","score_opus":0.024619221047159155,"score_gpt":0.3427587886521709,"score_spread":0.3181395676050118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415743958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005113947,0.0033052024,0.96531683,0.0063998266,0.0022576323,0.0013109655,0.000006740692,0.00015291439,0.01613592],"genre_scores_gemma":[0.9006976,0.00025274267,0.0073564597,0.0014519267,0.00022483211,0.00024907445,0.000004286267,0.000023035715,0.08974006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963211,0.0001619748,0.00077682274,0.0013158459,0.0002303086,0.0011939397],"domain_scores_gemma":[0.9979183,0.0005911512,0.00013410048,0.0005973829,0.0005587733,0.00020028833],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011093637,0.0004464127,0.00048781963,0.0004949188,0.0011989807,0.00198484,0.00076491275,0.00026376863,0.000045529767],"category_scores_gemma":[0.00040384993,0.00045648805,0.00019889754,0.0014166075,0.0003477461,0.004066853,0.0011853927,0.00026881072,0.00012185149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116495234,0.00054065726,0.00017036016,0.00041811168,0.000067113746,0.0000062935296,0.0016322515,0.0000568994,0.0027330448,0.65250134,0.014616624,0.3271408],"study_design_scores_gemma":[0.00039329418,0.00053529226,0.00011818513,0.00024246854,0.00005382285,0.000005650997,0.0008275168,0.8678088,0.05307028,0.042721376,0.033731822,0.0004914637],"about_ca_topic_score_codex":0.0004297556,"about_ca_topic_score_gemma":0.0005767454,"teacher_disagreement_score":0.95796037,"about_ca_system_score_codex":0.00029622583,"about_ca_system_score_gemma":0.0009037989,"threshold_uncertainty_score":0.9997887},"labels":[],"label_agreement":null},{"id":"W4415758623","doi":"10.1007/978-3-031-91379-2_5","title":"Batch-Integrated Gradients: A Library for Explaining Temporal Health Data","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Interpretability; Deep learning; Temporal database; Simple (philosophy); Feature (linguistics); Artificial neural network","score_opus":0.0960912429376613,"score_gpt":0.3159174342750721,"score_spread":0.21982619133741077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415758623","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.6305984e-7,0.0007175785,0.64628154,0.0056468872,0.0011470319,0.0010392389,0.0004942801,0.00093318714,0.34373957],"genre_scores_gemma":[0.00012424428,0.00027570204,0.19821073,0.00467637,0.00022706174,0.000054499327,0.0022992543,0.0000808784,0.7940513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611163,0.00005310278,0.0009990521,0.0016894182,0.00039274045,0.00075407437],"domain_scores_gemma":[0.9954339,0.00044412608,0.0004387821,0.0032390424,0.00015426354,0.000289848],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006731344,0.00057412195,0.00075588207,0.00049975456,0.00037182018,0.0006003101,0.0053850953,0.00030589773,0.0003022806],"category_scores_gemma":[0.000121012585,0.00053185347,0.00018368168,0.0002516525,0.00009430561,0.0023090905,0.0023462847,0.00049763924,0.00018786344],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001250655,0.00002069692,0.0000055345704,0.00007764197,0.000045942543,0.000017156011,0.00017740452,0.0000031883765,5.738572e-7,0.6419838,0.29262838,0.065027185],"study_design_scores_gemma":[0.00011370126,0.0002100684,4.968253e-7,0.0005280345,0.0000115418125,0.000006228698,0.000110032306,0.045769792,0.0001224357,0.09057846,0.8620623,0.0004869582],"about_ca_topic_score_codex":0.00031889137,"about_ca_topic_score_gemma":0.00029634318,"teacher_disagreement_score":0.56943387,"about_ca_system_score_codex":0.00014335594,"about_ca_system_score_gemma":0.0017102653,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W4415775588","doi":"10.1101/2025.07.18.664723","title":"Identifying intervention strategies from machine learning models with COALA: a counterfactual optimization framework","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Interpretability; Counterfactual thinking; Counterfactual conditional; Feature (linguistics); Psychological intervention; Replicate; Focus (optics); Biomedicine","score_opus":0.03052836204450768,"score_gpt":0.25418553221458406,"score_spread":0.22365717017007639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415775588","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04952882,0.0012190364,0.9463037,0.00013244881,0.0011435382,0.00057582185,0.00009034274,0.0009766691,0.000029617058],"genre_scores_gemma":[0.7779979,0.00021655248,0.22136325,0.00007937488,0.00014155664,0.00013272431,0.0000017146244,0.00005626826,0.000010677949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959997,0.00033278984,0.0007909343,0.0015618294,0.0006790862,0.0006356693],"domain_scores_gemma":[0.99649066,0.00023844467,0.0007124993,0.0015673139,0.00080991175,0.00018114776],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000702166,0.00067493797,0.0006282978,0.00046518992,0.00040111493,0.0025508762,0.0018464308,0.00058542565,0.000052680938],"category_scores_gemma":[0.00019771686,0.00071550644,0.00017179271,0.00092432636,0.00012220861,0.0020189488,0.0014283932,0.0016351788,0.00003664607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060079838,0.00018089864,0.0007470313,0.00033452344,0.00027720255,0.000072590534,0.00034108895,0.9469586,0.005318799,0.045668986,0.000022972597,0.000017248118],"study_design_scores_gemma":[0.00022362602,0.00009945729,0.00035582567,0.0025888947,0.0000984382,2.0001728e-8,0.000088183464,0.94706976,0.047677614,0.0008124783,0.00011375213,0.0008719497],"about_ca_topic_score_codex":0.00112996,"about_ca_topic_score_gemma":0.00004805015,"teacher_disagreement_score":0.7284691,"about_ca_system_score_codex":0.00041350618,"about_ca_system_score_gemma":0.00068422867,"threshold_uncertainty_score":0.9995296},"labels":[],"label_agreement":null},{"id":"W4415794686","doi":"10.1145/3772071","title":"Designing and Personalising Hybrid Health Explanations for Lay Users","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"Modalities; Set (abstract data type); Modality (human–computer interaction); Preference; Coaching; Recommender system; Feature (linguistics); Design science; Preference elicitation","score_opus":0.048926140005219804,"score_gpt":0.33782373632704654,"score_spread":0.28889759632182677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415794686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026179976,0.0003899587,0.9889596,0.00428284,0.0020097906,0.0011221645,0.000039580984,0.00020754086,0.00037050038],"genre_scores_gemma":[0.96990556,0.00012325193,0.027375743,0.0007962206,0.000052087664,0.0005070798,0.000008072915,0.000024401383,0.0012075793],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976964,0.00023646752,0.00063167705,0.0007039818,0.00025628993,0.00047519864],"domain_scores_gemma":[0.99667156,0.0019215944,0.00021165978,0.0007068298,0.0003372495,0.00015112325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065303774,0.00028063948,0.00035496528,0.0006709271,0.0008125057,0.00047931308,0.0008003167,0.00006488048,0.000015261765],"category_scores_gemma":[0.00022319965,0.00028764125,0.00015744084,0.000518534,0.00007383039,0.0009448413,0.00002821053,0.00031058778,0.00003891152],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005895295,0.0015211176,0.000311425,0.0008388094,0.0016706397,0.000042747488,0.036291353,0.08004063,0.008265722,0.22993326,0.0076487404,0.632846],"study_design_scores_gemma":[0.0008889013,0.001635473,0.00010572033,0.0034256135,0.00012465674,0.00018408494,0.052829288,0.30900556,0.5252269,0.01406732,0.09092562,0.0015808977],"about_ca_topic_score_codex":0.0007304025,"about_ca_topic_score_gemma":0.00010468018,"teacher_disagreement_score":0.96728754,"about_ca_system_score_codex":0.0005403052,"about_ca_system_score_gemma":0.0002013853,"threshold_uncertainty_score":0.99995756},"labels":[],"label_agreement":null},{"id":"W4415834490","doi":"10.21203/rs.3.rs-7973071/v1","title":"The Impact of Network Preprocessing Structure Design on XAI Explanation Quality","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"QUAD Engineering (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center","keywords":"Interpretability; Preprocessor; Context (archaeology); Data pre-processing; Quality (philosophy); Key (lock); Payload (computing); Similarity (geometry)","score_opus":0.21195626000857767,"score_gpt":0.511208179433281,"score_spread":0.2992519194247033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415834490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03628544,0.0022242211,0.9492951,0.0017878849,0.0008459061,0.003189956,0.00010155008,0.0002692943,0.00600067],"genre_scores_gemma":[0.9935498,0.0001883338,0.0054311994,0.000022575747,0.0002488002,0.00010961065,0.000019815223,0.000015011061,0.00041480095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99299043,0.0028082049,0.0006590814,0.00093927386,0.0016927402,0.0009102478],"domain_scores_gemma":[0.99157774,0.004051772,0.00034713952,0.0022574225,0.0016483569,0.00011758609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077511556,0.00028593544,0.00037316774,0.00032547678,0.0008983474,0.00089439435,0.0031978537,0.00033909688,0.000023781942],"category_scores_gemma":[0.0026343598,0.00019657346,0.00022724738,0.0014882889,0.00021806434,0.00029186296,0.002033575,0.0017008976,0.00001589775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024143961,0.000117023854,0.0011177594,0.00065636245,0.00012602686,0.000012415097,0.0030460912,0.8316726,0.00036762064,0.06931557,0.009043972,0.08428311],"study_design_scores_gemma":[0.00012728288,0.00057152216,0.008797643,0.0021804287,0.0000073394976,0.00000185292,0.0006055408,0.37516004,0.025630856,0.5861062,0.0003346939,0.0004766159],"about_ca_topic_score_codex":0.0018399224,"about_ca_topic_score_gemma":0.00019938803,"teacher_disagreement_score":0.9572644,"about_ca_system_score_codex":0.0006464395,"about_ca_system_score_gemma":0.0020454326,"threshold_uncertainty_score":0.8624665},"labels":[],"label_agreement":null},{"id":"W4415967295","doi":"10.48550/arxiv.2510.18148","title":"Extracting Rule-based Descriptions of Attention Features in Transformers","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Security token; Transformer; Interpretation (philosophy); Word (group theory); Value (mathematics); Pattern recognition (psychology)","score_opus":0.07306531986248128,"score_gpt":0.317219122067993,"score_spread":0.24415380220551175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415967295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6931932,0.00055037584,0.29749388,0.0018947821,0.0022770802,0.0009967221,0.000030602157,0.00010652547,0.003456811],"genre_scores_gemma":[0.9903468,0.00030190722,0.0072935633,0.00025278365,0.00011012127,0.00015997901,0.000036239686,0.0000305741,0.0014680537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99405485,0.0005064478,0.0019457601,0.0016838487,0.00072054984,0.001088532],"domain_scores_gemma":[0.9963424,0.0006314308,0.0008165148,0.0013929093,0.00061238493,0.00020432593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017102218,0.00071303744,0.00090872514,0.00123067,0.00044221026,0.00025508902,0.0020653827,0.00071544567,0.00014857951],"category_scores_gemma":[0.00049871864,0.00083801564,0.0006775933,0.0021147956,0.00036883386,0.00113687,0.00050434493,0.0019267139,0.00011977151],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033144097,0.0023458765,0.64170504,0.0024864317,0.00027730077,0.00015732963,0.009980448,0.072140075,0.10852188,0.011293187,0.00018398576,0.15057702],"study_design_scores_gemma":[0.00090984843,0.00028978204,0.61439073,0.0059474627,0.0002362059,0.000013205456,0.0043996596,0.10152769,0.26521796,0.004466878,0.0008810121,0.0017195911],"about_ca_topic_score_codex":0.0035318022,"about_ca_topic_score_gemma":0.0018775957,"teacher_disagreement_score":0.29715356,"about_ca_system_score_codex":0.0005496085,"about_ca_system_score_gemma":0.0012749401,"threshold_uncertainty_score":0.99940705},"labels":[],"label_agreement":null},{"id":"W4415984007","doi":"10.1080/13675567.2025.2584309","title":"Leveraging AI and blockchain for GVC resilience: a case study approach","year":2025,"lang":"en","type":"article","venue":"International Journal of Logistics Research and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Blockchain; Supply chain; Key (lock); Production (economics)","score_opus":0.1344025690496368,"score_gpt":0.4680133779068803,"score_spread":0.3336108088572435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415984007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018698543,0.00023142944,0.9765734,0.0032644419,0.00007256414,0.00047529206,0.000005299558,0.000009646291,0.0006693728],"genre_scores_gemma":[0.9747695,0.000059136444,0.024493024,0.00013277975,0.000122884,0.00011719887,6.858695e-7,0.0000033931915,0.00030139726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870753,0.000075270655,0.00034900891,0.00023711477,0.0004355386,0.00019554475],"domain_scores_gemma":[0.99694246,0.00073844317,0.000095133444,0.00020344504,0.0018967723,0.00012375489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016433361,0.00007077943,0.00011378157,0.00046968932,0.00034205127,0.00042260473,0.00078068685,0.000032304342,0.0000013413916],"category_scores_gemma":[0.0006302581,0.00006312503,0.000026567324,0.00039699904,0.0002171087,0.00013724802,0.000329777,0.00027996834,8.5887797e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000771608,0.0012575252,0.0027667412,0.00004310478,0.00017448833,0.000560311,0.0025422268,0.0035158966,0.000751475,0.85270774,0.001956659,0.1336467],"study_design_scores_gemma":[0.0010090368,0.0007839349,0.00043040363,0.00006979148,0.000025246194,0.0026412788,0.018755857,0.4951404,0.0014745189,0.46615282,0.013281657,0.0002350624],"about_ca_topic_score_codex":0.000113630944,"about_ca_topic_score_gemma":0.000023761626,"teacher_disagreement_score":0.95607096,"about_ca_system_score_codex":0.000072647024,"about_ca_system_score_gemma":0.00023953513,"threshold_uncertainty_score":0.4075187},"labels":[],"label_agreement":null},{"id":"W4416005966","doi":"10.5465/amproc.2025.10937abstract","title":"The Promise and Limitation of Explainable AI in Smart Cities: A Sociotechnical Perspective","year":2025,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sociotechnical system; Perspective (graphical); Heuristics; Context (archaeology); Work (physics); Function (biology); Cognition","score_opus":0.017407614075813472,"score_gpt":0.30118000860372796,"score_spread":0.2837723945279145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416005966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6741367,0.0022045816,0.051237516,0.16932364,0.00015561741,0.004109382,0.0000013095325,0.00031170552,0.09851954],"genre_scores_gemma":[0.9933262,0.0005325848,0.00397765,0.0005123697,0.000007826331,0.00011889627,9.597719e-8,0.0000050191434,0.0015193637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987744,0.000016575583,0.00037789234,0.00033100188,0.00024844115,0.00025165104],"domain_scores_gemma":[0.999457,0.00014962308,0.00014992563,0.0000904098,0.00012761021,0.000025438727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010126603,0.00010859438,0.00016636537,0.00027234774,0.00013778872,0.000083341576,0.00072819367,0.000087334025,9.1405144e-7],"category_scores_gemma":[0.00017778823,0.00009333291,0.00003775646,0.00080359075,0.00022539058,0.0007349978,0.0005090388,0.00022370166,0.0000018787906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022399028,0.00004195282,0.0005332456,0.00017797599,0.000026796237,5.450894e-7,0.0029691705,0.000007912035,0.00056269905,0.98590094,0.0019752767,0.0077811047],"study_design_scores_gemma":[0.0004594435,0.00015133288,0.015784469,0.00043537928,0.00003386746,0.0000013596228,0.0377016,0.014293074,0.04225931,0.87701476,0.011632166,0.00023323069],"about_ca_topic_score_codex":0.00003740267,"about_ca_topic_score_gemma":0.0000027721119,"teacher_disagreement_score":0.3191895,"about_ca_system_score_codex":0.00010824196,"about_ca_system_score_gemma":0.000022148064,"threshold_uncertainty_score":0.38060054},"labels":[],"label_agreement":null},{"id":"W4416017596","doi":"10.1145/3746252.3761591","title":"Advances in Financial AI: Innovations, Risk, and Responsibility in the Era of LLMs","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège Boréal","funders":"","keywords":"Relevance (law); Event (particle physics); Financial sector; Financial services; Financial market; Core (optical fiber); Risk management","score_opus":0.012728274445534541,"score_gpt":0.30725071922131747,"score_spread":0.29452244477578293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416017596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7661121,0.00055109884,0.22219576,0.005272641,0.000122036494,0.0002878995,0.0000013846488,0.00002271322,0.005434373],"genre_scores_gemma":[0.9934325,0.00013604717,0.005538801,0.00081869663,0.0000053259632,0.000016670721,2.2982078e-7,9.577091e-7,0.000050763407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998968,0.000214668,0.00033250908,0.00022910659,0.00011635108,0.00013936867],"domain_scores_gemma":[0.9989318,0.00053561345,0.000051811166,0.00038487426,0.000087374145,0.0000085256615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016345918,0.000060679115,0.00010782769,0.00017927395,0.00006119464,0.000041171385,0.00046689346,0.000037170623,0.000004448056],"category_scores_gemma":[0.001242827,0.000044583212,0.000013362618,0.002157761,0.0000880141,0.00057492766,0.00013037058,0.00023623266,0.0000023958817],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023700664,0.00007736924,0.09050647,0.000011589608,4.5420202e-7,0.0000029290215,0.0013585398,0.00019606514,0.0001145812,0.7419586,0.00012927211,0.16562042],"study_design_scores_gemma":[0.00016729678,0.000078621386,0.4290438,0.00006138667,0.0000010803524,9.544618e-7,0.00075739826,0.016868768,0.01230514,0.5365157,0.004085101,0.00011476057],"about_ca_topic_score_codex":0.00077966903,"about_ca_topic_score_gemma":0.006513239,"teacher_disagreement_score":0.33853734,"about_ca_system_score_codex":0.000025027904,"about_ca_system_score_gemma":0.00016243986,"threshold_uncertainty_score":0.363454},"labels":[],"label_agreement":null},{"id":"W4416023900","doi":"10.48550/arxiv.2511.04053","title":"Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute for Catastrophic Loss Reduction","keywords":"Context (archaeology); Vulnerability (computing); Linear subspace; ENCODE; Language model; Hierarchy; Correlation; Numerical modeling","score_opus":0.11026174088064708,"score_gpt":0.3656238299806145,"score_spread":0.2553620890999674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416023900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28879467,0.0018170769,0.7018207,0.00155783,0.0030892636,0.0012066191,0.0001557141,0.00037192192,0.0011862207],"genre_scores_gemma":[0.974957,0.0005187409,0.020113435,0.0018045626,0.00032002077,0.0002626696,0.00010664015,0.00008126177,0.0018356764],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881945,0.0011781629,0.0029235163,0.003613855,0.0009799731,0.003109947],"domain_scores_gemma":[0.99289924,0.0018139483,0.0010851211,0.0030930236,0.00070549594,0.0004031464],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.003293583,0.0014954768,0.0020538403,0.0006820965,0.0008217056,0.0009776538,0.005482231,0.0011351487,0.00025691112],"category_scores_gemma":[0.0023786812,0.0017054166,0.00074605754,0.002702566,0.00035138856,0.0027322036,0.010230469,0.0038055591,0.00096152024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001430482,0.002335582,0.6804133,0.0011544214,0.00051868305,0.0016398431,0.12679306,0.116345614,0.0025961574,0.06221028,0.0004394449,0.005410583],"study_design_scores_gemma":[0.00082699215,0.00013919035,0.0060525816,0.0036535135,0.00008402782,0.000024083502,0.008476486,0.94795126,0.026261607,0.0030629064,0.0014519602,0.0020153672],"about_ca_topic_score_codex":0.004375121,"about_ca_topic_score_gemma":0.00067486096,"teacher_disagreement_score":0.8316057,"about_ca_system_score_codex":0.001414426,"about_ca_system_score_gemma":0.0009957838,"threshold_uncertainty_score":0.9998986},"labels":[],"label_agreement":null},{"id":"W4416030400","doi":"10.48550/arxiv.2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Rationalization (economics); Confabulation (neural networks); Sonnet; Face (sociological concept); Analogical reasoning; Psychology of reasoning","score_opus":0.0654847306672032,"score_gpt":0.3068589928171223,"score_spread":0.2413742621499191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416030400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7299057,0.00090922765,0.22957224,0.015387976,0.0021906001,0.0012260734,0.00002744063,0.00028879408,0.020491946],"genre_scores_gemma":[0.98612064,0.00015717227,0.008642329,0.0032796196,0.00019336675,0.0001251691,0.000005951462,0.000018600456,0.0014571674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99672025,0.00032315552,0.00074170396,0.0010492537,0.0005529678,0.0006126872],"domain_scores_gemma":[0.99637157,0.00054895,0.00037204754,0.0024334935,0.00020235154,0.00007161722],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015531166,0.0003897302,0.000509059,0.00031849334,0.00018360451,0.00019226188,0.0044267084,0.000327257,0.000028634498],"category_scores_gemma":[0.00045683482,0.00032754982,0.00023740511,0.0010825046,0.00013640148,0.00031648634,0.0025224031,0.001143774,0.0001462186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008659611,0.0007875855,0.3405605,0.00090595684,0.00027364597,0.0004734154,0.08137622,0.0071202703,0.0016958328,0.4679332,0.012102943,0.08668382],"study_design_scores_gemma":[0.00082590344,0.0004517064,0.14112446,0.005596163,0.00018177606,0.00005311712,0.006310767,0.2662946,0.39647266,0.06647579,0.112284444,0.003928623],"about_ca_topic_score_codex":0.0012662434,"about_ca_topic_score_gemma":0.00025266962,"teacher_disagreement_score":0.40145743,"about_ca_system_score_codex":0.00012476757,"about_ca_system_score_gemma":0.00035850285,"threshold_uncertainty_score":0.9999176},"labels":[],"label_agreement":null},{"id":"W4416035385","doi":"10.18653/v1/2025.emnlp-main.1641","title":"REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research","keywords":"Action (physics); Feature (linguistics); Identification (biology); Perspective (graphical); Key (lock)","score_opus":0.02425595569452285,"score_gpt":0.27496898561305166,"score_spread":0.25071302991852884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20882854,0.0032114247,0.7797523,0.0013987526,0.00073185674,0.00072109693,6.5934137e-7,0.00015519091,0.0052001774],"genre_scores_gemma":[0.9782125,0.00035680976,0.018308232,0.0004666115,0.0001267102,0.000032002263,5.6490126e-7,0.000036600093,0.002460015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509734,0.0005640296,0.0013636688,0.0011914578,0.00064210326,0.0011413735],"domain_scores_gemma":[0.99415755,0.003303395,0.0006609427,0.0013034989,0.00038099472,0.00019359759],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0025671166,0.00056509126,0.0007364278,0.00040865835,0.0015834632,0.00071087596,0.0016702407,0.0002191509,0.000015259062],"category_scores_gemma":[0.0036010772,0.00047375626,0.0002073067,0.0018369488,0.00038776314,0.0012595283,0.002613356,0.0011094873,0.000014090025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004286992,0.00023723421,0.0110802185,0.0022138495,0.00022921816,0.0000659706,0.022436827,0.40562767,0.073296666,0.0671848,0.0001488239,0.41743585],"study_design_scores_gemma":[0.00019461664,0.00014781987,0.0009111031,0.0029631576,0.00012598048,0.000011874997,0.0014333292,0.9304517,0.057907578,0.005414994,0.00005964441,0.0003782093],"about_ca_topic_score_codex":0.0010353312,"about_ca_topic_score_gemma":0.00029327153,"teacher_disagreement_score":0.7693839,"about_ca_system_score_codex":0.00013082399,"about_ca_system_score_gemma":0.00037472145,"threshold_uncertainty_score":0.9997714},"labels":[],"label_agreement":null},{"id":"W4416035479","doi":"10.18653/v1/2025.emnlp-main.1563","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Bundesministerium für Bildung und Forschung; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Natural language; Natural (archaeology); Empirical research; Consequentialism; On Language","score_opus":0.10660886907344636,"score_gpt":0.34412832543448185,"score_spread":0.2375194563610355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019291492,0.001967784,0.83579457,0.009730534,0.0018718033,0.00072385865,0.0000202571,0.00050713494,0.13009256],"genre_scores_gemma":[0.925128,0.00012451019,0.016907565,0.0055416916,0.00012331523,0.00005189352,0.0000037253915,0.000018259521,0.052101053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509615,0.00049208244,0.0010096661,0.0015049935,0.00060050987,0.0012965864],"domain_scores_gemma":[0.99660945,0.00044574798,0.0004050488,0.0017174566,0.00045932955,0.00036298527],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007969113,0.00056925946,0.0007678873,0.0003200212,0.0006142519,0.0012522633,0.0025111018,0.00044556957,0.0019030321],"category_scores_gemma":[0.00080596795,0.00045888076,0.0002930896,0.0018865375,0.0007920177,0.0014415052,0.0012199288,0.0006187659,0.00058053475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025862746,0.00042978098,0.00043073355,0.000102799044,0.000106992054,0.0024195812,0.0017502833,0.0019707896,0.0005235514,0.9328797,0.014867634,0.04425956],"study_design_scores_gemma":[0.00048873806,0.00022649924,0.00040508146,0.0003680177,0.000093291375,0.000100954276,0.00873291,0.8890575,0.02502593,0.07189124,0.0026748092,0.00093499915],"about_ca_topic_score_codex":0.00351863,"about_ca_topic_score_gemma":0.005652229,"teacher_disagreement_score":0.90583646,"about_ca_system_score_codex":0.00029569372,"about_ca_system_score_gemma":0.0008294838,"threshold_uncertainty_score":0.9997863},"labels":[],"label_agreement":null},{"id":"W4416036171","doi":"10.18653/v1/2025.emnlp-main.727","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tamkeen; York University; New York University Abu Dhabi","keywords":"Pipeline (software); Generalizability theory; Set (abstract data type); Training (meteorology); Base (topology); Quality (philosophy); Case-based reasoning","score_opus":0.012842702575389067,"score_gpt":0.2684944967031227,"score_spread":0.25565179412773364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416036171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29355207,0.0001397982,0.5602704,0.017985808,0.0007894685,0.00054635125,0.0000024043538,0.0008100583,0.12590362],"genre_scores_gemma":[0.93291193,0.0000032667929,0.049398486,0.00378584,0.00010725092,0.000032294527,0.0000047434423,0.000016867109,0.013739315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976072,0.000112611575,0.00054432376,0.00070754014,0.00028623937,0.0007421344],"domain_scores_gemma":[0.9989193,0.00013606268,0.00009321118,0.00065272115,0.00009104538,0.00010763072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019285,0.00023376153,0.00026792166,0.00042886805,0.00024603817,0.00031988297,0.0012069544,0.00012891938,0.000052594864],"category_scores_gemma":[0.0003237391,0.00022837702,0.00009908543,0.001547908,0.00010854996,0.00055633544,0.0004074632,0.00033005516,0.000042500837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013791837,0.000058993268,0.0033237808,0.0000338114,0.000022090488,0.00010328024,0.008605074,0.0017550553,0.0022197105,0.81024545,0.0042361794,0.1693828],"study_design_scores_gemma":[0.00063479616,0.0001411668,0.0017721026,0.00046279086,0.000012928779,0.000046943172,0.0059096427,0.8024481,0.0808024,0.049646124,0.057350848,0.00077218306],"about_ca_topic_score_codex":0.00036943416,"about_ca_topic_score_gemma":0.00039386426,"teacher_disagreement_score":0.80069304,"about_ca_system_score_codex":0.00017956168,"about_ca_system_score_gemma":0.00019957832,"threshold_uncertainty_score":0.93129444},"labels":[],"label_agreement":null},{"id":"W4416070485","doi":"10.48550/arxiv.2505.04627","title":"Is the end of Insight in Sight ?","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"HORIZON EUROPE Framework Programme; Fonds de recherche du Québec – Nature et technologies; European Commission","keywords":"Interpretability; Perspective (graphical); Outcome (game theory); TRACE (psycholinguistics); Cognition; Ideal (ethics); Artificial neural network","score_opus":0.07370824725669334,"score_gpt":0.3066526265678747,"score_spread":0.23294437931118134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416070485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8815481,0.0020687263,0.050513096,0.017292775,0.0026862163,0.0010240064,0.000021699901,0.00018178095,0.04466357],"genre_scores_gemma":[0.99512935,0.0002000565,0.0012265382,0.0012249261,0.00007970524,0.000059940387,0.000002850554,0.000009588936,0.0020670437],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978075,0.00017852291,0.00060502754,0.0007125818,0.0003350338,0.0003613246],"domain_scores_gemma":[0.9972048,0.0003929272,0.00024845678,0.0019278362,0.00017352357,0.000052472125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005465185,0.00025824585,0.0003678338,0.00026423362,0.00008997216,0.00008928075,0.00309529,0.0002348221,0.000093399256],"category_scores_gemma":[0.00018378878,0.00019977547,0.00016542149,0.00079529686,0.00018253353,0.00022919246,0.002819629,0.0007264574,0.00016955884],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050768693,0.0009064822,0.55785537,0.00092516805,0.0003186461,0.0002732731,0.06984581,0.0072722277,0.007106185,0.28844157,0.008008514,0.058995996],"study_design_scores_gemma":[0.00023986549,0.00011781039,0.11588075,0.0011029235,0.00004600314,0.00000553054,0.00055931736,0.034384746,0.68693936,0.08698543,0.072657384,0.0010808996],"about_ca_topic_score_codex":0.0012283461,"about_ca_topic_score_gemma":0.00044610794,"teacher_disagreement_score":0.6798332,"about_ca_system_score_codex":0.00010140817,"about_ca_system_score_gemma":0.00040463466,"threshold_uncertainty_score":0.8146607},"labels":[],"label_agreement":null},{"id":"W4416079975","doi":"10.1117/12.3095478","title":"Consistency and stability benchmarking of Grad-CAM, SHAP, and LIME for diffuse and focal brain MRI classification","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Benchmarking; Robustness (evolution); Consistency (knowledge bases); Stability (learning theory); Pipeline (software); Pattern recognition (psychology); Neuroimaging; Convolutional neural network","score_opus":0.05193027304978776,"score_gpt":0.3038734037802744,"score_spread":0.25194313073048663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416079975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47603917,0.0019017733,0.50722367,0.011798828,0.00033182304,0.0012899425,0.000020437048,0.00004608659,0.0013482877],"genre_scores_gemma":[0.98109424,0.00052770704,0.017541211,0.00047670695,0.00003812523,0.00005326448,0.0000033805404,0.000011309536,0.00025403936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664915,0.00024316438,0.0010336098,0.0012748396,0.00026111197,0.00053813175],"domain_scores_gemma":[0.9957893,0.0024993701,0.0002870333,0.0007597872,0.00044097242,0.0002235249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017493819,0.00034311702,0.0005587239,0.00025473055,0.0005475818,0.00046505887,0.00039994437,0.00022734964,0.000028410836],"category_scores_gemma":[0.0008409383,0.00034327156,0.00008689995,0.0006182452,0.0012736752,0.00082161534,0.00063301914,0.00020161379,0.0000011112736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013917498,0.00044931803,0.040028326,0.00090398174,0.000075539625,0.0000017856297,0.004017706,0.0000031452648,0.01518237,0.66778,0.00037109846,0.2710476],"study_design_scores_gemma":[0.00086868973,0.0008348051,0.060060564,0.00029088504,0.00010121496,0.000010626181,0.003336582,0.81522036,0.029866735,0.08760083,0.0012829336,0.00052576844],"about_ca_topic_score_codex":0.0003346802,"about_ca_topic_score_gemma":0.0006334486,"teacher_disagreement_score":0.8152172,"about_ca_system_score_codex":0.000074354495,"about_ca_system_score_gemma":0.0002742464,"threshold_uncertainty_score":0.99990195},"labels":[],"label_agreement":null},{"id":"W4416082371","doi":"10.36227/techrxiv.175735299.97215847/v2","title":"Responsible Agentic Reasoning and AI Agents: A Critical Survey","year":2025,"lang":"","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"HORIZON EUROPE Framework Programme; European Commission","keywords":"Trustworthiness; Audit; Automated reasoning; Perception; Knowledge representation and reasoning","score_opus":0.08589055885772025,"score_gpt":0.39037313808595014,"score_spread":0.3044825792282299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416082371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0142550375,0.0015865822,0.94379336,0.009332994,0.004972751,0.0012246574,0.0000785314,0.00039246245,0.024363639],"genre_scores_gemma":[0.8608889,0.0014733552,0.08046466,0.0064278883,0.00025800173,0.00016912188,0.000035568522,0.00006758054,0.050214935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98857874,0.0032309003,0.0017727878,0.0034888405,0.0011080027,0.001820739],"domain_scores_gemma":[0.98867965,0.0052354694,0.00026964524,0.0032384247,0.0017628815,0.00081391045],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007795226,0.0010131334,0.0012056929,0.00092323957,0.0011113829,0.0037295767,0.0032374253,0.0008380412,0.0012760112],"category_scores_gemma":[0.0154549945,0.0011178681,0.00031468298,0.0021074305,0.000896273,0.0013405115,0.010160068,0.0019772437,0.0006844953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003741393,0.00073695194,0.008712904,0.0011819293,0.00029858618,0.0006548481,0.005326456,0.0017152389,0.00019551809,0.928783,0.014760144,0.03726027],"study_design_scores_gemma":[0.00025401803,0.00033424073,0.020768149,0.0025850143,0.0001555077,0.000072748306,0.000655991,0.869245,0.0089530945,0.08781573,0.0071750353,0.00198548],"about_ca_topic_score_codex":0.008074521,"about_ca_topic_score_gemma":0.002490519,"teacher_disagreement_score":0.86752975,"about_ca_system_score_codex":0.00035485253,"about_ca_system_score_gemma":0.0028120573,"threshold_uncertainty_score":0.99963695},"labels":[],"label_agreement":null},{"id":"W4416184308","doi":"10.1109/acsos-c66519.2025.00041","title":"Self-Evaluation can Help Agents Meet Social Expectations","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reflection (computer programming); Test (biology); Surprise; Product (mathematics); Architecture; Sociotechnical system","score_opus":0.06218617163229865,"score_gpt":0.35510897531596236,"score_spread":0.2929228036836637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416184308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030096749,0.0007404178,0.60498,0.051823054,0.0064931815,0.0027821343,0.000019443103,0.0008282122,0.30223686],"genre_scores_gemma":[0.9791035,0.000041612053,0.010348133,0.0020802987,0.0003110919,0.00021342278,0.000011422359,0.000019143861,0.007871354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519426,0.0006964542,0.0009216417,0.0010828289,0.0012207183,0.0008840843],"domain_scores_gemma":[0.997184,0.00026945095,0.000249992,0.0008190113,0.0013388761,0.00013871644],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012803462,0.00039707168,0.00036575124,0.00055408705,0.0017584238,0.001020814,0.0014858935,0.0002452922,0.0009506011],"category_scores_gemma":[0.00042446132,0.00045338,0.00022778162,0.0029117712,0.00016568077,0.0010255008,0.0005844688,0.00024024791,0.0006910604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015037283,0.0007977358,0.0003676774,0.000097902055,0.0002614318,0.000016292755,0.059127636,0.0009238102,0.0003897748,0.7594786,0.064556904,0.11396714],"study_design_scores_gemma":[0.00036624528,0.000100718935,0.0008922095,0.000056627232,0.0001975651,0.000002381499,0.014250863,0.9023454,0.023812601,0.048221517,0.009179698,0.0005741649],"about_ca_topic_score_codex":0.0005455452,"about_ca_topic_score_gemma":0.002119891,"teacher_disagreement_score":0.9490068,"about_ca_system_score_codex":0.0009268608,"about_ca_system_score_gemma":0.0018214749,"threshold_uncertainty_score":0.9999627},"labels":[],"label_agreement":null},{"id":"W4416184344","doi":"10.1109/acsos-c66519.2025.00029","title":"A Reflective Architecture for LLM-Based Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reflection (computer programming); Architecture; Event (particle physics); Cognitive architecture; Reliability (semiconductor); Trustworthiness; Systems architecture; Key (lock)","score_opus":0.03268728511905356,"score_gpt":0.32750486842253923,"score_spread":0.2948175833034857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416184344","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045768742,0.0012075227,0.9422977,0.0086727515,0.004008516,0.0026776078,0.000018983776,0.00030742458,0.040351782],"genre_scores_gemma":[0.9027925,0.000013936406,0.066778876,0.003993782,0.0003077127,0.0007306031,0.000004998509,0.000038178943,0.025339423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956701,0.000328832,0.0008996674,0.0014632798,0.00044713428,0.0011910308],"domain_scores_gemma":[0.9956276,0.0014326882,0.000235105,0.001543696,0.00093924906,0.00022166838],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010990327,0.0005169658,0.00061332964,0.0006838109,0.0007743356,0.0011713848,0.0020189942,0.00032692828,0.00005540322],"category_scores_gemma":[0.0006175656,0.00048682198,0.00036516963,0.0024588455,0.00024388033,0.0003969738,0.00034631617,0.00042764348,0.00016454485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028364305,0.00056366203,0.00004542559,0.00070639397,0.00017243948,0.00002183669,0.0016415882,0.056060847,0.0035686959,0.8485868,0.010308988,0.07803968],"study_design_scores_gemma":[0.00039528418,0.0008057404,0.000016440661,0.00046265803,0.00005519395,0.00000419913,0.00063350116,0.7846515,0.109502524,0.0509507,0.052005276,0.0005169675],"about_ca_topic_score_codex":0.00072189467,"about_ca_topic_score_gemma":0.00044672555,"teacher_disagreement_score":0.9023348,"about_ca_system_score_codex":0.00043026338,"about_ca_system_score_gemma":0.0014855248,"threshold_uncertainty_score":0.9998655},"labels":[],"label_agreement":null},{"id":"W4416237636","doi":"10.1109/aiot66900.2025.00046","title":"Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Guelph; York University","funders":"","keywords":"Entropy (arrow of time); Leverage (statistics); Regularization (linguistics); Suite; Trustworthiness; Differential privacy; Information privacy","score_opus":0.010969360244178203,"score_gpt":0.26110460880284314,"score_spread":0.2501352485586649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416237636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020364784,0.000077177385,0.96424025,0.0049947407,0.00023698912,0.00046426526,2.7541967e-7,0.00046776686,0.027482037],"genre_scores_gemma":[0.8841227,0.000021880265,0.098211095,0.0012893326,0.00008045644,0.00017389015,0.000011829972,0.000015351856,0.016073449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982235,0.000080359816,0.0003759888,0.0006085602,0.0002897964,0.00042184044],"domain_scores_gemma":[0.99805814,0.00011098324,0.000102739716,0.00139728,0.0002508345,0.000080000864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042968063,0.00016454079,0.00015950268,0.00024204432,0.00034223852,0.0003350725,0.0019140553,0.00010007736,0.000091381844],"category_scores_gemma":[0.00020218534,0.0001663295,0.000057925463,0.0013597781,0.000038757546,0.0012697532,0.0009653416,0.00012361578,0.0002749373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058659452,0.000071247516,0.00048716622,0.000029818731,0.000011391699,0.000002972538,0.00032333913,0.0010832787,0.03385271,0.9322405,0.0030035365,0.028888207],"study_design_scores_gemma":[0.00007074767,0.000021967062,0.00025059513,0.000018281115,0.000004507065,0.0000017390489,0.00008537928,0.5653951,0.202778,0.21229778,0.0189234,0.0001525143],"about_ca_topic_score_codex":0.00027651677,"about_ca_topic_score_gemma":0.000036636076,"teacher_disagreement_score":0.8820862,"about_ca_system_score_codex":0.00015906311,"about_ca_system_score_gemma":0.000096813295,"threshold_uncertainty_score":0.678272},"labels":[],"label_agreement":null},{"id":"W4416288715","doi":"10.1007/978-3-032-09694-4_32","title":"A Survey of Explainable Intrusion Detection Systems in IoT Networks","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Intrusion detection system; Internet of Things; Key (lock); Bridge (graph theory); Intrusion prevention system; Network security","score_opus":0.02311809529734,"score_gpt":0.24178355474611404,"score_spread":0.21866545944877405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416288715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039909655,0.04138685,0.9495366,0.000033143588,0.003113049,0.0011805304,0.000005297305,0.00007514434,0.0042702914],"genre_scores_gemma":[0.99570376,0.0012612635,0.00011900882,0.000055851706,0.00035709748,0.00007183969,0.000021223508,0.00004349391,0.0023664425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962324,0.0004553266,0.0013472663,0.00094623247,0.000379633,0.0006391778],"domain_scores_gemma":[0.996515,0.0016037499,0.0005914673,0.00088644587,0.00030335586,0.00010001105],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023743587,0.0005437013,0.0011890808,0.0006825095,0.00013534355,0.0003189835,0.00075092143,0.0012062456,0.000003915656],"category_scores_gemma":[0.00022585763,0.0005136738,0.000094782255,0.00073359493,0.000094627954,0.0001689394,0.00036552807,0.0010661049,0.000002365543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047747315,0.000020251959,0.00078169716,0.00034403495,0.00003206625,0.000055984532,0.00023609053,0.9347403,0.000010375545,0.020144636,0.000084489315,0.043502316],"study_design_scores_gemma":[0.00015268412,0.00013205792,0.0002592247,0.0027136772,0.000011086046,0.000019514255,0.00001433862,0.99262106,0.000027386286,0.0016075847,0.0019976946,0.0004436875],"about_ca_topic_score_codex":0.013228724,"about_ca_topic_score_gemma":0.016145343,"teacher_disagreement_score":0.9953047,"about_ca_system_score_codex":0.0003023604,"about_ca_system_score_gemma":0.00011373111,"threshold_uncertainty_score":0.9997315},"labels":[],"label_agreement":null},{"id":"W4416329793","doi":"10.1088/3049-477x/ae209d","title":"Integrating explainability and bias detection in binary medical image classification: a systematic review","year":2025,"lang":"en","type":"article","venue":"Machine Learning Health","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Debiasing; Context (archaeology); Counterfactual thinking; Binary classification; Binary number; Feature (linguistics); Adversarial system","score_opus":0.03279360825787257,"score_gpt":0.348339967714137,"score_spread":0.3155463594562644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416329793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0258637,0.039550696,0.8665584,0.06328458,0.00036664004,0.0026052403,8.255127e-7,0.0005926495,0.0011772702],"genre_scores_gemma":[0.9886472,0.0028389886,0.004996246,0.0031261207,0.000019464269,0.00019345328,0.000004595872,0.000010709838,0.00016322333],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960713,0.0018158107,0.00091667724,0.00050852064,0.0003477791,0.00033991353],"domain_scores_gemma":[0.9982767,0.00070053694,0.00029132277,0.00048781346,0.00010358895,0.00014003846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068395184,0.00016265342,0.00052140217,0.000256818,0.0003543079,0.00011497315,0.00047468266,0.00007384148,0.000012483545],"category_scores_gemma":[0.006880408,0.00013929169,0.000047997863,0.0012558621,0.00006894595,0.00034359453,0.00023131,0.00077015656,0.000020567737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029975303,0.00043227678,0.018647151,0.64081186,0.000038315324,0.00010134649,0.007178006,0.00012086426,0.00043197692,0.093176335,0.0002213477,0.23881054],"study_design_scores_gemma":[0.00014863556,0.00023474185,0.0031913167,0.063257374,0.000010781313,0.000041243104,0.0008345012,0.929685,0.00012953841,0.0019500557,0.0003075912,0.00020920827],"about_ca_topic_score_codex":0.0015075416,"about_ca_topic_score_gemma":0.0010862151,"teacher_disagreement_score":0.9627835,"about_ca_system_score_codex":0.00032773925,"about_ca_system_score_gemma":0.0003519618,"threshold_uncertainty_score":0.8236988},"labels":[],"label_agreement":null},{"id":"W4416330618","doi":"10.3791/69125","title":"Ensemble of Temporal Weighting, Causal Inference, and Hierarchical Attribution towards SHAP Optimization","year":2025,"lang":"en","type":"article","venue":"Journal of Visualized Experiments","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Oakville-Trafalgar Memorial Hospital","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Interpretability; Weighting; Outlier; Causal inference; Normalization (sociology); Preprocessor; Boosting (machine learning); Bayesian probability","score_opus":0.042631444041659104,"score_gpt":0.42794175650051436,"score_spread":0.3853103124588553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416330618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19082023,0.00039617487,0.80729544,0.00028216073,0.00037377185,0.00011159531,0.0000010215356,0.000018513601,0.0007011011],"genre_scores_gemma":[0.91747564,0.00008987442,0.08216227,0.00010931047,0.000045163557,0.00000430885,0.0000019988647,0.0000058619435,0.00010556236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99816126,0.00017721405,0.0007999102,0.00020217469,0.00042974015,0.0002297192],"domain_scores_gemma":[0.998658,0.00009676511,0.000489313,0.00020191782,0.00044154076,0.000112463975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006310728,0.00014407322,0.00035123233,0.00036482158,0.00011333177,0.00012112326,0.00044885828,0.0000969791,0.000031091276],"category_scores_gemma":[0.00022123942,0.00012710568,0.00008460399,0.00051565544,0.00009147808,0.0007223771,0.00023194532,0.00017590198,0.0000021055264],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009341899,0.002189589,0.020403825,0.00019285327,0.00047614085,0.00013890011,0.0097982725,0.007600259,0.30104667,0.60139734,0.0020418307,0.05378015],"study_design_scores_gemma":[0.0010868928,0.0006743179,0.0010239081,0.0002662343,0.000024601699,0.000027660695,0.00025823418,0.13999538,0.84917593,0.0057735536,0.0014863921,0.00020689829],"about_ca_topic_score_codex":0.000060841983,"about_ca_topic_score_gemma":0.0000017845551,"teacher_disagreement_score":0.7266554,"about_ca_system_score_codex":0.0000743524,"about_ca_system_score_gemma":0.00027924377,"threshold_uncertainty_score":0.51832193},"labels":[],"label_agreement":null},{"id":"W4416341665","doi":"10.1109/aists66100.2025.11232814","title":"Agentic AI: A Paradigm Shift in Autonomous Decision-Making and Intelligent Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Intersection (aeronautics); Intelligent decision support system; Key (lock); Trustworthiness; Scalability; Paradigm shift; Intelligent agent","score_opus":0.02324647379602173,"score_gpt":0.3116334744232632,"score_spread":0.2883870006272415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416341665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036273625,0.009550139,0.94044834,0.0031164577,0.004187818,0.0013835191,0.000002569445,0.0001775214,0.0048600314],"genre_scores_gemma":[0.994272,0.0005048948,0.002830146,0.0013227958,0.000080195256,0.000088457775,6.0728183e-7,0.000027673377,0.00087322376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936717,0.0003982874,0.0020677957,0.0018451846,0.00061549316,0.0014015472],"domain_scores_gemma":[0.9959187,0.0017514554,0.0002698529,0.001638552,0.0001250495,0.00029637],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019369243,0.0006487625,0.0008878762,0.0014164012,0.0004891742,0.0027952164,0.0019845467,0.00035235396,0.000177563],"category_scores_gemma":[0.0005330058,0.0006619019,0.00018064077,0.0030444257,0.00032375884,0.0013509938,0.0016982629,0.00069514825,0.00048294975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005303985,0.00029803082,0.002945475,0.00023084623,0.00006064401,0.00037240985,0.0045000757,0.015021199,0.000015149079,0.7329488,0.0003697673,0.24318461],"study_design_scores_gemma":[0.00016066385,0.00014929227,0.002238411,0.0023569795,0.000032550655,0.000032645527,0.0009280529,0.7885397,0.0004791593,0.19949007,0.0049915933,0.0006008601],"about_ca_topic_score_codex":0.0016961193,"about_ca_topic_score_gemma":0.0016963851,"teacher_disagreement_score":0.9579984,"about_ca_system_score_codex":0.00069298816,"about_ca_system_score_gemma":0.00080232054,"threshold_uncertainty_score":0.99958324},"labels":[],"label_agreement":null},{"id":"W4416353039","doi":"10.2139/ssrn.5767066","title":"Lessons in AI Literacy and Explainability from Lucy and Ricky","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Literacy; sort; Adult literacy","score_opus":0.01416387573049721,"score_gpt":0.3116542392430538,"score_spread":0.2974903635125566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416353039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4584948,0.01993759,0.5006537,0.018980416,0.0007644028,0.0004752733,0.000018004795,0.00009810591,0.0005777225],"genre_scores_gemma":[0.98642737,0.00937369,0.0032517167,0.00030757833,0.00017054098,0.000029917494,0.0000041349326,0.000013464392,0.00042157984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956216,0.0003762334,0.0006533207,0.0009763484,0.00030966417,0.0020627836],"domain_scores_gemma":[0.9982741,0.0003462548,0.00025888518,0.0007704873,0.00019383554,0.00015643852],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002449648,0.00036957132,0.00049674325,0.0004191686,0.000269034,0.000940721,0.0012930774,0.0002916153,0.000007452335],"category_scores_gemma":[0.00030293257,0.00036871032,0.00010728835,0.00038528876,0.00011403734,0.00096547266,0.001755681,0.005470272,0.0000058740393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038596463,0.00016847752,0.006834614,0.00006469973,0.00010063623,0.00004918062,0.004942036,0.00029697217,0.000055665805,0.73992956,0.00004627077,0.24747328],"study_design_scores_gemma":[0.00018905834,0.000097108845,0.0024942432,0.00020634654,0.000018089535,0.000078909296,0.00058569113,0.015152672,0.00027382528,0.980021,0.0005518971,0.0003311521],"about_ca_topic_score_codex":0.0023403715,"about_ca_topic_score_gemma":0.0039701117,"teacher_disagreement_score":0.5279326,"about_ca_system_score_codex":0.0012970003,"about_ca_system_score_gemma":0.0038312313,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4416365576","doi":"10.64628/aam.74ych3cms","title":"Artificial intelligence is front and centre at COP30","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Front (military); Front and back ends; Focus (optics); Applications of artificial intelligence","score_opus":0.03247379579920854,"score_gpt":0.28826435624184993,"score_spread":0.25579056044264137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416365576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021159673,0.0038517453,0.8800797,0.03451647,0.003861672,0.0010424256,0.000022083406,0.0002888941,0.055177364],"genre_scores_gemma":[0.8954873,0.001100231,0.0116980905,0.0067692883,0.00022052215,0.000021142672,0.0000033204417,0.000032880078,0.08466719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9941202,0.00025074545,0.0014722418,0.0020312537,0.0006746108,0.0014509904],"domain_scores_gemma":[0.9965613,0.000528748,0.0002514134,0.0016812207,0.0005019451,0.0004753989],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008646705,0.00068443886,0.0006709972,0.00044668533,0.0011375792,0.001189868,0.0018364897,0.00038811954,0.0053561097],"category_scores_gemma":[0.0003045251,0.0007017926,0.00022304442,0.0013482253,0.000756174,0.0010105455,0.002934954,0.00049047533,0.0049965596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091956455,0.00029597874,0.0010116973,0.00011758665,0.00009370983,0.000070962524,0.0080924,0.00016348125,0.0013198623,0.48514932,0.020985378,0.48260766],"study_design_scores_gemma":[0.000044814784,0.00014811034,0.00013498586,0.00024210228,0.00006230419,0.000013488752,0.0025932528,0.3927894,0.45854336,0.11235499,0.032306414,0.00076677074],"about_ca_topic_score_codex":0.0008014675,"about_ca_topic_score_gemma":0.002008507,"teacher_disagreement_score":0.87432766,"about_ca_system_score_codex":0.00048598446,"about_ca_system_score_gemma":0.00044375943,"threshold_uncertainty_score":0.999847},"labels":[],"label_agreement":null},{"id":"W4416367125","doi":"10.1109/icoa66896.2025.11236830","title":"Multi-Armed Bandits-Based Optimization of Decision Trees","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Pruning; Decision tree; Overfitting; Benchmark (surveying); Probabilistic logic; Generalization; Tree (set theory); Incremental decision tree; Decision tree learning","score_opus":0.032938843794816916,"score_gpt":0.32014363556601005,"score_spread":0.2872047917711931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416367125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035639647,0.00047474352,0.98889655,0.0011456117,0.0016728662,0.00063460553,0.000005466192,0.00013069302,0.0034755187],"genre_scores_gemma":[0.5892119,0.000098288634,0.4081122,0.00045618587,0.000025415817,0.000016745289,0.0000037991103,0.00001237429,0.0020630949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963432,0.00022232844,0.0012756143,0.000932197,0.0006303221,0.0005963196],"domain_scores_gemma":[0.99618506,0.0010388251,0.00034005416,0.001342527,0.00093340693,0.00016015061],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009173339,0.000364915,0.00050994655,0.0007921989,0.00032887064,0.0003208904,0.0016640245,0.00026167298,0.00086069165],"category_scores_gemma":[0.00103401,0.00035329178,0.00023959621,0.0029463314,0.00027993336,0.00083720207,0.0004340829,0.0002030445,0.00011413453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107456326,0.00069124013,0.0006000083,0.000061171566,0.00003243669,0.000012724659,0.00036802658,0.8713548,0.0020679259,0.01200611,0.000882952,0.111815155],"study_design_scores_gemma":[0.0005408516,0.00018134472,0.00049454643,0.00033317637,0.000029726982,6.493657e-7,0.00017306113,0.82224953,0.17439881,0.00086484547,0.00048130585,0.00025216304],"about_ca_topic_score_codex":0.00036868418,"about_ca_topic_score_gemma":0.00043704855,"teacher_disagreement_score":0.58564794,"about_ca_system_score_codex":0.00017539677,"about_ca_system_score_gemma":0.0008082442,"threshold_uncertainty_score":0.99989194},"labels":[],"label_agreement":null},{"id":"W4416540783","doi":"10.2139/ssrn.5786806","title":"Explainable Artificial Intelligence and Machine Learning: Whatcha Talkin’ ’Bout, Willis?","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Counterfactual thinking; Structuring; Field (mathematics); Strengths and weaknesses; Artificial neural network; Deep learning; Comparability","score_opus":0.03398647871139915,"score_gpt":0.27487938527953154,"score_spread":0.2408929065681324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416540783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00954774,0.038152926,0.93700147,0.006847284,0.004308271,0.0013482393,0.000021342677,0.00031195587,0.0024607687],"genre_scores_gemma":[0.83163613,0.14268152,0.0032552301,0.00044226777,0.0016072706,0.00011141942,0.000029964474,0.00014085107,0.020095373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9782604,0.0016892935,0.0033796565,0.0032965753,0.0019095013,0.011464578],"domain_scores_gemma":[0.99254024,0.00090772053,0.002175143,0.0020028513,0.0014423688,0.0009316564],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.012965904,0.0020012849,0.0019613572,0.0016406988,0.0036922502,0.0045068515,0.0058968905,0.0012602564,0.00025752326],"category_scores_gemma":[0.00157409,0.0021277824,0.0008898688,0.002377168,0.00091550004,0.0027998479,0.0051409197,0.023934629,0.0003668354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00022317971,0.00039102774,0.00024264172,0.00019670192,0.0005267284,0.00013495686,0.0040024505,0.019856365,0.00017593744,0.62388825,0.000031522988,0.35033026],"study_design_scores_gemma":[0.00016580966,0.0015006206,0.000012476506,0.00092272076,0.0002227945,0.0014409336,0.011951053,0.17346786,0.006361813,0.79186696,0.010322006,0.0017649888],"about_ca_topic_score_codex":0.0024267356,"about_ca_topic_score_gemma":0.0049863006,"teacher_disagreement_score":0.9337462,"about_ca_system_score_codex":0.004539193,"about_ca_system_score_gemma":0.015853858,"threshold_uncertainty_score":0.9994817},"labels":[],"label_agreement":null},{"id":"W4416733323","doi":"10.1016/j.cjca.2025.11.032","title":"Feature Importance Bias: Addressing Interpretability Issues in Tree-Based Acute Myocardial Infarction Risk Models","year":2025,"lang":"en","type":"letter","venue":"Canadian Journal of Cardiology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Myocardial infarction; Feature (linguistics); Risk assessment; MEDLINE","score_opus":0.04002773415070752,"score_gpt":0.28089617457848914,"score_spread":0.24086844042778163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416733323","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024348963,0.003639502,0.3747902,0.6075297,0.0067578508,0.00049327675,0.00018576025,0.000048947633,0.0041198907],"genre_scores_gemma":[0.6082881,0.00092595816,0.015231611,0.3584953,0.015894996,0.000078209545,0.00013645741,0.00012807905,0.00082127773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956347,0.0014868808,0.00092706527,0.0006703239,0.00035528242,0.0009257683],"domain_scores_gemma":[0.99661756,0.00051726284,0.000856874,0.0010345135,0.00065296714,0.00032080762],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017050089,0.00044869693,0.0013668039,0.0015586029,0.00018643982,0.00028748176,0.0019863534,0.001285198,0.0000073413253],"category_scores_gemma":[0.0007858254,0.00043879845,0.00067552004,0.00078844465,0.0003082879,0.0007783071,0.0000849185,0.0041133948,0.0000065241097],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040982923,0.0000022646448,0.015943078,0.00005191087,0.00044644225,0.003273409,0.00052289193,0.055529226,0.000012048829,0.00022471155,0.90837115,0.015581881],"study_design_scores_gemma":[0.00037914343,0.00027763002,0.0027231867,0.0005721437,0.0002495988,0.000312163,0.000089876645,0.023511041,0.00018941995,0.01852462,0.952423,0.00074818847],"about_ca_topic_score_codex":0.004560659,"about_ca_topic_score_gemma":0.013921921,"teacher_disagreement_score":0.6058532,"about_ca_system_score_codex":0.0011863386,"about_ca_system_score_gemma":0.004984636,"threshold_uncertainty_score":0.9998064},"labels":[],"label_agreement":null},{"id":"W4416792504","doi":"10.1038/s41433-025-04138-w","title":"Can ‘Deep Research’ agents and general AI agentic systems autonomously perform systematic review and meta-analysis?","year":2025,"lang":"en","type":"article","venue":"Eye","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"MEDLINE; Precision medicine","score_opus":0.1005571165387217,"score_gpt":0.38726323823701586,"score_spread":0.2867061216982942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416792504","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038526498,0.76628155,0.12159537,0.050824698,0.0010090298,0.012794424,0.000033550612,0.0006668237,0.008268068],"genre_scores_gemma":[0.97581375,0.0017174113,0.0009903522,0.0030477098,0.000026506572,0.00052090833,0.000004385601,0.00001477969,0.017864224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969725,0.00069526664,0.00069265487,0.0006569461,0.00049582496,0.00048678438],"domain_scores_gemma":[0.99810517,0.0001596761,0.0001426859,0.0011137964,0.00030851553,0.00017013829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030807343,0.0002165443,0.0013003513,0.00039967144,0.00041362183,0.0007265334,0.00084870466,0.000064200955,0.00005424809],"category_scores_gemma":[0.00026587406,0.00016573793,0.00025352664,0.0017947537,0.000118249394,0.00037921884,0.0005107627,0.0002385327,0.00006168395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066889106,0.00026780064,0.0010467691,0.34370375,0.10010212,0.00030331974,0.0058426266,0.0015156663,0.00014950233,0.5373079,0.009095826,0.0006580007],"study_design_scores_gemma":[0.000164078,0.0001625489,0.0006144977,0.0026649018,0.18977377,0.0000300998,0.0007132639,0.7970487,0.0005012753,0.006055102,0.0014171987,0.0008545907],"about_ca_topic_score_codex":0.00078949233,"about_ca_topic_score_gemma":0.00028162642,"teacher_disagreement_score":0.9372872,"about_ca_system_score_codex":0.0001243283,"about_ca_system_score_gemma":0.000098549404,"threshold_uncertainty_score":0.7005978},"labels":[],"label_agreement":null},{"id":"W4416873224","doi":"10.1109/access.2025.3639184","title":"Breast Cancer Diagnosis With Explainable Artificial Intelligence (XAI): Uncovering Strengths and Biases","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Breast cancer; Transparency (behavior); Clinical Practice; Convolutional neural network; Artificial neural network; Mammography","score_opus":0.04088765908412852,"score_gpt":0.34453654811353973,"score_spread":0.30364888902941123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873224","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.511176,0.000822742,0.48069882,0.0034172847,0.0013446321,0.0005685687,0.00004607417,0.0003955681,0.0015303165],"genre_scores_gemma":[0.99633163,0.00067225564,0.0016128179,0.000520922,0.00014241632,0.00048945576,0.0000016866986,0.000019826013,0.00020895878],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976353,0.00007489067,0.00043421378,0.0008464112,0.0003570817,0.0006520991],"domain_scores_gemma":[0.99782497,0.0008826928,0.0001451615,0.00072498806,0.0002626775,0.00015952505],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028056095,0.00031898625,0.0003171021,0.00032967457,0.00044975316,0.001318091,0.0016605976,0.00009554503,0.00010644719],"category_scores_gemma":[0.00014827376,0.00028254164,0.0000525663,0.0017332758,0.00019270266,0.0026792504,0.0005389857,0.0002336778,0.000025023424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013747133,0.00035483442,0.026627842,0.00020770455,0.00012596833,0.00019921608,0.001182071,0.03386379,0.00050387974,0.06343121,0.002492136,0.87087387],"study_design_scores_gemma":[0.00022008303,0.00023881634,0.0046087103,0.0018410586,0.00009569476,0.000087839304,0.0015955198,0.09127089,0.83344734,0.06048666,0.004589168,0.0015182215],"about_ca_topic_score_codex":0.004172519,"about_ca_topic_score_gemma":0.0032165628,"teacher_disagreement_score":0.8693557,"about_ca_system_score_codex":0.00015190688,"about_ca_system_score_gemma":0.0002662788,"threshold_uncertainty_score":0.9999627},"labels":[],"label_agreement":null},{"id":"W4416913708","doi":"10.3390/info16121058","title":"Beyond Accuracy: Explainable Deep Learning for Alzheimer’s Disease Detection Using Structural MRI Data","year":2025,"lang":"en","type":"article","venue":"Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Canadian Institutes of Health Research; National Institutes of Health; H. Lundbeck A/S; Northern California Institute for Research and Education; Servier; BioClinica; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; Alliance de recherche numérique du Canada; Eisai; Alzheimer's Association; U.S. Department of Defense","keywords":"Interpretability; Deep learning; Convolutional neural network; Neuroimaging; Magnetic resonance imaging; Kernel (algebra); Artificial neural network; Limit (mathematics)","score_opus":0.04876642285899911,"score_gpt":0.32868793085896414,"score_spread":0.279921507999965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416913708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016507622,0.00015195964,0.9809203,0.0003368635,0.000724244,0.00051274727,0.000006908537,0.00019493907,0.00064442516],"genre_scores_gemma":[0.9700718,0.000010886007,0.029288314,0.00034483595,0.0000665947,0.0000421704,0.00013735855,0.0000058351534,0.0000321901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878335,0.00004373101,0.00040558475,0.00023854339,0.00020850221,0.00032027846],"domain_scores_gemma":[0.9985652,0.00018276238,0.00021111044,0.0007118928,0.0002500819,0.000078965124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043272146,0.00013511658,0.00011172692,0.00025576234,0.00067348965,0.00062048057,0.00095279445,0.000059253805,0.000007838326],"category_scores_gemma":[0.0006585294,0.00014042476,0.000041660285,0.0005305641,0.00002873696,0.012095157,0.0004616863,0.00013423464,0.000037878723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009382689,0.000013955934,0.000424209,0.00011553793,0.000049697057,0.000002024542,0.0022653441,0.2117326,0.00040319972,0.0561144,0.0003182035,0.728467],"study_design_scores_gemma":[0.00011942226,0.000022929053,0.00039250872,0.00001972276,0.000028139151,0.0000023057778,0.0004645466,0.9676308,0.0071186586,0.012327917,0.0117234355,0.00014960725],"about_ca_topic_score_codex":0.0001258629,"about_ca_topic_score_gemma":0.000038410184,"teacher_disagreement_score":0.95356417,"about_ca_system_score_codex":0.00011184506,"about_ca_system_score_gemma":0.0001386316,"threshold_uncertainty_score":0.8768697},"labels":[],"label_agreement":null},{"id":"W4416961909","doi":"10.1109/pst65910.2025.11268869","title":"DEDALUS &amp; ICARUS: Image Privacy Classification Systems with Risk Oriented Explanations","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Image sharing; Classifier (UML); Contextual image classification; Image (mathematics); Modular design; Automation; Delegate; Digital image","score_opus":0.03508505571376721,"score_gpt":0.30350809266854417,"score_spread":0.268423036954777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416961909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013351417,0.0005891017,0.93094283,0.0040838383,0.0020300583,0.0017098339,0.000036258527,0.0005323193,0.04672434],"genre_scores_gemma":[0.92727125,0.0004294104,0.05019878,0.00026917073,0.00015435032,0.00033914723,0.00004342946,0.00004050574,0.021253973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940006,0.0007280994,0.001428346,0.0017514064,0.0010002701,0.0010912492],"domain_scores_gemma":[0.993281,0.00063121587,0.0007278204,0.0030978073,0.0019147127,0.00034742194],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013197983,0.0006185608,0.00058542273,0.0008739518,0.0014524983,0.0019033629,0.0022621367,0.00028964033,0.00020651544],"category_scores_gemma":[0.0009699536,0.00055223156,0.00016176722,0.004998941,0.000606954,0.0024073867,0.0006186355,0.00067657547,0.0016679873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011319315,0.00075967907,0.004236908,0.00018845013,0.00029884806,0.0000282241,0.0045953295,0.0031280855,0.0021525726,0.9511233,0.010857921,0.02251748],"study_design_scores_gemma":[0.00064679445,0.000294074,0.0041774204,0.000557875,0.00025998653,0.00003009071,0.006219854,0.8733846,0.0077526076,0.004863086,0.10074462,0.0010689811],"about_ca_topic_score_codex":0.0030209096,"about_ca_topic_score_gemma":0.0010320521,"teacher_disagreement_score":0.9462602,"about_ca_system_score_codex":0.000657431,"about_ca_system_score_gemma":0.0011513655,"threshold_uncertainty_score":0.9998475},"labels":[],"label_agreement":null},{"id":"W4416962054","doi":"10.1109/pst65910.2025.11268815","title":"Privacy Preservation with Noise in Explainable AI","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transparency (behavior); Bottleneck; Trustworthiness; Process (computing); Inference; Information privacy; Cloud computing","score_opus":0.023771869554077306,"score_gpt":0.2905466310788237,"score_spread":0.26677476152474644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416962054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062612444,0.00038999593,0.84277594,0.02357721,0.00060894166,0.0013678641,0.0000011317454,0.0001959553,0.06847049],"genre_scores_gemma":[0.9346463,0.00010306156,0.014427494,0.00350649,0.00005963445,0.0001743598,0.0000029323498,0.000023122317,0.04705662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955642,0.00026258503,0.0009869626,0.0013372579,0.0006339174,0.0012150365],"domain_scores_gemma":[0.99678826,0.00030139703,0.00018567775,0.0019006246,0.0006464435,0.00017758255],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010984433,0.00046378275,0.00047898167,0.00085759786,0.0003956643,0.001075839,0.0023820128,0.0002284894,0.00035905032],"category_scores_gemma":[0.00041245724,0.00043046608,0.000085032945,0.0053805243,0.00020251304,0.0058601447,0.0011393946,0.0005753431,0.00033918204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028533174,0.0010472036,0.02929386,0.00033558934,0.00005966109,0.00020879386,0.007114747,0.021642717,0.0012412943,0.87318915,0.0069814827,0.058600154],"study_design_scores_gemma":[0.0008152692,0.00053818413,0.008192956,0.0008221636,0.00002597499,0.0000072237144,0.0015030097,0.80710363,0.08133052,0.059270732,0.039557364,0.00083294895],"about_ca_topic_score_codex":0.003909202,"about_ca_topic_score_gemma":0.0021094447,"teacher_disagreement_score":0.87203383,"about_ca_system_score_codex":0.0004609787,"about_ca_system_score_gemma":0.0011994494,"threshold_uncertainty_score":0.99996114},"labels":[],"label_agreement":null},{"id":"W4416986401","doi":"10.1007/978-981-97-8440-0_85-1","title":"LLM Explainability","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; York University","funders":"","keywords":"Transparency (behavior); Bridging (networking); Simplicity; Key (lock); Natural (archaeology)","score_opus":0.024732873403855493,"score_gpt":0.25675086683470605,"score_spread":0.23201799343085056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416986401","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012694376,0.0001575036,0.28213912,0.0012117177,0.0005669787,0.00025704358,0.0000029208277,0.00038207587,0.71528137],"genre_scores_gemma":[0.0007354235,0.00006267048,0.014499095,0.0009675772,0.00010575679,0.00002012106,0.0000047493863,0.000018220011,0.9835864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772704,0.00002528714,0.0004925796,0.0009520723,0.0004022537,0.00040079022],"domain_scores_gemma":[0.9972271,0.00025798543,0.00013089007,0.0019504414,0.00030284442,0.00013073914],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00039249758,0.0003776026,0.0003939275,0.000248944,0.0001689126,0.00022721675,0.0020334092,0.00034854596,0.0011001405],"category_scores_gemma":[0.00011395404,0.0003621703,0.00022846056,0.000108229906,0.00011933896,0.00041741107,0.00094182236,0.00041350725,0.0017499034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002010275,0.000020097272,0.0000021131355,0.000033311502,0.00001693451,0.000034717083,0.00008127678,0.0000065986537,0.0000049395626,0.92377925,0.022892062,0.05312671],"study_design_scores_gemma":[0.000020044941,0.000050711365,0.000002022928,0.00005455257,0.0000069820626,0.0000034096793,0.000010936128,0.0016395674,0.0012025395,0.4761297,0.5205719,0.0003076424],"about_ca_topic_score_codex":0.000087985936,"about_ca_topic_score_gemma":0.00010937973,"teacher_disagreement_score":0.4976798,"about_ca_system_score_codex":0.00023001748,"about_ca_system_score_gemma":0.0003507702,"threshold_uncertainty_score":0.99988306},"labels":[],"label_agreement":null},{"id":"W4417001716","doi":"10.1109/mis.2025.3622004","title":"Architectural Concepts for Integrating Fundamental Drives and Emotions Into Artificial Intelligence","year":2025,"lang":"","type":"article","venue":"IEEE Intelligent Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"HORIZON EUROPE Framework Programme","keywords":"Artificial psychology; Applications of artificial intelligence; Artificial life; Artificial general intelligence; Embedding; Artificial intelligence, situated approach; Affective computing","score_opus":0.048976274409543226,"score_gpt":0.35184343857947215,"score_spread":0.3028671641699289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417001716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07194942,0.0046316874,0.8972937,0.0022608219,0.018191664,0.004249369,0.00007165006,0.0003391312,0.001012577],"genre_scores_gemma":[0.98369026,0.00031078354,0.011163167,0.0003816176,0.0010602662,0.0006763982,0.000020958962,0.00008238167,0.0026141377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901585,0.0008208605,0.00355091,0.0026304517,0.00089471176,0.0019445868],"domain_scores_gemma":[0.9932019,0.0025160261,0.00092392083,0.0016357085,0.0011052416,0.0006172024],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0022681889,0.0013083436,0.0014803999,0.0012471536,0.002157892,0.0033748243,0.0025762299,0.00058402086,0.00006131433],"category_scores_gemma":[0.0010555643,0.0013256207,0.0006338586,0.0020773509,0.0016591621,0.001203496,0.00077606,0.0010666378,0.0002865511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017545048,0.00044993483,0.00031711176,0.0011879093,0.00042485722,0.000031607055,0.026702184,0.012868399,0.0120879365,0.5439541,0.0006582159,0.4011423],"study_design_scores_gemma":[0.00013453721,0.000951811,0.000032737425,0.0027405927,0.00016479501,0.00010539776,0.032324575,0.7403279,0.14884147,0.06689193,0.0061141644,0.0013701131],"about_ca_topic_score_codex":0.0026281767,"about_ca_topic_score_gemma":0.0012016089,"teacher_disagreement_score":0.91174084,"about_ca_system_score_codex":0.00093173026,"about_ca_system_score_gemma":0.0007532986,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W4417091950","doi":"10.48550/arxiv.2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","year":2025,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; European Commission; Open Philanthropy Project","keywords":"Interpretability; Benchmark (surveying); Task (project management); Variable (mathematics); Causal model; Artificial neural network; Task analysis","score_opus":0.01612328950733706,"score_gpt":0.2312647162251226,"score_spread":0.21514142671778552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417091950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02595531,0.000191441,0.93702406,0.001693761,0.0017759778,0.0007479501,0.00018425196,0.0003657186,0.032061514],"genre_scores_gemma":[0.9391177,0.00006233674,0.056033645,0.00020671802,0.000051852927,0.0000026816874,0.000045876594,0.000015144053,0.004463994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99693847,0.0002924035,0.00041023735,0.001311087,0.00053012307,0.0005176822],"domain_scores_gemma":[0.996144,0.00030641063,0.0004457715,0.002344469,0.00056073995,0.00019863767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005969585,0.00042646247,0.0007476312,0.00048800674,0.00030697722,0.00015053673,0.0046172184,0.00043190242,0.00041019951],"category_scores_gemma":[0.00016834766,0.00056422094,0.0004671121,0.00063286215,0.00028984513,0.0005546522,0.00756671,0.0007628327,0.00012380276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062988495,0.0020138638,0.0027910823,0.0071203536,0.0014382617,0.001194718,0.08054011,0.0053285183,0.0027773138,0.57757246,0.018144295,0.30044913],"study_design_scores_gemma":[0.0011067695,0.0009396511,0.0040161675,0.004698787,0.00060604553,0.00003489984,0.014396261,0.43528506,0.011557045,0.49083441,0.03264484,0.0038800456],"about_ca_topic_score_codex":0.0021928565,"about_ca_topic_score_gemma":0.00092895865,"teacher_disagreement_score":0.91316247,"about_ca_system_score_codex":0.00040296727,"about_ca_system_score_gemma":0.000640279,"threshold_uncertainty_score":0.99968094},"labels":[],"label_agreement":null},{"id":"W4417100285","doi":"10.1109/iccv51701.2025.00227","title":"Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Construct (python library); Interpretation (philosophy); Architecture; Representation (politics); Image (mathematics); Semantics (computer science)","score_opus":0.06662042109555602,"score_gpt":0.3273261182293067,"score_spread":0.2607056971337507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417100285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024692027,0.00062532484,0.97088593,0.0035569593,0.002930032,0.002628552,0.0004562091,0.0007305564,0.017939491],"genre_scores_gemma":[0.87181103,0.00010143175,0.055327434,0.0040038903,0.0010731523,0.003550552,0.0009605465,0.000100516416,0.06307145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949722,0.00021711952,0.0011595725,0.0020973028,0.00063579733,0.0009179682],"domain_scores_gemma":[0.99485743,0.00096763455,0.00043392373,0.0027617011,0.00075513433,0.00022419618],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005288553,0.00064796035,0.0008618138,0.0004295559,0.00038588315,0.0014270729,0.0038567518,0.00047454296,0.00011563483],"category_scores_gemma":[0.0009983273,0.0006682605,0.00070406584,0.0008605594,0.00031797268,0.0011933596,0.0022540549,0.0006722514,0.00005095118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007283301,0.00014800462,0.000073876676,0.0001965707,0.00011459741,0.000028970517,0.0063658007,0.006953971,0.00025319503,0.95401627,0.018037718,0.013803741],"study_design_scores_gemma":[0.0011308935,0.0003078346,0.00023676842,0.00068141625,0.00023477415,0.000018604052,0.0029392196,0.15051554,0.094026126,0.7238452,0.023429487,0.002634154],"about_ca_topic_score_codex":0.0011532259,"about_ca_topic_score_gemma":0.0001814233,"teacher_disagreement_score":0.9155585,"about_ca_system_score_codex":0.00027828992,"about_ca_system_score_gemma":0.0012357023,"threshold_uncertainty_score":0.99960953},"labels":[],"label_agreement":null},{"id":"W4417336979","doi":"10.1109/tts.2025.3636017","title":"A Survey of Accessible Explainable Artificial Intelligence Research","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Technology and Society","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CNIB Foundation; Ontario Tech University","funders":"Canada Research Chairs; Government of Canada","keywords":"Modalities; USable; Inclusion (mineral); Everyday life; Sight; Cognition","score_opus":0.11554870799396895,"score_gpt":0.3871854518925586,"score_spread":0.27163674389858966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417336979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03886565,0.0013367602,0.95339084,0.0033081253,0.0012599594,0.00069230114,0.000039662013,0.00022099294,0.0008857114],"genre_scores_gemma":[0.99058455,0.0028417674,0.0044261124,0.00016303669,0.00001867048,0.00014357928,0.0000010579323,0.000021203605,0.0018000486],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99500287,0.0006815641,0.0011610634,0.001343892,0.0006032024,0.0012074327],"domain_scores_gemma":[0.9950639,0.0015279927,0.00021121881,0.0015023239,0.0015552946,0.00013926429],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.0051336847,0.0004169612,0.00067849254,0.0017164384,0.0022639188,0.0002804985,0.0020360546,0.0012697505,0.00010828071],"category_scores_gemma":[0.0002166096,0.00045925353,0.00026103237,0.013773476,0.003554982,0.0007131535,0.00007621936,0.0023951312,0.00007102239],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017331885,0.0017591548,0.00023310557,0.000431994,0.00035545253,0.000015676475,0.0044250423,0.003096104,0.0045462903,0.2868246,0.000614139,0.6975251],"study_design_scores_gemma":[0.000102511054,0.0006656301,0.00019043911,0.00042581942,0.000043567423,0.000005540039,0.008442313,0.1396497,0.7165411,0.1333494,0.000198618,0.00038536396],"about_ca_topic_score_codex":0.0013256969,"about_ca_topic_score_gemma":0.00072732626,"teacher_disagreement_score":0.95171887,"about_ca_system_score_codex":0.00023932908,"about_ca_system_score_gemma":0.0009658738,"threshold_uncertainty_score":0.99990636},"labels":[],"label_agreement":null},{"id":"W4417346112","doi":"10.64898/2025.12.11.25342109","title":"Deceptive Bias Measurement in Deep Learning: Assessing Shortcut Reliance in TCGA Cancer Models","year":2025,"lang":"","type":"article","venue":"medRxiv","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; Ontario Tech University","funders":"","keywords":"Metric (unit); Exploit; Limit (mathematics); Measure (data warehouse); Key (lock); Deep learning","score_opus":0.14397873150265963,"score_gpt":0.3484576135299461,"score_spread":0.20447888202728645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417346112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5200436,0.0093147885,0.4577804,0.002994104,0.0019179694,0.0008500117,0.000001014254,0.000118950535,0.006979183],"genre_scores_gemma":[0.9929852,0.0023694953,0.0029405,0.0005284829,0.000088782006,0.00026659077,7.4189575e-7,0.000042859076,0.0007773596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919332,0.0012740043,0.0017276169,0.0019367499,0.0014653739,0.0016630363],"domain_scores_gemma":[0.99695027,0.00041577278,0.00042581838,0.0011127726,0.0008562735,0.00023911051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0054067723,0.00065260247,0.00086086756,0.0012737726,0.00041560142,0.0008225507,0.0020617368,0.00035069883,0.000102413],"category_scores_gemma":[0.001549979,0.00073016837,0.00018653498,0.0059884135,0.00029982312,0.0025369886,0.0007922289,0.0015862962,0.00010142815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058899488,0.00043676904,0.2948608,0.00014100164,0.000047666403,0.00023177126,0.010060212,0.49280986,0.003653306,0.011032936,0.000063539876,0.18660323],"study_design_scores_gemma":[0.0003379637,0.00008923387,0.04762579,0.0025487745,0.000023668887,0.0000017159034,0.002012873,0.9124933,0.022389304,0.010646361,0.0011445391,0.0006864934],"about_ca_topic_score_codex":0.003989373,"about_ca_topic_score_gemma":0.017720697,"teacher_disagreement_score":0.4729416,"about_ca_system_score_codex":0.0023986085,"about_ca_system_score_gemma":0.0015686314,"threshold_uncertainty_score":0.99951494},"labels":[],"label_agreement":null},{"id":"W4417470956","doi":"10.1109/iccst63435.2025.11295479","title":"Explainable Bidirectional LSTM Autoencoder for Insider Threat Detection in Various Scenarios","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Transparency (behavior); Insider threat; Deep learning; Anomaly detection; Identification (biology); Recall","score_opus":0.02707232682504421,"score_gpt":0.2938553117160457,"score_spread":0.26678298489100144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417470956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062019154,0.00081427826,0.96487653,0.0036951734,0.0049241525,0.002094952,0.000005889527,0.00036865124,0.017018477],"genre_scores_gemma":[0.9256062,0.00018964702,0.03974095,0.0020872874,0.0002644962,0.00083950517,0.0000049781142,0.000051929117,0.031215012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99434686,0.00027502648,0.0013798868,0.0018408687,0.0005833939,0.0015739541],"domain_scores_gemma":[0.9966376,0.0009031666,0.0002344651,0.0011701789,0.0008368377,0.00021777052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015822634,0.0006444134,0.00068404834,0.0014774775,0.0011407313,0.0009186462,0.0012009953,0.00054587575,0.00038165558],"category_scores_gemma":[0.0007478229,0.00069621793,0.00032760168,0.0038896056,0.00022953085,0.0021959732,0.00061376096,0.0006353856,0.00027329277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047273588,0.0016909767,0.0015738684,0.0004389628,0.00022282993,0.00010424605,0.00499019,0.06831182,0.0071054827,0.4080009,0.00484698,0.502241],"study_design_scores_gemma":[0.0006146819,0.00032634413,0.00060684106,0.0001926077,0.000035559115,0.000025545498,0.0007856483,0.76488316,0.10302107,0.1075941,0.021299373,0.0006150831],"about_ca_topic_score_codex":0.0062649143,"about_ca_topic_score_gemma":0.015706012,"teacher_disagreement_score":0.92513555,"about_ca_system_score_codex":0.0013585206,"about_ca_system_score_gemma":0.0013587041,"threshold_uncertainty_score":0.9995489},"labels":[],"label_agreement":null},{"id":"W4417510320","doi":"10.1109/eecsi67060.2025.11290147","title":"Beyond Black-Box Explanations: Monte Carlo Dropout for Uncertainty-Aware Explainable AI in Marketing Analytics","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Marriott International (Canada)","funders":"","keywords":"Dropout (neural networks); Flagging; Monte Carlo method; Reliability (semiconductor); Bayesian probability; Artificial neural network; Bayesian network; Markov chain Monte Carlo","score_opus":0.02251304990419496,"score_gpt":0.30899290663046053,"score_spread":0.2864798567262656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417510320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015876956,0.0013393805,0.9194471,0.020696446,0.0025383884,0.0037426571,0.00006953307,0.00035129476,0.03593822],"genre_scores_gemma":[0.9362322,0.00045754068,0.011998893,0.0041177715,0.0002228188,0.0004714134,0.000022774753,0.000068247406,0.046408325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913044,0.0007003981,0.0024441965,0.002280882,0.00090098183,0.002369163],"domain_scores_gemma":[0.992019,0.003164866,0.0004942577,0.0020862727,0.0018567984,0.00037882314],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0050249957,0.000934079,0.0011391169,0.0020019906,0.0011460617,0.0016521261,0.0029540416,0.0005451984,0.00027126676],"category_scores_gemma":[0.0028518946,0.0010406948,0.0004895801,0.0053886687,0.00046598274,0.0024453935,0.0011526026,0.0008645382,0.0001410873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007187739,0.0012976474,0.004696567,0.0016141185,0.0004462021,0.00029446368,0.013223204,0.3808066,0.0003373424,0.44789046,0.06086961,0.08780501],"study_design_scores_gemma":[0.00077031617,0.00020066011,0.0001491487,0.00069198495,0.000091735164,0.000004601132,0.021325393,0.92848426,0.0037326778,0.031766742,0.011816839,0.0009656527],"about_ca_topic_score_codex":0.003552615,"about_ca_topic_score_gemma":0.009603021,"teacher_disagreement_score":0.92035526,"about_ca_system_score_codex":0.0015686309,"about_ca_system_score_gemma":0.0017566107,"threshold_uncertainty_score":0.9993843},"labels":[],"label_agreement":null},{"id":"W603409675","doi":"","title":"Uncertainty in artificial intelligence : proceedings of the Thirtieth Conference (2014) : July 23-27, 2014, Quebec City, Quebec, Canada","year":2014,"lang":"en","type":"book","venue":"AUAI Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Regional science; Geography; Political science; History; Computer science","score_opus":0.03868165507069612,"score_gpt":0.24610295276083743,"score_spread":0.2074212976901413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W603409675","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013849445,0.00056456274,0.027425488,0.0017689824,0.0057450826,0.0035493583,0.000097773685,0.00036610116,0.9590977],"genre_scores_gemma":[0.08439277,0.000051567924,0.0005126293,0.0007029631,0.00041624715,0.00016904551,0.000013081865,0.00009642668,0.91364527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938773,0.00017826806,0.0017057104,0.0015145355,0.0015660973,0.0011580995],"domain_scores_gemma":[0.9949187,0.00065304304,0.0013151701,0.0016586053,0.0011714888,0.0002830006],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011517451,0.0008697243,0.0010826198,0.00025304334,0.00026177647,0.00054819015,0.006281496,0.00064463797,0.000054096527],"category_scores_gemma":[0.00033795304,0.0007324871,0.0002705771,0.00014750761,0.000810348,0.00043310766,0.0019112031,0.001599465,0.00007453545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049277096,0.00004605899,0.000030654533,0.00034475917,0.00006497749,0.000024149853,0.0031798782,0.00080760964,0.00023008969,0.7290798,0.23677476,0.029367983],"study_design_scores_gemma":[0.0001421761,0.00016528102,0.00012342907,0.001954033,0.00010366028,0.000019685329,0.0002938416,0.016738754,0.07674806,0.21092048,0.690508,0.002282561],"about_ca_topic_score_codex":0.8966712,"about_ca_topic_score_gemma":0.9906834,"teacher_disagreement_score":0.51815933,"about_ca_system_score_codex":0.001227485,"about_ca_system_score_gemma":0.007685689,"threshold_uncertainty_score":0.9995126},"labels":[],"label_agreement":null},{"id":"W6888541425","doi":"10.20381/ruor-29662","title":"Decision Trees: Modeling with fast intuition and slow, deliberate analysis","year":2023,"lang":"en","type":"article","venue":"University of Ottawa - Library","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Intuition; Decision tree; Categorization; Evidential reasoning approach; Rational analysis; Decision analysis; Decision theory; Exploit","score_opus":0.0133907329061007,"score_gpt":0.19585126743195838,"score_spread":0.18246053452585767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888541425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34089106,0.000018485796,0.6567017,0.00029161852,0.000021377577,0.000049986207,0.0000046260866,0.00017535992,0.0018457932],"genre_scores_gemma":[0.9552731,0.00008762063,0.043968897,0.000053658943,0.00000984741,1.3892111e-7,0.0000173999,0.0000068600925,0.0005825072],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912566,0.000043563592,0.00012718531,0.0003262204,0.0001962837,0.00018109009],"domain_scores_gemma":[0.9993803,0.000092686394,0.000067224544,0.00031736618,0.0000501474,0.000092283604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011405405,0.00009591772,0.00016932441,0.00060577795,0.0001890485,0.000085163934,0.00048678092,0.000050465198,0.00004178738],"category_scores_gemma":[0.0000078405155,0.00009846273,0.000062689745,0.0022611872,0.0000677034,0.0024194564,0.0003307259,0.000074630065,0.000038614482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017777724,0.00014891346,0.02073437,0.000048624195,0.0005014438,0.0005234708,0.0089059565,0.6516545,0.0007781301,0.20091866,0.0045450083,0.11106318],"study_design_scores_gemma":[0.00012264165,0.00008215657,0.0015944004,0.000030819083,0.00004677274,0.0000019652373,0.0010489486,0.98850685,0.00089801586,0.007036153,0.00049892295,0.00013234402],"about_ca_topic_score_codex":0.00015232098,"about_ca_topic_score_gemma":0.0001686684,"teacher_disagreement_score":0.614382,"about_ca_system_score_codex":0.000012877643,"about_ca_system_score_gemma":0.00004731179,"threshold_uncertainty_score":0.4015194},"labels":[],"label_agreement":null},{"id":"W6892417037","doi":"10.5281/zenodo.10669077","title":"dataset supporting \"From Consumption to Context\", ERC, 2024.","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Consumption (sociology); Production (economics); Quality (philosophy); Identification (biology); Focus (optics)","score_opus":0.09290532404214259,"score_gpt":0.3230041916306258,"score_spread":0.23009886758848325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892417037","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008154091,0.00003614788,0.014601484,0.0011346627,0.00074721826,0.00069147395,0.9812917,0.00086617284,0.00054960855],"genre_scores_gemma":[0.00018982777,0.00016916174,0.0005410023,0.00075962907,0.00027627833,2.1751721e-7,0.9967223,0.00080867327,0.0005329226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602133,0.0005227781,0.00064858946,0.0012267493,0.0007920193,0.00078854844],"domain_scores_gemma":[0.996582,0.00014967965,0.00031024448,0.002043675,0.0005513465,0.00036308658],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001435111,0.00033308603,0.00033940043,0.00060172664,0.0020024683,0.002960657,0.0053917896,0.0001915062,0.009388984],"category_scores_gemma":[0.0019128424,0.0003830512,0.00007486733,0.0011749686,0.00013941167,0.00068671757,0.006597402,0.00065285125,0.3466243],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018400784,0.00006707463,1.7456452e-7,0.00005616938,0.000041651532,0.00012653819,0.0002808515,0.000052071082,0.00017737794,0.0007810985,0.96157223,0.03682637],"study_design_scores_gemma":[0.00011076047,0.0001632325,0.000015594158,0.00009004724,0.000019796164,0.000036062294,0.00018624635,0.00076569425,0.0002980136,0.00033235893,0.9975842,0.00039797605],"about_ca_topic_score_codex":0.00095464976,"about_ca_topic_score_gemma":0.0000445609,"teacher_disagreement_score":0.33723533,"about_ca_system_score_codex":0.000283088,"about_ca_system_score_gemma":0.000016384634,"threshold_uncertainty_score":0.9999895},"labels":[],"label_agreement":null},{"id":"W6893338574","doi":"10.5281/zenodo.15103223","title":"Tanytarsus miriforceps","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pupa; Glacial period; Global biodiversity; Taxonomy (biology); Fauna; Latitude","score_opus":0.035760456474956945,"score_gpt":0.26912211974864647,"score_spread":0.2333616632736895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893338574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043977825,0.000118294294,0.55320317,0.00396308,0.00033963835,0.00037886377,0.000017267066,0.0017897737,0.43579212],"genre_scores_gemma":[0.98337173,0.000080136364,0.006013107,0.0011756445,0.00012015609,8.986062e-8,0.00016090536,0.00069229875,0.0083859125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832237,0.00022088738,0.00025088227,0.00048187998,0.00029825704,0.00042574303],"domain_scores_gemma":[0.99843204,0.00003882728,0.00006320663,0.0008102242,0.0005310067,0.00012466947],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00064500095,0.00012487486,0.00011977889,0.00031700448,0.002066288,0.001350489,0.002667068,0.00005811989,0.0025611576],"category_scores_gemma":[0.00059159094,0.00013546823,0.00005270021,0.0013366218,0.00012769693,0.00055356167,0.0019977668,0.0002193997,0.011607343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001952025,0.000102052494,0.0000026370458,0.000031249732,0.00002738436,0.000023750457,0.0009994459,0.00015776156,0.0052981204,0.5080083,0.20688614,0.27844363],"study_design_scores_gemma":[0.00013164691,0.00009112315,0.000118789205,0.000024033694,0.0000040652244,0.000025063557,0.00020904925,0.006675594,0.007077407,0.006222962,0.9792774,0.00014287865],"about_ca_topic_score_codex":0.000023935345,"about_ca_topic_score_gemma":5.6657916e-7,"teacher_disagreement_score":0.978974,"about_ca_system_score_codex":0.00015509564,"about_ca_system_score_gemma":0.000007851389,"threshold_uncertainty_score":0.9996862},"labels":[],"label_agreement":null},{"id":"W6912667637","doi":"10.5281/zenodo.6784186","title":"Trustworthy Artificial Intelligence for Environmental Science (TAI4ES) Summer School 2022","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Trustworthiness; Robustness (evolution); Citizen science; Climate science; Work (physics); Range (aeronautics)","score_opus":0.053563699001662766,"score_gpt":0.2687462083050172,"score_spread":0.21518250930335445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912667637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035590503,0.0002380271,0.90958226,0.0036132575,0.0012147961,0.0024037254,0.0004223262,0.0017738156,0.045161285],"genre_scores_gemma":[0.9938608,0.00003182996,0.00349912,0.00048266433,0.00017627995,0.0000014548806,0.00025313618,0.0005647965,0.0011299134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964263,0.00030704,0.0004410249,0.0009713101,0.001050522,0.00080381316],"domain_scores_gemma":[0.9982158,0.00006826881,0.00016099459,0.0009557569,0.00026079125,0.0003383963],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002555104,0.00019177812,0.0001633202,0.000517442,0.008914075,0.0015874181,0.004770844,0.000036753307,0.015827158],"category_scores_gemma":[0.00079415354,0.0002277908,0.00009107734,0.0018335902,0.0005044308,0.0011068931,0.0051180343,0.00042791828,0.005865799],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012280469,0.0005465001,0.000009245646,0.000023334007,0.00002780266,0.000033087726,0.0021886134,0.003641561,0.050899457,0.24891458,0.03422966,0.6593633],"study_design_scores_gemma":[0.000101899524,0.00063907885,0.00007142835,0.0000059216945,0.000007928268,0.000104127066,0.0022641362,0.049213745,0.02784495,0.00819338,0.91116726,0.0003861284],"about_ca_topic_score_codex":0.000013742973,"about_ca_topic_score_gemma":5.056445e-7,"teacher_disagreement_score":0.9582703,"about_ca_system_score_codex":0.0006775777,"about_ca_system_score_gemma":0.000031046176,"threshold_uncertainty_score":0.999449},"labels":[],"label_agreement":null},{"id":"W6917848079","doi":"10.58079/14hds","title":"IJCAI 2025 Workshop on Explainable Artificial Intelligence (XAI)","year":2025,"lang":"en","type":"article","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Raising (metalworking); Applications of artificial intelligence; Work (physics); Intelligent decision support system; Expert system","score_opus":0.059227258871344106,"score_gpt":0.2934785044055431,"score_spread":0.23425124553419896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6917848079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029633068,0.00030338613,0.68044406,0.078638986,0.002600856,0.0014785947,0.000028981758,0.0014575128,0.20541452],"genre_scores_gemma":[0.92137045,0.00010811452,0.0072434354,0.0034844794,0.00041645247,0.00007852916,0.000031176754,0.00004842138,0.067218915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957956,0.00032719594,0.00063500914,0.0012737779,0.00065715704,0.0013112765],"domain_scores_gemma":[0.996718,0.000793084,0.00026129824,0.0014194428,0.00042722412,0.0003809688],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007951396,0.000555063,0.00051306345,0.0008996625,0.0009664876,0.00090980553,0.003169724,0.0006827285,0.00036469646],"category_scores_gemma":[0.0010031541,0.0005847462,0.00027572544,0.004577722,0.00028094382,0.0017618674,0.00076544704,0.0012777558,0.0010004587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010927714,0.00027795142,0.00004115852,0.00002360588,0.000096504824,0.0003281556,0.0016055845,0.00741073,0.0027266135,0.82604307,0.039885733,0.12145159],"study_design_scores_gemma":[0.0010491777,0.0008585017,0.003155451,0.0020258892,0.00021565252,0.000082090664,0.045752417,0.13300174,0.45822483,0.14644837,0.20537269,0.0038131634],"about_ca_topic_score_codex":0.00049361034,"about_ca_topic_score_gemma":0.00019611962,"teacher_disagreement_score":0.8917374,"about_ca_system_score_codex":0.0008724721,"about_ca_system_score_gemma":0.0006423796,"threshold_uncertainty_score":0.9997774},"labels":[],"label_agreement":null},{"id":"W6920925388","doi":"10.6084/m9.figshare.26488316","title":"Additional file 1 of Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deep learning; Propensity score matching; Architecture; Artificial neural network; F1 score; Deep neural networks","score_opus":0.07067990908266547,"score_gpt":0.2886858573578392,"score_spread":0.21800594827517372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920925388","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068143256,0.00007353336,0.89339495,0.00104507,0.0002826955,0.0021781463,0.02551893,0.000048477774,0.009314944],"genre_scores_gemma":[0.3270083,0.00000199276,0.66779166,0.00008442621,0.00007693634,0.00047369231,0.0025931913,0.000033931086,0.0019358685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852985,0.000052976262,0.0003103615,0.0005267296,0.0002319824,0.00034811875],"domain_scores_gemma":[0.9987047,0.00079385936,0.00006737199,0.00026561643,0.00009390743,0.00007455092],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037062788,0.00015175942,0.00022462415,0.00018929201,0.00016292607,0.0004487416,0.0010758709,0.000068259054,0.051533926],"category_scores_gemma":[0.0002340379,0.000141169,0.00007494588,0.00045210923,0.000055894212,0.00087983225,0.00046768365,0.00029757587,0.00005890935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004810212,0.000092444294,0.00002648168,0.00012034966,0.00003799427,0.00006970694,0.017199129,0.424486,0.0008618158,0.004307868,0.021802802,0.53094727],"study_design_scores_gemma":[0.00006657831,0.00009525203,0.000037404247,0.0005273446,0.000003880516,0.000013457282,0.00043185754,0.94920903,0.0031782903,0.0177488,0.02848803,0.0002000497],"about_ca_topic_score_codex":0.00030904418,"about_ca_topic_score_gemma":0.0013489057,"teacher_disagreement_score":0.53074723,"about_ca_system_score_codex":0.000098287535,"about_ca_system_score_gemma":0.00034409738,"threshold_uncertainty_score":0.94933313},"labels":[],"label_agreement":null},{"id":"W6921069386","doi":"10.6084/m9.figshare.26488316.v1","title":"Additional file 1 of Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deep learning; Propensity score matching; Architecture; Artificial neural network; F1 score; Deep neural networks","score_opus":0.0693289352225452,"score_gpt":0.2601704189500754,"score_spread":0.19084148372753024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921069386","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039845382,0.00007043959,0.030831989,0.00018833706,0.000058130143,0.0005226438,0.96681976,0.00025185893,0.00085839676],"genre_scores_gemma":[0.18042743,0.0000015098301,0.12020322,0.0003283854,0.00023746604,0.0030624145,0.694732,0.00008383306,0.0009237302],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860084,0.00003915354,0.0002675343,0.0004549579,0.00026354697,0.00037397232],"domain_scores_gemma":[0.99827325,0.0011962326,0.00006549666,0.000242249,0.00014685332,0.000075900374],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009202358,0.00016429184,0.00019252484,0.00021938873,0.00014301838,0.0001937068,0.0006359207,0.00008456504,0.46170235],"category_scores_gemma":[0.0011104763,0.00015691914,0.000108978,0.00049233175,0.000013015998,0.00057657075,0.00025780886,0.00035229695,0.00014364305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011104171,0.00003334052,0.0000029511382,0.0006310993,0.000017843098,0.000046887442,0.0040531014,0.28783676,0.00008821358,0.0016365655,0.6693186,0.036323514],"study_design_scores_gemma":[0.000037965394,0.00006276146,0.00005302408,0.0033332868,0.0000016508626,0.0000111706895,0.00011284946,0.9372968,0.0008364829,0.011726077,0.046330072,0.00019788065],"about_ca_topic_score_codex":0.000059733757,"about_ca_topic_score_gemma":0.000329016,"teacher_disagreement_score":0.64946,"about_ca_system_score_codex":0.00010455537,"about_ca_system_score_gemma":0.00026721187,"threshold_uncertainty_score":0.63989764},"labels":[],"label_agreement":null},{"id":"W6924805576","doi":"10.15468/dl.v56cnn","title":"Occurrence Download","year":2023,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Alien; The Internet","score_opus":0.02857313338577185,"score_gpt":0.24590530863717722,"score_spread":0.21733217525140536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924805576","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004540027,0.000010027963,0.0009795225,0.00043801992,0.0014936853,0.0003223289,0.9961313,0.00048160652,0.000098132696],"genre_scores_gemma":[0.000004073384,0.00006589677,0.000016190572,0.00056978967,0.000002158694,0.0000066114067,0.9993349,1.755993e-8,3.9621577e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976933,0.00008850633,0.0005253153,0.00041354625,0.0007663156,0.0005130192],"domain_scores_gemma":[0.9977678,0.000057341193,0.00033654072,0.0012030976,0.00041570517,0.00021951729],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00052425143,0.00032603383,0.00029524718,0.00018639909,0.00043389024,0.00058013725,0.0024830564,0.0003549388,0.00018379543],"category_scores_gemma":[0.00034576442,0.00035046146,0.00017179863,0.0011898759,0.00016094894,0.0031097168,0.0014008796,0.00034547577,0.7730557],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008546813,0.000024768862,0.000077142126,0.00008406181,0.000017776383,0.000009864969,0.00008177336,0.0000499728,4.534567e-8,0.0000054159254,0.9965588,0.0030818759],"study_design_scores_gemma":[0.00008116016,0.000039043494,0.000026316884,0.0000035353694,0.000013302741,0.0000044114245,0.00012461186,0.000010291797,0.000018569906,0.000022889199,0.9993019,0.00035392778],"about_ca_topic_score_codex":0.0018788072,"about_ca_topic_score_gemma":0.000070027694,"teacher_disagreement_score":0.7728719,"about_ca_system_score_codex":0.00041940174,"about_ca_system_score_gemma":0.000256487,"threshold_uncertainty_score":0.99989474},"labels":[],"label_agreement":null},{"id":"W6926439288","doi":"10.25318/1410016801-fra","title":"Enquête sur la population active (EPA), estimations de l'emploi selon les régions urbaines et rurales basées sur les limites du recensement de 2006, la catégorie de travailleur et le Système de classification des industries de l'Amérique du Nord (SCIAN), non désaisonnalisées","year":2020,"lang":"fr","type":"dataset","venue":"Statistics Canada Dissemination","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Research methodology; Statistical analysis; Rural population","score_opus":0.03544382676574347,"score_gpt":0.283193869432293,"score_spread":0.24775004266654954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926439288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055023454,0.0003121082,0.66737574,0.01265458,0.0002454042,0.0008683094,0.26332814,0.00012378849,0.00006847618],"genre_scores_gemma":[0.6733231,0.0023607889,0.04125774,0.00026078938,0.0002071152,0.0004467256,0.28173536,0.000103409315,0.00030497782],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9940865,0.0021499633,0.0010754588,0.000857934,0.0007948195,0.0010352947],"domain_scores_gemma":[0.99026346,0.0061878893,0.001006192,0.0005397592,0.001482795,0.0005199046],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017504308,0.00074653036,0.00059610687,0.00039275983,0.0014977237,0.0010848362,0.00092199043,0.00065241853,0.00003224356],"category_scores_gemma":[0.012112024,0.0009090394,0.000092678674,0.0010513169,0.0004499866,0.0012223166,0.00018246575,0.00092162716,0.0000076194597],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00009903968,0.0005231358,0.0359312,0.0009611418,0.00020544874,0.00037988706,0.01413302,0.015150292,0.0030341698,0.092030756,0.7924812,0.04507071],"study_design_scores_gemma":[0.00037547998,0.00029173619,0.5788057,0.0022067153,0.00048170623,0.00029816106,0.008771808,0.30953878,0.010715305,0.009575905,0.07716914,0.0017695884],"about_ca_topic_score_codex":0.60095185,"about_ca_topic_score_gemma":0.93498516,"teacher_disagreement_score":0.71531206,"about_ca_system_score_codex":0.0044260197,"about_ca_system_score_gemma":0.007996283,"threshold_uncertainty_score":0.99995214},"labels":[],"label_agreement":null},{"id":"W6929203315","doi":"10.48322/gpwf-9m90","title":"ISIS-2 Topside Sounder Average Ionogram over Sodankyla, Finland: SOD, Latitude 67, Longitude 27","year":2024,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Ionogram; Longitude; Ionosphere; Ionosonde; Latitude; Amplitude; Depth sounding","score_opus":0.050387360651909484,"score_gpt":0.34402292218052666,"score_spread":0.2936355615286172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929203315","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006586232,0.0011338228,0.02039781,0.0013161638,0.006088946,0.0021350184,0.9587619,0.000048711594,0.009459016],"genre_scores_gemma":[0.0012135172,0.00066604797,0.05295648,0.0020689103,0.0017296404,0.0002815246,0.9020596,0.0001668705,0.038857397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99527824,0.00018094043,0.0008742764,0.0018284176,0.00086239196,0.0009757302],"domain_scores_gemma":[0.99611497,0.00033958707,0.00030824824,0.0027832813,0.00014234032,0.00031154547],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010052363,0.0007119966,0.000722586,0.0003021921,0.00033205134,0.0054699313,0.0065015554,0.0005395121,0.008638332],"category_scores_gemma":[0.00014506889,0.000668137,0.00028932167,0.00075916806,0.00014025076,0.0015357455,0.004351604,0.0010264332,0.088168815],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013476734,0.00016357946,0.000033761975,0.00006206157,0.00014772786,0.0006886707,0.00048595597,0.00041840956,0.0000118259895,0.00037162623,0.9857973,0.011805597],"study_design_scores_gemma":[0.00014017976,0.000105306164,0.000032825064,0.00022879307,0.000076011886,0.00004280006,0.00006428413,0.0020941817,0.00052157044,0.0045394623,0.99130756,0.00084702374],"about_ca_topic_score_codex":0.0018366474,"about_ca_topic_score_gemma":0.0060764523,"teacher_disagreement_score":0.079530485,"about_ca_system_score_codex":0.0002498427,"about_ca_system_score_gemma":0.00058298634,"threshold_uncertainty_score":0.999577},"labels":[],"label_agreement":null},{"id":"W6930223830","doi":"10.5281/zenodo.10906565","title":"FIGURE 11 in The six-spotted spider mite, Eotetranychus sexmaculatus (Riley) (Trombidiformes: Tetranychidae) in Australia, New Zealand, Japan and USA: a revised morphological and molecular-based concept, synonyms, and related species","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Aedeagus; Spider; Ficus; Dorsum; Synonym (taxonomy)","score_opus":0.03712770111963032,"score_gpt":0.2648735230825352,"score_spread":0.22774582196290488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930223830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7034102,0.00902382,0.0052406113,0.014504585,0.0007238632,0.007693147,0.000535034,0.0027232673,0.25614545],"genre_scores_gemma":[0.8550713,0.0008247437,0.0017725715,0.0006642399,0.00015568102,7.8668734e-7,0.00047412948,0.002514408,0.13852213],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997169,0.000532996,0.00043712702,0.00090775266,0.00042070932,0.00053238095],"domain_scores_gemma":[0.9989311,0.000079229845,0.00013223474,0.0005750235,0.00007906347,0.00020334873],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006826514,0.0003489169,0.00037750567,0.0005895653,0.00033104667,0.0010522285,0.0010361164,0.00027684902,0.0042003603],"category_scores_gemma":[0.00036586833,0.00028967662,0.00005346803,0.0012781495,0.00039569568,0.00019828953,0.00062916154,0.0007226533,0.00080342795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009966999,0.00045886572,0.0007133227,0.000689432,0.00015828147,0.0036196094,0.0132497195,0.00016396504,0.0055208667,0.02401636,0.9334715,0.01783841],"study_design_scores_gemma":[0.0012506671,0.0006314209,0.0073453486,0.00082618487,0.000045256536,0.00060906354,0.00067698373,0.0018907457,0.00022947935,0.001393088,0.98436266,0.000739122],"about_ca_topic_score_codex":0.00076980185,"about_ca_topic_score_gemma":0.0000850124,"teacher_disagreement_score":0.15166108,"about_ca_system_score_codex":0.00008794567,"about_ca_system_score_gemma":0.000012770908,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W6930512154","doi":"10.5281/zenodo.14219114","title":"Evidence that metapopulation dynamics maintain a species' range limit","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Memorial University of Newfoundland","funders":"","keywords":"Metapopulation; Occupancy; Range (aeronautics); Habitat; Limit (mathematics); Dynamics (music)","score_opus":0.10701404468961144,"score_gpt":0.2895682735354299,"score_spread":0.18255422884581846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930512154","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028234042,0.00048006803,0.41465148,0.003679032,0.00086473086,0.0014222133,0.5635019,0.0014410083,0.013931342],"genre_scores_gemma":[0.0017200117,0.0012568398,0.0016861304,0.0004960928,0.0002441495,2.8899882e-7,0.99146557,0.00052196026,0.0026089833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958553,0.0008724383,0.0005237805,0.0010879976,0.0009681685,0.00069234724],"domain_scores_gemma":[0.9961571,0.00018702011,0.00042818856,0.0021367455,0.00086611835,0.00022479343],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017115517,0.00037391868,0.0003796695,0.0007702515,0.0022460092,0.0031509374,0.005965878,0.00024450303,0.00406735],"category_scores_gemma":[0.0031821053,0.00041174024,0.0001501084,0.0016920131,0.0001935139,0.0011719593,0.005098445,0.0007543675,0.0047125756],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025504809,0.000084742416,6.68438e-7,0.00015370971,0.000044499742,0.000054031512,0.00014254768,0.00010674754,0.000020588366,0.023845714,0.93383527,0.041686],"study_design_scores_gemma":[0.00010034347,0.0001522088,0.000040066767,0.00027340016,0.00003828398,0.00004846351,0.00014919142,0.007551459,0.00011868767,0.0011020646,0.9900447,0.00038114493],"about_ca_topic_score_codex":0.0001817828,"about_ca_topic_score_gemma":0.000029309058,"teacher_disagreement_score":0.42796364,"about_ca_system_score_codex":0.0009276844,"about_ca_system_score_gemma":0.000026150614,"threshold_uncertainty_score":0.99983346},"labels":[],"label_agreement":null},{"id":"W6930745371","doi":"10.5281/zenodo.14204514","title":"dataset for: Carbonate content and stable isotopic composition of atmospheric aerosol carbon in the Canadian High Arctic","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Aerosol; Atmospheric composition; Carbonate; Arctic; Carbon fibers; Atmospheric chemistry; Chemical composition; The arctic","score_opus":0.04898680673641995,"score_gpt":0.2535648990486426,"score_spread":0.20457809231222265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930745371","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007725601,0.000248451,0.00044404727,0.0012599253,0.00021520043,0.0010701873,0.9955122,0.000056724017,0.00042073123],"genre_scores_gemma":[0.04327471,0.00014219499,0.0002708187,0.00026394567,0.00006220037,6.39114e-7,0.95571166,0.00023664652,0.0000371662],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801177,0.00032886412,0.0003485189,0.0005228035,0.00036587467,0.00042214614],"domain_scores_gemma":[0.99847806,0.00007049478,0.0001279502,0.0008628741,0.00032495908,0.00013566946],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088385487,0.00018565377,0.00022126682,0.00014452855,0.00074221374,0.0011124633,0.0020087778,0.00010754854,0.00034235054],"category_scores_gemma":[0.00020392291,0.00016876466,0.000032647902,0.000667187,0.0001596779,0.00022128383,0.0008863233,0.0003924886,0.00047245264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014110374,0.000054195523,0.0000010003561,0.0003152111,0.000028080545,0.00004345549,0.00047019587,0.000088673994,0.00012483695,0.0028332165,0.99461484,0.0014122117],"study_design_scores_gemma":[0.00013213283,0.00022244647,0.000023927747,0.00010552522,0.000024933172,0.00005320553,0.00015831464,0.0045112385,0.00013479295,0.0004928519,0.9939636,0.00017703499],"about_ca_topic_score_codex":0.117649876,"about_ca_topic_score_gemma":0.012285686,"teacher_disagreement_score":0.10536419,"about_ca_system_score_codex":0.0003465537,"about_ca_system_score_gemma":0.000032172244,"threshold_uncertainty_score":0.9999245},"labels":[],"label_agreement":null},{"id":"W6931245852","doi":"10.5281/zenodo.2595490","title":"Norway's Fair Share of Meeting the Paris Agreement","year":2018,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Pledge; Equity (law); Convention; Fair share; United Nations Framework Convention on Climate Change; Conference of the parties; Equity theory","score_opus":0.0831382354683342,"score_gpt":0.29366332934149586,"score_spread":0.21052509387316165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931245852","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056394073,0.0005452379,0.05507357,0.0016111418,0.0007850414,0.0010733694,0.00024761015,0.0007381131,0.939362],"genre_scores_gemma":[0.8922708,0.006551471,0.009799891,0.0010966839,0.0054294136,0.0000014521586,0.0048635704,0.0098786615,0.070108056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959624,0.00049028354,0.0006751829,0.0007566882,0.0015528123,0.0005626567],"domain_scores_gemma":[0.99400926,0.0000821893,0.0005911421,0.0016584902,0.0035044497,0.00015447433],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030842612,0.00026442442,0.00030940786,0.0002860476,0.002339636,0.0012260292,0.0050774175,0.00015276634,0.01062538],"category_scores_gemma":[0.0019136012,0.0002230525,0.00014037198,0.0010056022,0.00031973014,0.00037878763,0.0052387044,0.00048738267,0.0125358645],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011853099,0.00011121601,0.00000322591,0.00021666597,0.00009837215,0.000023854536,0.0028275412,0.0000648607,0.00060769275,0.0067142947,0.8739646,0.1153558],"study_design_scores_gemma":[0.00005918224,0.00024119501,0.000064942564,0.00019030907,0.000018523537,0.0000677639,0.0004187137,0.0015569399,0.003197797,0.0003697842,0.9935796,0.0002352407],"about_ca_topic_score_codex":0.00023301787,"about_ca_topic_score_gemma":0.0000044547246,"teacher_disagreement_score":0.8917069,"about_ca_system_score_codex":0.000386486,"about_ca_system_score_gemma":0.000051461437,"threshold_uncertainty_score":0.9998108},"labels":[],"label_agreement":null},{"id":"W6931388259","doi":"10.5281/zenodo.5942213","title":"Randomized Row-Swap: Mitigating Row Hammer by Breaking Spatial Correlation Between Aggressor and Victim Rows","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Row; Hammer; Row and column spaces; Artifact (error); Correlation","score_opus":0.025053710177181263,"score_gpt":0.24684530834001547,"score_spread":0.22179159816283422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931388259","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030598705,0.000723097,0.4235783,0.0015606163,0.00042325136,0.0017610426,0.0003038832,0.0023796791,0.5689642],"genre_scores_gemma":[0.39144966,0.0022651493,0.025231197,0.0031393915,0.0052085407,0.000008566722,0.027749384,0.05058877,0.49435934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99609965,0.0012396303,0.0005135445,0.0008845744,0.0007318622,0.00053073],"domain_scores_gemma":[0.9980814,0.00018567649,0.00057858956,0.0007055394,0.0002364064,0.000212377],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015985781,0.00032216273,0.00050444395,0.00046085377,0.002060677,0.0015061232,0.0015375005,0.000178391,0.025013559],"category_scores_gemma":[0.0011405196,0.00035308872,0.00010287087,0.00067156466,0.00026069456,0.0004231043,0.0026098578,0.00060869765,0.0024073313],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034993773,0.00007208733,0.000008378858,0.00009711563,0.00016927918,0.0000369474,0.0027229604,0.00011068075,0.0002461161,0.0050362777,0.78289884,0.20825134],"study_design_scores_gemma":[0.0043305545,0.00009628914,0.0000091087,0.00011152658,0.00003945507,0.00004491168,0.00016649681,0.012550105,0.00024385465,0.00039473045,0.9816101,0.00040286192],"about_ca_topic_score_codex":0.00061711686,"about_ca_topic_score_gemma":0.0000061056357,"teacher_disagreement_score":0.39834708,"about_ca_system_score_codex":0.0002002037,"about_ca_system_score_gemma":0.0000101316855,"threshold_uncertainty_score":0.9998921},"labels":[],"label_agreement":null},{"id":"W6939163186","doi":"10.60692/shed7-39w71","title":"Towards a new geological time scale: A template for improved rock-based subdivision of pre-Cryogenian time","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University; University of Victoria; McGill University","funders":"","keywords":"Subdivision; Global Boundary Stratotype Section and Point; Proterozoic; Period (music); Phanerozoic; Time line; Geologic time scale; Mesozoic","score_opus":0.02837866957244144,"score_gpt":0.22760554594826354,"score_spread":0.1992268763758221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939163186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15595832,0.0000031473494,0.8413396,0.00023473898,0.00023545047,0.0011415852,0.00012996692,0.00035055378,0.00060667086],"genre_scores_gemma":[0.98862195,1.9753985e-8,0.010069451,0.00023950884,0.000040543342,0.0002103225,0.000038299742,0.000011116482,0.0007687877],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773204,0.00013363885,0.0009396698,0.0003072634,0.0004635351,0.00042384275],"domain_scores_gemma":[0.99832183,0.000035579273,0.0005442,0.0006696882,0.00026591812,0.00016278242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090111286,0.00022213101,0.00036619738,0.00033900375,0.00034570482,0.00019905402,0.0010159225,0.00008584591,0.00013763348],"category_scores_gemma":[0.000047428097,0.0001973677,0.00017350022,0.00059115386,0.000023261193,0.0009396108,0.0004196485,0.00012430693,0.0005328646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007701877,0.0003089531,0.017632043,0.0039074873,0.00069014315,0.00006262942,0.49595183,0.36323237,0.0077966712,0.012839996,0.027096575,0.06277942],"study_design_scores_gemma":[0.00067818584,0.00055304595,0.0008462262,0.00004060045,0.000015879707,0.00003312247,0.0006147502,0.97874445,0.016677022,0.0000439695,0.0014740803,0.00027864572],"about_ca_topic_score_codex":0.000056563542,"about_ca_topic_score_gemma":3.1052613e-7,"teacher_disagreement_score":0.83266366,"about_ca_system_score_codex":0.00019404812,"about_ca_system_score_gemma":0.00024304882,"threshold_uncertainty_score":0.8048421},"labels":[],"label_agreement":null},{"id":"W6939223020","doi":"10.6084/m9.figshare.24558116","title":"Additional file 1 of Identifying relapse predictors in individual participant data with decision trees","year":2023,"lang":"en","type":"article","venue":"Open MIND","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Decision tree; Identification (biology); Decision tree learning; Data collection","score_opus":0.2542951446503515,"score_gpt":0.3763187699263751,"score_spread":0.12202362527602356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939223020","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29914194,0.00007312619,0.015461104,0.0006884231,0.00057079346,0.0019625993,0.67241883,0.00007055278,0.009612595],"genre_scores_gemma":[0.3962715,0.0000131925535,0.51381946,0.00008120921,0.00014161493,0.0006153708,0.08412127,0.000052094383,0.004884254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828523,0.000064289445,0.0003646388,0.0005126751,0.00047938954,0.00029375762],"domain_scores_gemma":[0.9970707,0.0017487103,0.00013691281,0.0009162558,0.00005062107,0.0000767963],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006244924,0.00009866432,0.00016912485,0.00020581443,0.00008720335,0.00028935954,0.0029296787,0.00004429842,0.18291065],"category_scores_gemma":[0.0010069493,0.00008510465,0.000017490953,0.0012187103,0.00007482701,0.0017744941,0.0023033721,0.0001092386,0.0012376544],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028733217,0.00010333599,0.0003445266,0.0000033912322,0.000029899245,0.00013429242,0.0023328478,0.0007294809,0.00004978452,0.00014984809,0.877903,0.11819091],"study_design_scores_gemma":[0.00078189553,0.0006495142,0.07627749,0.00261187,0.00006979289,0.0000419183,0.0062033534,0.20104626,0.008818836,0.006414685,0.69617915,0.00090522773],"about_ca_topic_score_codex":0.0000861052,"about_ca_topic_score_gemma":0.0023833073,"teacher_disagreement_score":0.5882976,"about_ca_system_score_codex":0.000015007519,"about_ca_system_score_gemma":0.00027646363,"threshold_uncertainty_score":0.99954},"labels":[],"label_agreement":null},{"id":"W6958056017","doi":"10.6084/m9.figshare.24558116.v1","title":"Additional file 1 of Identifying relapse predictors in individual participant data with decision trees","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Decision tree; Identification (biology); Decision tree learning; Data collection","score_opus":0.25016936399942064,"score_gpt":0.34049582705226406,"score_spread":0.09032646305284342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958056017","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000383551,0.000020613807,0.00009499969,0.00003393137,0.000031364816,0.00013115205,0.99894,0.00012906006,0.0002353092],"genre_scores_gemma":[0.018703409,9.140218e-7,0.006028846,0.0000342543,0.000045189474,0.00043693592,0.9745236,0.000013360226,0.00021350465],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834186,0.000046089892,0.00030826943,0.00043695926,0.00054944976,0.0003173611],"domain_scores_gemma":[0.9961707,0.002693662,0.00013347354,0.00084235484,0.00008144732,0.00007836806],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001397432,0.00010724462,0.00014332047,0.00024176476,0.000075859876,0.00011514786,0.001679229,0.000055332253,0.81349766],"category_scores_gemma":[0.005269718,0.00009501257,0.000025744168,0.0013473162,0.000015651662,0.0011196937,0.0012270086,0.00013115091,0.0032633457],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050635895,0.000028943135,0.000028243361,0.000016785227,0.000011285933,0.00007505244,0.0004174717,0.00042628162,0.0000036155084,0.000043567743,0.9938759,0.0050677746],"study_design_scores_gemma":[0.0002873321,0.00027474173,0.07551724,0.012491547,0.000018611096,0.000023313794,0.0009966962,0.17216454,0.0013784602,0.002636912,0.7336113,0.0005993143],"about_ca_topic_score_codex":0.000014999037,"about_ca_topic_score_gemma":0.00053468155,"teacher_disagreement_score":0.81023437,"about_ca_system_score_codex":0.000015730213,"about_ca_system_score_gemma":0.00021328781,"threshold_uncertainty_score":0.99751276},"labels":[],"label_agreement":null},{"id":"W6964230188","doi":"10.25549/chs-m11049","title":"La Fiesta de Los Angeles float, 1915","year":2012,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Front (military); Colored; Center (category theory); Quarter (Canadian coin)","score_opus":0.010644279339718444,"score_gpt":0.18714214846559796,"score_spread":0.1764978691258795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964230188","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046005993,0.00015552413,0.0038386895,0.0001074817,0.000047825786,0.00011025233,0.9921839,0.00016782602,0.0029283897],"genre_scores_gemma":[0.0012877285,0.00008570058,0.0019815825,0.00017556039,0.00017398616,4.398791e-7,0.9948358,0.00003675729,0.0014224473],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985893,0.00009859185,0.00020308973,0.00037189462,0.00029769857,0.00043946502],"domain_scores_gemma":[0.9985498,0.00020377117,0.00021642518,0.00073692336,0.000037155496,0.00025588615],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000119755285,0.00027238982,0.00029907646,0.0002162057,0.00012946197,0.00027850713,0.002120057,0.00032990467,0.0011738876],"category_scores_gemma":[0.000036567995,0.00029708317,0.00019577601,0.0003056094,0.0002882324,0.0011161945,0.0012114927,0.0003447878,0.008721508],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024161383,0.00012745618,0.00059801835,0.00011646233,0.00003500614,0.00017473972,0.000125732,0.000009622922,0.0000024107019,0.00012275945,0.9956568,0.003006848],"study_design_scores_gemma":[0.00007241043,0.000023110066,0.000004514609,0.000100010424,0.00002288864,0.00001689458,0.00087978155,0.00011138093,0.000086259206,0.0009598149,0.997412,0.0003108886],"about_ca_topic_score_codex":0.00013095184,"about_ca_topic_score_gemma":0.00002275128,"teacher_disagreement_score":0.00754762,"about_ca_system_score_codex":0.00005160098,"about_ca_system_score_gemma":0.00026367954,"threshold_uncertainty_score":0.99994814},"labels":[],"label_agreement":null},{"id":"W6968162160","doi":"10.5281/zenodo.15204811","title":"From Code to Clarity: Applying Generative, Analytical, Explainable and Predictive AI in Research","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Code (set theory); Resource (disambiguation); Capstone; Expert system","score_opus":0.09677650972676288,"score_gpt":0.34892253131562456,"score_spread":0.2521460215888617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968162160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06440834,0.00020487158,0.83041245,0.014306458,0.00017848765,0.0018596452,0.00012276367,0.000744887,0.08776211],"genre_scores_gemma":[0.9897376,0.00008244039,0.0063609513,0.0011885273,0.00012912192,0.0000015378582,0.00016192756,0.00037723908,0.0019607022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969133,0.0007941295,0.00031934038,0.00083995913,0.0005170925,0.0006161485],"domain_scores_gemma":[0.99797237,0.00016951338,0.000038119477,0.00070876273,0.0008838226,0.00022738804],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002050944,0.00014199984,0.00019296816,0.00083169,0.002040071,0.0019720125,0.0017417397,0.0000895516,0.00053919345],"category_scores_gemma":[0.0016526796,0.00015760299,0.000025653053,0.0027326297,0.0002193105,0.00073531945,0.0036289857,0.0005962523,0.0013494742],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035011492,0.00058826036,0.00011184692,0.00010832312,0.000113776965,0.0001890812,0.021164892,0.0031748894,0.02081142,0.3483674,0.31919077,0.28582922],"study_design_scores_gemma":[0.0003042527,0.00030739058,0.0010281131,0.00011137169,0.000006112643,0.000008382528,0.0034109475,0.14995328,0.0063666203,0.0218935,0.8163652,0.00024485248],"about_ca_topic_score_codex":0.00029647665,"about_ca_topic_score_gemma":0.000011324776,"teacher_disagreement_score":0.9253292,"about_ca_system_score_codex":0.00033767003,"about_ca_system_score_gemma":0.000021007745,"threshold_uncertainty_score":0.9994281},"labels":[],"label_agreement":null},{"id":"W6968549152","doi":"10.5281/zenodo.15285505","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Control (management); Key (lock); Process (computing); Action (physics); Matching (statistics)","score_opus":0.04140303531784949,"score_gpt":0.2817263463880848,"score_spread":0.2403233110702353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968549152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002015012,0.00011854224,0.8521657,0.0016765123,0.00040589712,0.00043877962,0.000009239499,0.0020900236,0.1410803],"genre_scores_gemma":[0.9893811,0.00003794123,0.0014854348,0.00049726246,0.000120751145,1.4720129e-7,0.00012356084,0.0005543896,0.007799441],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788576,0.0002257325,0.00030333744,0.0006039344,0.0004623263,0.0005188878],"domain_scores_gemma":[0.99876136,0.00004074691,0.000047979946,0.0005566066,0.0003388953,0.00025442083],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00078061153,0.00015624605,0.00013149194,0.0003160319,0.0013962376,0.002828607,0.0019299402,0.000049514845,0.00770073],"category_scores_gemma":[0.0005042306,0.00016561165,0.000059987593,0.0010853214,0.000071124094,0.0008293196,0.0023282527,0.00029421697,0.024516083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024473735,0.00006760986,0.0000012152079,0.00006849305,0.000073347146,0.00011366427,0.017399328,0.028223686,0.00867821,0.13936143,0.4085723,0.39741626],"study_design_scores_gemma":[0.00005619757,0.00035624483,0.000007606729,0.000082698076,0.000004634226,0.00003911227,0.00038911804,0.094801344,0.0076023005,0.00047038446,0.8960051,0.0001852373],"about_ca_topic_score_codex":0.000036234233,"about_ca_topic_score_gemma":2.490944e-7,"teacher_disagreement_score":0.9873661,"about_ca_system_score_codex":0.00025169874,"about_ca_system_score_gemma":0.000008449595,"threshold_uncertainty_score":0.9999038},"labels":[],"label_agreement":null},{"id":"W6976917809","doi":"10.6084/m9.figshare.c.4960382.v1","title":"Severe pain at the end of life: a population-level observational study","year":2020,"lang":"en","type":"other","venue":"Figshare","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Observational study; Referral; Quality of life (healthcare); Population; Palliative care; Cohort study; Disease; Cohort","score_opus":0.22316499669914341,"score_gpt":0.31596926541248843,"score_spread":0.09280426871334502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976917809","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009600471,0.0026081314,0.0038971072,0.0075713973,0.0010061768,0.0075111794,0.66488844,0.0014891668,0.31093243],"genre_scores_gemma":[0.061651908,0.000007653685,0.006573593,0.0068147895,0.0018748489,0.0013374917,0.14203358,0.0007265435,0.7789796],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983218,0.00021425336,0.00030745007,0.00042272694,0.0005439677,0.0001898597],"domain_scores_gemma":[0.99835736,0.00043496027,0.00034574143,0.0006918204,0.000090237554,0.00007986471],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017104943,0.00020344176,0.00024206014,0.000073411255,0.000104477724,0.00008011825,0.0013580435,0.00012196723,0.23110689],"category_scores_gemma":[0.0019775354,0.00016161351,0.000085173306,0.00046210695,0.000010062564,0.00012351488,0.0006502474,0.0001641938,0.0022989851],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002172483,0.000043614862,0.0005334098,0.00007921653,0.000037612717,0.000008139921,0.00038954217,0.00008725926,0.0000011739565,0.00042057585,0.99437445,0.00402283],"study_design_scores_gemma":[0.00012516,0.00013189383,0.018198237,0.0008452389,0.00001113205,0.0000024006633,0.0001964144,0.0093127005,0.000036347148,0.00047283797,0.97018605,0.000481557],"about_ca_topic_score_codex":0.0003817184,"about_ca_topic_score_gemma":0.0015564082,"teacher_disagreement_score":0.52285486,"about_ca_system_score_codex":0.000055954046,"about_ca_system_score_gemma":0.00019452554,"threshold_uncertainty_score":0.9984778},"labels":[],"label_agreement":null},{"id":"W6987899304","doi":"","title":"Unsupervised learning of interpretable models for sparse, smooth data","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Unsupervised learning; Gratitude; Pattern recognition (psychology); Interpretability; Feature (linguistics)","score_opus":0.061729265498892856,"score_gpt":0.2859917548831768,"score_spread":0.22426248938428395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987899304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6419428,0.0027252974,0.025189627,0.000113383256,0.012438735,0.009082334,0.0053951195,0.0022102701,0.30090246],"genre_scores_gemma":[0.96569973,0.00021935695,0.019424003,0.00014887132,0.00004304773,0.000158761,0.0019571786,0.00022007641,0.012128951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937546,0.00037568263,0.0014884027,0.0022496455,0.0010195819,0.0011120454],"domain_scores_gemma":[0.9931572,0.00078612904,0.0010407649,0.003694574,0.0010371715,0.00028413866],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021371471,0.00083276676,0.0011844843,0.00061195286,0.0007802495,0.00030350435,0.0067568775,0.0007553366,0.00008337709],"category_scores_gemma":[0.0011638843,0.0009210977,0.00038326808,0.0009880154,0.00006401645,0.004955507,0.001238718,0.0014303921,0.00027154488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028895086,0.0003051349,0.000015238147,0.0011622625,0.000280061,0.00002046025,0.00012731476,0.013174066,0.034926757,0.7167924,0.000028734015,0.23287861],"study_design_scores_gemma":[0.0008256629,0.0006792917,0.000031471533,0.0014883025,0.00025377248,0.000011306945,0.0012732995,0.57710105,0.23342931,0.13688941,0.04583414,0.002182956],"about_ca_topic_score_codex":0.0007251583,"about_ca_topic_score_gemma":0.00053561473,"teacher_disagreement_score":0.579903,"about_ca_system_score_codex":0.00035589866,"about_ca_system_score_gemma":0.00023078031,"threshold_uncertainty_score":0.99932396},"labels":[],"label_agreement":null},{"id":"W6988028185","doi":"","title":"Visual Explanation of Evidence in Additive Classifiers","year":2006,"lang":"en","type":"article","venue":"NPARC","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Feature (linguistics); Matching (statistics); Set (abstract data type)","score_opus":0.0897363119366656,"score_gpt":0.32485270943714356,"score_spread":0.23511639750047797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6988028185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43510786,0.00008485214,0.5096048,0.0024388144,0.0004207565,0.000378157,0.0000046424693,0.00014254868,0.051817536],"genre_scores_gemma":[0.99134177,0.00001329061,0.008288647,0.00006493339,0.000039526225,0.000017147302,0.0000018267388,0.00000394699,0.00022890176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989206,0.00007627297,0.00027103495,0.00024198212,0.0002808763,0.00020919212],"domain_scores_gemma":[0.99927676,0.00027738625,0.0000964606,0.00020971292,0.0001095844,0.000030077643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033540974,0.00007562449,0.00011090648,0.00017706005,0.00003554596,0.000037441703,0.00041022184,0.000046301557,0.00007259745],"category_scores_gemma":[0.00017463329,0.00006881872,0.00003099218,0.00058218685,0.00006328712,0.0007865012,0.000077053795,0.00008506079,0.000060393213],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033652897,0.00024565935,0.003830614,0.00002422023,0.000006310991,0.000063262196,0.0017530429,0.000925111,0.23270081,0.6057505,0.0048877494,0.14977904],"study_design_scores_gemma":[0.00012191164,0.00017772811,0.015825776,0.00015555363,0.000002764743,0.000004339972,0.0004822707,0.1383717,0.7307768,0.11260119,0.0012502716,0.0002297165],"about_ca_topic_score_codex":0.0002710481,"about_ca_topic_score_gemma":0.0002637768,"teacher_disagreement_score":0.55623394,"about_ca_system_score_codex":0.000082467,"about_ca_system_score_gemma":0.0000721325,"threshold_uncertainty_score":0.2806346},"labels":[],"label_agreement":null},{"id":"W6998841087","doi":"","title":"Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Interpretation (philosophy); Shapley value; Game theory; Feature (linguistics); Context (archaeology)","score_opus":0.019627784395443063,"score_gpt":0.2585945895065906,"score_spread":0.23896680511114754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6998841087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039146733,0.0014100906,0.9668062,0.008087481,0.0001282234,0.00042137614,0.000008030177,0.00011014799,0.019113801],"genre_scores_gemma":[0.94004947,0.00024210359,0.052686237,0.00020850473,0.0000056209715,0.000088365436,0.000023361126,0.000011106816,0.006685253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966234,0.0021295908,0.00040215635,0.0003949537,0.0002214498,0.00022846699],"domain_scores_gemma":[0.9915574,0.00507035,0.00023046749,0.0009652293,0.0021292209,0.000047314585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004772062,0.00014642427,0.00019303542,0.00014567192,0.00049865135,0.0002801271,0.0014478432,0.00006174792,0.00001855306],"category_scores_gemma":[0.0026051176,0.00012247048,0.000112557645,0.00070201023,0.00019971697,0.00052026164,0.0004418478,0.0001986232,0.0000073972324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017376175,0.00011532306,0.00013955141,0.000031345593,0.000042936063,2.7763915e-7,0.01986371,0.013233362,0.0018448278,0.8714665,0.0002801188,0.09296468],"study_design_scores_gemma":[0.00012597589,0.0000011213286,0.000069878246,0.00021461357,0.000013090848,8.0542105e-7,0.00044355824,0.8499082,0.103579864,0.044150006,0.0013972846,0.00009563055],"about_ca_topic_score_codex":0.00043919188,"about_ca_topic_score_gemma":0.00078888854,"teacher_disagreement_score":0.93613476,"about_ca_system_score_codex":0.000054530985,"about_ca_system_score_gemma":0.00015725972,"threshold_uncertainty_score":0.49942014},"labels":[],"label_agreement":null},{"id":"W7009631941","doi":"","title":"Explaining black box algorithms: epistemological challenges and machine learning solutions","year":2021,"lang":"en","type":"dissertation","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Counterintuitive; Black box; Counterfactual conditional; Intersection (aeronautics); Feature (linguistics); Thought experiment; Algorithmic learning theory; Independence (probability theory); Interpretation (philosophy)","score_opus":0.08439689035374899,"score_gpt":0.2896423948841034,"score_spread":0.20524550453035445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009631941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1543126,0.009651256,0.4201216,0.0077054217,0.000841437,0.0026138525,0.0004170825,0.0009612034,0.40337554],"genre_scores_gemma":[0.482484,0.2292405,0.17663978,0.00005977409,0.00029338177,0.0000033599088,0.0027302455,0.00018283354,0.1083661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99445724,0.0014375125,0.00028667675,0.0014215936,0.0011345117,0.0012624325],"domain_scores_gemma":[0.9961865,0.0011558895,0.00035173554,0.00085476413,0.00092065835,0.00053047744],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0015698342,0.00044519157,0.00077240396,0.0014678283,0.0023049484,0.00013687945,0.002724643,0.0004407979,0.00014286493],"category_scores_gemma":[0.0003864582,0.00059615285,0.00032660025,0.0011875018,0.0011115543,0.0012156552,0.002582632,0.0021599934,0.000022203016],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012565617,0.0009719233,0.0010290889,0.0015754858,0.00089819863,0.0064087217,0.105664104,0.0007075473,0.0019929963,0.5365103,0.0016911291,0.341294],"study_design_scores_gemma":[0.0016795237,0.002349637,0.00819294,0.0013255164,0.00018282507,0.00009703158,0.52012444,0.14161639,0.000680781,0.022989342,0.29881415,0.001947453],"about_ca_topic_score_codex":0.0011101639,"about_ca_topic_score_gemma":0.007523486,"teacher_disagreement_score":0.5135209,"about_ca_system_score_codex":0.0003351614,"about_ca_system_score_gemma":0.0006727118,"threshold_uncertainty_score":0.999649},"labels":[],"label_agreement":null},{"id":"W7017822690","doi":"","title":"CAMEO: Explaining Consensus and Expertise Across MOdels","year":2024,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Variety (cybernetics); Feature (linguistics); Test (biology); Space (punctuation); Key (lock); Multiple Models","score_opus":0.02551582153685272,"score_gpt":0.24941663359785793,"score_spread":0.2239008120610052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017822690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99390936,0.0010553455,0.002185043,0.00087399123,0.00064834836,0.00022650622,0.000020068399,0.00021514535,0.000866195],"genre_scores_gemma":[0.7050986,0.0003539352,0.009429015,0.000042021045,0.00004577405,0.0000016273196,0.00005632145,0.000043524367,0.28492913],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99822086,0.00006051164,0.00018524023,0.0007330827,0.0003360286,0.0004642616],"domain_scores_gemma":[0.99884576,0.000071116825,0.00017762701,0.000538149,0.00020765682,0.00015969925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022893489,0.00029339732,0.00040710106,0.00023560735,0.00035035232,0.00018038854,0.0008166565,0.00029397444,0.000022994327],"category_scores_gemma":[0.000018790408,0.00034889398,0.00013163291,0.00032803675,0.00015832689,0.0005844427,0.00034139535,0.00031858162,0.00010331176],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000749202,0.000038740283,0.000019342715,0.00034220342,0.00009419279,0.00054832775,0.9512607,0.000580247,0.0038952671,0.016660573,0.0014207436,0.025064746],"study_design_scores_gemma":[0.00028278123,0.00018904365,0.00009890903,0.00072512863,0.000076193246,0.000032367938,0.7620048,0.2075924,0.016888415,0.010748789,0.000509185,0.00085198064],"about_ca_topic_score_codex":0.028700337,"about_ca_topic_score_gemma":0.043214973,"teacher_disagreement_score":0.2888107,"about_ca_system_score_codex":0.000096416836,"about_ca_system_score_gemma":0.00011608943,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W7020563275","doi":"","title":"Le Guide pratique des carrières d'avenir au Québec","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.021000788617256266,"score_gpt":0.25096542903574465,"score_spread":0.22996464041848838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020563275","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011935268,0.01321213,0.038786605,0.045099452,0.0006881662,0.0012131113,0.00028123692,0.00047337066,0.8883107],"genre_scores_gemma":[0.15069604,0.0007949102,0.010930222,0.0028895754,0.0013869638,0.0004317973,0.000036673537,0.00048772353,0.8323461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911993,0.0011084869,0.0017569518,0.001959815,0.0025163118,0.0014591494],"domain_scores_gemma":[0.985924,0.009543277,0.0013413595,0.0016822065,0.00055183255,0.0009572907],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.001399311,0.0013773562,0.001147869,0.0017203622,0.0010940607,0.0016100728,0.004099125,0.0004039926,0.006039362],"category_scores_gemma":[0.010391812,0.0014586976,0.0006005565,0.0021842464,0.002110409,0.0024287181,0.0020317684,0.0010357165,0.003531641],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00013473432,0.0010369631,0.0189864,0.0004268166,0.00060042343,0.00021786141,0.040879883,0.0023297053,0.0010412679,0.47936267,0.45016268,0.004820597],"study_design_scores_gemma":[0.00061375235,0.00039243654,0.011522395,0.0006759672,0.000096696465,0.00017444386,0.0010171724,0.005903592,0.0028590397,0.004152402,0.97105306,0.0015390151],"about_ca_topic_score_codex":0.97264194,"about_ca_topic_score_gemma":0.999749,"teacher_disagreement_score":0.5208904,"about_ca_system_score_codex":0.030483894,"about_ca_system_score_gemma":0.5113442,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W7020891162","doi":"","title":"More than meets the eyes, women's narratives of their experience of an eating disorder","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative; Qualitative research; Eating disorders; Identity (music); Ambivalence; Intervention (counseling)","score_opus":0.004437880716472076,"score_gpt":0.1713230279576406,"score_spread":0.1668851472411685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020891162","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15460171,0.0014378069,0.0009888703,0.0029785088,0.0002820569,0.00054027664,0.00031694444,0.000040721465,0.8388131],"genre_scores_gemma":[0.9443707,0.00017627665,0.0029582595,0.00047364456,0.000052341846,0.00003125328,0.000004398381,0.00007784769,0.05185528],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99757767,0.00012425505,0.0003619036,0.00034999487,0.0012546518,0.00033153422],"domain_scores_gemma":[0.99867487,0.00016441992,0.00040672225,0.0005998469,8.468632e-7,0.00015329098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000017885977,0.00025870564,0.00036735646,0.0000426679,0.00013050775,0.00002720825,0.001204123,0.00004122806,0.00012401374],"category_scores_gemma":[0.000002948396,0.00018973708,0.000033989163,0.00017312114,0.00031462946,0.00042174695,0.00024980574,0.00012775834,1.9662945e-9],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075384835,0.0006084985,0.01866925,0.0019550927,0.0007773833,0.00022860522,0.17391798,0.0013646664,0.048465453,0.5552965,0.010239467,0.18772328],"study_design_scores_gemma":[0.00039384785,0.00068462244,0.0067955665,0.001388151,0.000018888928,0.00001235605,0.2966499,0.014494829,0.3245591,0.008091044,0.3454656,0.0014460796],"about_ca_topic_score_codex":0.009281163,"about_ca_topic_score_gemma":0.04878333,"teacher_disagreement_score":0.789769,"about_ca_system_score_codex":0.000005354857,"about_ca_system_score_gemma":0.0009272004,"threshold_uncertainty_score":0.9973161},"labels":[],"label_agreement":null},{"id":"W7023945779","doi":"","title":"Photosynthetic characteristics of sinking microalgae under the sea ice","year":2014,"lang":"en","type":"article","venue":"Institutional Repository National Institute of Polar Research (National Institute of Polar Research (Japan))","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phytoplankton; Sea ice; Photosynthesis; Chlorophyll a; Water column; Algal mat; Photosynthetically active radiation; Bloom","score_opus":0.0893767167420057,"score_gpt":0.3683418370270795,"score_spread":0.2789651202850738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023945779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7762666,0.0014674878,0.11822685,0.010682164,0.0049211513,0.0033432988,0.0010438325,0.00022841785,0.083820224],"genre_scores_gemma":[0.98990816,0.00011066549,0.007789387,0.00016937406,0.0008296451,0.00012748083,0.00021610256,0.000042028943,0.00080715015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9817357,0.0017194839,0.0021622316,0.0012055824,0.011856471,0.0013205174],"domain_scores_gemma":[0.97720623,0.0028075925,0.00083648955,0.0013179638,0.017377391,0.0004543299],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.017478572,0.0005097293,0.0007768305,0.0026254053,0.0029698645,0.00044528424,0.004858396,0.00042529745,0.00005423969],"category_scores_gemma":[0.010827506,0.00045958793,0.00040946266,0.0039322847,0.008439288,0.0038522682,0.0016228107,0.0020649568,0.0001313471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013803558,0.0008244442,0.0012706096,0.0002553935,0.00021808496,0.000023983024,0.000266422,0.007409433,0.09181532,0.89520985,0.0007319247,0.0018365282],"study_design_scores_gemma":[0.0020845125,0.0012913214,0.040304683,0.0017707018,0.000059659233,0.0006921596,0.0006332643,0.04997679,0.48683003,0.20781484,0.20695877,0.0015832633],"about_ca_topic_score_codex":0.0031594802,"about_ca_topic_score_gemma":0.00047461293,"teacher_disagreement_score":0.687395,"about_ca_system_score_codex":0.0015554288,"about_ca_system_score_gemma":0.009591383,"threshold_uncertainty_score":0.9997856},"labels":[],"label_agreement":null},{"id":"W7024547198","doi":"","title":"Sharing intimate images without consent may soon land you on sex offender list","year":2023,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sex offender; Inequality; Interrogation; Criminal justice; Informed consent; Forensic psychology","score_opus":0.019916260025826412,"score_gpt":0.23585152813825752,"score_spread":0.2159352681124311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024547198","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014074646,0.00006651063,0.000077693876,0.0004410606,0.0005684269,0.00046335996,0.000048139664,0.0010145018,0.99717957],"genre_scores_gemma":[0.0054809,0.00013438836,0.0024064102,0.00032936363,0.00013335048,0.000025004025,0.0000259179,0.00018231504,0.99128234],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99771714,0.00007077019,0.0006956842,0.00046040997,0.0005745453,0.0004814546],"domain_scores_gemma":[0.9980821,0.00019581239,0.0005670426,0.0008675721,0.00014377222,0.00014367074],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004358907,0.00042039595,0.0004614312,0.00019002326,0.00011888757,0.0003235904,0.0010875122,0.00030245876,0.03857404],"category_scores_gemma":[0.00020322615,0.00040994165,0.00014882756,0.000024337121,0.00015390331,0.0000011464113,0.000531209,0.0003619867,0.01932089],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025543091,0.00004022121,0.00005873925,0.00029521532,0.000051885643,0.00006045681,0.00032593528,0.0017916124,0.0000010557504,0.0005033971,0.9948673,0.0019786383],"study_design_scores_gemma":[0.0001869641,0.00011692348,0.000013552126,0.00045816417,0.000018459754,0.000036721736,0.00010927789,0.0019494776,0.0003921618,0.000120814475,0.99615955,0.000437928],"about_ca_topic_score_codex":0.008371958,"about_ca_topic_score_gemma":0.002656991,"teacher_disagreement_score":0.01925315,"about_ca_system_score_codex":0.00008821365,"about_ca_system_score_gemma":0.000050874052,"threshold_uncertainty_score":0.99983525},"labels":[],"label_agreement":null},{"id":"W7024982779","doi":"","title":"Stock market reactions to changes in the FTSE SmallCap and S&amp;P/TSX SmallCap indices","year":2010,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Nucleofection; Gestational period; Hyporeflexia; Fusible alloy; TSG101; Hemopericardium; Demotion; Diafiltration","score_opus":0.01964985352938858,"score_gpt":0.20994008949760806,"score_spread":0.19029023596821948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024982779","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013928315,0.00011750243,0.009821497,0.00015865169,0.00088083436,0.0012273962,0.00009839498,0.0007420557,0.9730254],"genre_scores_gemma":[0.0045772507,0.000113202565,0.0010370351,0.00012726318,0.00015773908,0.0000010802459,0.0000135973,0.000085761654,0.99388707],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997334,0.00021089861,0.00021879739,0.0010917112,0.00050952757,0.00063508045],"domain_scores_gemma":[0.9977159,0.00028244444,0.00034236084,0.0011499977,0.00013718703,0.0003721325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000015712163,0.0005138894,0.00041660728,0.0018809115,0.00051920704,0.000580135,0.002919946,0.00055549317,0.000037546462],"category_scores_gemma":[0.00008148845,0.0005552286,0.00014943826,0.0015934894,0.00020983479,0.0013043872,0.0013718054,0.0007772746,0.00010993236],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019459843,0.00049165916,0.006566428,0.00021444127,0.00020078974,0.0010357128,0.0008113116,0.000045845794,0.005102865,0.0021998216,0.97805095,0.005085608],"study_design_scores_gemma":[0.00021331801,0.00014336513,0.0011412214,0.00016128307,0.00004785954,0.00010034339,0.005483887,0.000011546812,0.00012718388,0.000059911636,0.9918828,0.0006272884],"about_ca_topic_score_codex":0.0014290287,"about_ca_topic_score_gemma":0.037017044,"teacher_disagreement_score":0.035588015,"about_ca_system_score_codex":0.00030860785,"about_ca_system_score_gemma":0.00019877749,"threshold_uncertainty_score":0.99968994},"labels":[],"label_agreement":null},{"id":"W7025019453","doi":"","title":"This is not a peace pipe towards a critical indigenous philosophy","year":2006,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Politics; Critical theory; Political philosophy; Indigenous rights; Indigenous culture","score_opus":0.03430974960013838,"score_gpt":0.2901189485520834,"score_spread":0.25580919895194504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025019453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012517637,0.00032373986,0.6336052,0.02902555,0.0006300539,0.0003583191,0.000009918695,0.00084817316,0.32268143],"genre_scores_gemma":[0.94886065,0.000013153594,0.039544582,0.004518865,0.000354363,0.000029652736,0.0000018425795,0.000020145104,0.006656767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975863,0.000068121924,0.00038910448,0.0006514836,0.00059075,0.0007142454],"domain_scores_gemma":[0.9985197,0.00016377389,0.000049465005,0.0008582765,0.0002457727,0.00016296735],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033017178,0.0002286356,0.00022641165,0.00016911823,0.0003216088,0.00039355143,0.0013150956,0.00012362475,0.0008569433],"category_scores_gemma":[0.00012255265,0.00021083074,0.00012996315,0.0006613523,0.00015581641,0.00082642934,0.00035783637,0.00022462379,0.0033711393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012617714,0.0003647099,0.00010944826,0.000029897983,0.000011484481,0.00026098287,0.0042230194,0.000015591888,0.0046297936,0.94990104,0.020348554,0.020092854],"study_design_scores_gemma":[0.00022493508,0.00050193944,0.00035373252,0.000046424244,0.00002032048,0.00018098441,0.00017529762,0.028119152,0.580646,0.31333917,0.075249456,0.0011426237],"about_ca_topic_score_codex":0.0028819365,"about_ca_topic_score_gemma":0.00007441114,"teacher_disagreement_score":0.936343,"about_ca_system_score_codex":0.00010312469,"about_ca_system_score_gemma":0.00018632865,"threshold_uncertainty_score":0.9974049},"labels":[],"label_agreement":null},{"id":"W7029905003","doi":"","title":"Le discours miterrandien envers l'Allemagne de 1981 à 1991 : une rhétorique pour la grandeur et l'indépendance de la France","year":2010,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Derogation; Public investment; Context (archaeology); Face (sociological concept)","score_opus":0.003431736132328979,"score_gpt":0.17463656424254956,"score_spread":0.17120482811022059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7029905003","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008904547,0.0011522063,0.020711066,0.052025825,0.0007365471,0.00040490064,0.00026816162,0.00003844308,0.9157583],"genre_scores_gemma":[0.5879857,0.000947267,0.014653101,0.0025188175,0.000246562,0.000035138135,0.0000097840475,0.00013690814,0.3934667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568516,0.00063623337,0.00049881195,0.00075380853,0.0015143576,0.0009116158],"domain_scores_gemma":[0.9970303,0.0012566019,0.00042723306,0.0006290566,0.000002467866,0.00065429887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012720963,0.0005528488,0.0005805487,0.00006873408,0.00035512281,0.00020985684,0.0013146232,0.00021824807,0.00021681681],"category_scores_gemma":[0.000029983377,0.0005952304,0.000104574654,0.00022835337,0.0006017629,0.00081828685,0.00039860787,0.000906711,8.7546056e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017641936,0.00012252112,0.0054032905,0.00034507347,0.00012299417,0.0008899745,0.0019450015,0.0005197379,0.020392891,0.9475504,0.0045118732,0.018019812],"study_design_scores_gemma":[0.0005494137,0.000100502664,0.011681516,0.00068236375,0.00003532232,0.00009504051,0.0016622692,0.009319653,0.046379104,0.022622496,0.90603304,0.0008392603],"about_ca_topic_score_codex":0.1387644,"about_ca_topic_score_gemma":0.4447635,"teacher_disagreement_score":0.9249279,"about_ca_system_score_codex":0.00003280778,"about_ca_system_score_gemma":0.008756963,"threshold_uncertainty_score":0.9996499},"labels":[],"label_agreement":null},{"id":"W7033665926","doi":"","title":"Representing nature in Elizabeth Posthuma Simcoe’s Diary: an examination of Toronto’s colonial past (Canada)","year":2012,"lang":"en","type":"article","venue":"York University Digital Library (York University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Colonialism; Reading (process); Race (biology); White (mutation); Order (exchange); Government (linguistics)","score_opus":0.010352429611998528,"score_gpt":0.18564373815137233,"score_spread":0.1752913085393738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033665926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8392077,0.00020421398,0.003100085,0.0005424578,0.00046075124,0.00036139178,0.00013407684,0.00032304582,0.15566625],"genre_scores_gemma":[0.99494183,0.000024897141,0.0011976042,0.00008078208,0.00008855172,5.909968e-8,0.0000752308,0.0000163629,0.003574659],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980036,0.00027389743,0.0002067069,0.00050487346,0.00042471784,0.00058619137],"domain_scores_gemma":[0.99854016,0.00024855853,0.00021711012,0.00060753897,0.00007353724,0.00031310448],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00015331048,0.00023238087,0.00026851232,0.0003134465,0.00025148358,0.00017989395,0.0017863495,0.00023669156,0.000067110734],"category_scores_gemma":[0.00004215904,0.00030257925,0.00009294124,0.001301473,0.00014086434,0.015206447,0.00088430743,0.00032159357,0.000009914511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039183968,0.0013463825,0.24122255,0.000084312735,0.00011742681,0.00094253727,0.0076230327,0.0006020232,0.00037167643,0.69975877,0.006994563,0.040544912],"study_design_scores_gemma":[0.0018563305,0.0007432855,0.29426205,0.00030696744,0.00008111334,0.00003793957,0.044423897,0.009249841,0.01107892,0.0013110042,0.63412577,0.002522898],"about_ca_topic_score_codex":0.017309058,"about_ca_topic_score_gemma":0.029696474,"teacher_disagreement_score":0.69844776,"about_ca_system_score_codex":0.00045803175,"about_ca_system_score_gemma":0.00038831763,"threshold_uncertainty_score":0.99994266},"labels":[],"label_agreement":null},{"id":"W7036181783","doi":"","title":"ARCHIVEIT-3490-TWELVE_HOURS-EOFZCA-20130206170914-00000-crawling113.us.archive.org-6681.warc.gz","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Identification (biology); Product (mathematics)","score_opus":0.008722605257358287,"score_gpt":0.19934373735934793,"score_spread":0.19062113210198964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036181783","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006539619,0.00026416715,0.0010171889,0.0004393316,0.0010172558,0.0010936495,0.00013362843,0.00080868666,0.9951607],"genre_scores_gemma":[0.0009022783,0.00040992597,0.014959493,0.0007952965,0.0005124004,0.00008305406,0.00015931782,0.00023566603,0.9819426],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951698,0.00027533644,0.0014464036,0.00080219225,0.0011586052,0.001147665],"domain_scores_gemma":[0.9959629,0.00038245512,0.0012442748,0.0016190263,0.00032249145,0.00046882898],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00051721785,0.0008929526,0.0009259967,0.0004003981,0.00026026086,0.00039368862,0.002876728,0.0005986247,0.2419358],"category_scores_gemma":[0.00025559947,0.0008932499,0.0004499926,0.000050706378,0.0004692403,0.0000036371846,0.0008661861,0.0008590079,0.12168839],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037458827,0.00011589456,0.00001534245,0.00039974626,0.00010488767,0.00005652858,0.0005102134,0.00033244386,0.0000068729646,0.0028790527,0.9894381,0.00610344],"study_design_scores_gemma":[0.00032729813,0.00029762633,0.00002973621,0.0004183124,0.000042668176,0.00010718203,0.0001349508,0.0012173395,0.00023456944,0.00044861413,0.9958156,0.0009261214],"about_ca_topic_score_codex":0.013414196,"about_ca_topic_score_gemma":0.0016907458,"teacher_disagreement_score":0.120247416,"about_ca_system_score_codex":0.000112211696,"about_ca_system_score_gemma":0.00016116876,"threshold_uncertainty_score":0.9993518},"labels":[],"label_agreement":null},{"id":"W7037379763","doi":"","title":"Elements in autopsy liver tissue samples from Greenlandic Inuit and Danes:II. Iron measured by X-ray fluorescence spectometry","year":2000,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Liver tissue; Fluorescence; Autopsy; Fluorescence spectroscopy; Fluorescent staining","score_opus":0.0211583596697163,"score_gpt":0.25095033224946767,"score_spread":0.22979197257975137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037379763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97542334,0.00076891546,0.021395972,0.00032692327,0.00011710266,0.00035774385,0.00002472687,0.00020478509,0.0013805162],"genre_scores_gemma":[0.9588161,0.00022595645,0.03832955,0.00026110798,0.00005425644,0.000014859528,0.000010827811,0.000014896413,0.0022724469],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976244,0.0001263956,0.00044198934,0.00076069037,0.00051545457,0.00053106993],"domain_scores_gemma":[0.9989517,0.00012912025,0.00007191499,0.0006270511,0.000044784396,0.00017546919],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041606766,0.00024483266,0.00026605758,0.00019807061,0.0001765206,0.00021239884,0.0009669416,0.000106126965,0.0021655338],"category_scores_gemma":[0.000066612185,0.00022948475,0.000029431701,0.00077711564,0.00010255689,0.0008057709,0.0002587193,0.00018975309,0.0004058563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065917986,0.00057885196,0.056628883,0.000039497,0.00003881017,0.00028181824,0.015182458,0.00014654173,0.074849375,0.0054826853,0.0054038875,0.84130126],"study_design_scores_gemma":[0.0021499258,0.0013552262,0.32150075,0.00037570822,0.000051789215,0.000055344557,0.0014867822,0.18623619,0.4192704,0.018106753,0.04612618,0.0032849628],"about_ca_topic_score_codex":0.010660812,"about_ca_topic_score_gemma":0.003551249,"teacher_disagreement_score":0.83801633,"about_ca_system_score_codex":0.00013315938,"about_ca_system_score_gemma":0.00005491598,"threshold_uncertainty_score":0.99874663},"labels":[],"label_agreement":null},{"id":"W7038989158","doi":"","title":"Intentionnalité, point de vue et effets de discours dans les chroniques de Louis-Gilles Francoeur : suivi de, Contes orduriers -- texte dramatique","year":2006,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ideology; Relation (database); Section (typography); Natural (archaeology); Reading (process); Discourse analysis; Position (finance)","score_opus":0.0033849374031177755,"score_gpt":0.18042625145888513,"score_spread":0.17704131405576737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038989158","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010374753,0.0010850151,0.29935002,0.008943072,0.00022690186,0.00046642267,0.0003152969,0.00013811051,0.6791004],"genre_scores_gemma":[0.73536056,0.00076630485,0.035366494,0.00384416,0.00021215032,0.00007427367,0.000029460953,0.00026165985,0.22408491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970122,0.0003755504,0.00039509055,0.00045351902,0.0009585191,0.00080512714],"domain_scores_gemma":[0.99845463,0.00036485816,0.00033367504,0.00042572213,0.000002173487,0.000418959],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000097521224,0.0003901094,0.00040329696,0.00008030908,0.0001950527,0.00012919377,0.0009101782,0.00011217812,0.000060623242],"category_scores_gemma":[0.00002604389,0.0003882492,0.0000792136,0.000121838246,0.00023458044,0.0004127421,0.000264657,0.00032739923,1.3964353e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013221671,0.00017052866,0.042749695,0.0009639074,0.00030195815,0.0007605491,0.0044564395,0.00094227673,0.013450581,0.83057106,0.09829353,0.007207246],"study_design_scores_gemma":[0.000932007,0.0005099964,0.042395342,0.004909721,0.00013373283,0.00016527998,0.019341184,0.056758005,0.39595687,0.101058185,0.37498623,0.0028534664],"about_ca_topic_score_codex":0.1233397,"about_ca_topic_score_gemma":0.55157757,"teacher_disagreement_score":0.7295129,"about_ca_system_score_codex":0.00010698407,"about_ca_system_score_gemma":0.0044063707,"threshold_uncertainty_score":0.99985695},"labels":[],"label_agreement":null},{"id":"W7039356105","doi":"","title":"Medium and message : the confluence of Saxon and Frankish values as portrayed in the Old Saxon Heliand","year":2005,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"McGill University","keywords":"Battle; Scholarship; EPIC; Spirituality; Confluence; Power (physics)","score_opus":0.016616660022219853,"score_gpt":0.2600127870456585,"score_spread":0.24339612702343866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039356105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97218794,0.001926008,0.000005098345,0.00032067797,0.00053357595,0.0011064765,0.00008276252,0.00009410146,0.023743365],"genre_scores_gemma":[0.99550676,0.0013748024,0.0005614479,0.0009739001,0.000045841512,0.00011474152,0.00003719547,0.00005347813,0.0013318304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9952325,0.0006857176,0.0010619558,0.0011523606,0.0011702906,0.00069715147],"domain_scores_gemma":[0.9965052,0.0010333207,0.0006516086,0.0012650251,0.00035910695,0.00018573707],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003100205,0.0006236236,0.00067912764,0.0003575964,0.00089795474,0.00034626957,0.0021532294,0.0005226388,0.000064189924],"category_scores_gemma":[0.0009561136,0.00045372892,0.00014906088,0.0009749786,0.00029805372,0.0014124821,0.0002699492,0.0013649797,0.000037658676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025298027,0.0003915276,0.00048303517,0.00058140047,0.00018423372,0.00030065817,0.0020209868,0.00008924127,0.039606977,0.61630094,0.000022648594,0.33976534],"study_design_scores_gemma":[0.0014695592,0.0010630907,0.03153403,0.0020942462,0.00035146304,0.00032512867,0.013849635,0.0014031316,0.6742258,0.2236851,0.047161754,0.0028370658],"about_ca_topic_score_codex":0.0013833441,"about_ca_topic_score_gemma":0.004696747,"teacher_disagreement_score":0.6346188,"about_ca_system_score_codex":0.00011966913,"about_ca_system_score_gemma":0.00009410674,"threshold_uncertainty_score":0.99979144},"labels":[],"label_agreement":null},{"id":"W7039382887","doi":"","title":"Methane steam reforming over LaCr¦1¦-¦xNi¦xO¦3 perovskite catalysts","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Steam reforming; Perovskite (structure); Catalysis; Methane; Methane reformer; Methanation","score_opus":0.004253599344050588,"score_gpt":0.16148801852994316,"score_spread":0.15723441918589257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039382887","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010791605,0.001580932,0.00044409416,0.0013412056,0.00048718048,0.00030176612,0.00022046587,0.00008074899,0.99446446],"genre_scores_gemma":[0.07477123,0.0011258741,0.0033143451,0.0023710164,0.00031521372,0.00002506645,0.000032740914,0.0002660632,0.91777843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958791,0.000106944506,0.00048128326,0.0006893448,0.002176824,0.00066648005],"domain_scores_gemma":[0.9981578,0.00018379359,0.00036242412,0.00086195517,4.9559424e-7,0.00043353508],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000020770343,0.0004622347,0.00055357965,0.000114711365,0.00015811458,0.000064110165,0.0012828048,0.000105986626,0.00027830282],"category_scores_gemma":[0.0000032745252,0.00044474678,0.00007133843,0.00022324236,0.00011799947,0.0007272562,0.00048374035,0.00031027052,7.815927e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006419722,0.00028686767,0.0028833896,0.0017715149,0.0011492523,0.0028026225,0.0014789387,0.00025146035,0.030363942,0.3499694,0.28785896,0.32054168],"study_design_scores_gemma":[0.00019921624,0.000086018,0.00036696056,0.0004419049,0.000030989395,0.000021515738,0.00075372506,0.0016546809,0.12328095,0.0011973779,0.87119335,0.00077333534],"about_ca_topic_score_codex":0.018891558,"about_ca_topic_score_gemma":0.10002485,"teacher_disagreement_score":0.5833344,"about_ca_system_score_codex":0.000017092189,"about_ca_system_score_gemma":0.0018636966,"threshold_uncertainty_score":0.99980044},"labels":[],"label_agreement":null},{"id":"W7039951084","doi":"","title":"Table of Contents","year":2013,"lang":"en","type":"article","venue":"Archivaria","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.02854216567066083,"score_gpt":0.25008636675671075,"score_spread":0.2215442010860499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039951084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036525436,0.00003851433,0.78458816,0.001393301,0.0003863512,0.00032406574,0.0000019655738,0.00012607784,0.17661613],"genre_scores_gemma":[0.9600574,0.0000039703355,0.038813595,0.00022044568,0.000021677464,0.00001999956,8.3739906e-7,0.0000052415944,0.00085688365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99911124,0.000044796652,0.00021646952,0.00020494845,0.00016360139,0.00025895727],"domain_scores_gemma":[0.99911016,0.00012213328,0.00006865893,0.00052350713,0.00009699854,0.00007855155],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011734297,0.00007504611,0.000118686,0.000066372326,0.000056227203,0.000068716006,0.000842637,0.000020396488,0.00016918493],"category_scores_gemma":[0.0000883851,0.00006761859,0.000035148954,0.00025517112,0.00005652963,0.0005591503,0.00025143506,0.00007016615,0.0009117609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001331595,0.000043750137,0.0007877384,0.000005348655,0.000008039266,0.0000023741047,0.000472981,0.000043841985,0.03556515,0.9503659,0.0020473613,0.0106561845],"study_design_scores_gemma":[0.00012305823,0.00011519592,0.010524766,0.00002378926,0.0000030076303,0.0000073269634,0.00008869164,0.06477247,0.16015539,0.759841,0.004161962,0.00018330495],"about_ca_topic_score_codex":0.0014592482,"about_ca_topic_score_gemma":0.000004906627,"teacher_disagreement_score":0.9235319,"about_ca_system_score_codex":0.0000067947767,"about_ca_system_score_gemma":0.000031070493,"threshold_uncertainty_score":0.9998661},"labels":[],"label_agreement":null},{"id":"W7088512390","doi":"10.5281/zenodo.17327407","title":"Anisodactylus (Anisodactylus) californicus Dejean 1829","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ectotherm; Cannibalism; Context (archaeology); Population","score_opus":0.02874844257387879,"score_gpt":0.2640888384302528,"score_spread":0.23534039585637404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7088512390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060976455,0.00018076014,0.623822,0.004384954,0.00044051546,0.000663796,0.000073675976,0.0026756783,0.361661],"genre_scores_gemma":[0.98746264,0.000121223704,0.004996921,0.0012713595,0.00015321566,1.9012495e-7,0.00028558608,0.00086011743,0.0048487308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997326,0.00038735947,0.00041583844,0.0007295741,0.00046312573,0.0006780623],"domain_scores_gemma":[0.9977258,0.00007556796,0.0001199568,0.001143239,0.000706339,0.00022911715],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009650471,0.00021737556,0.00021145213,0.00041839652,0.0028978612,0.0019563662,0.0034727221,0.00009915021,0.002778354],"category_scores_gemma":[0.0009431694,0.00023255967,0.00009163831,0.0016701327,0.00018358478,0.00076212984,0.0027681147,0.00034514407,0.012643514],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051196585,0.0002857904,0.000006696319,0.00007011501,0.00006968869,0.00006480696,0.0016552265,0.00024161523,0.0120463185,0.4366137,0.23088631,0.31800854],"study_design_scores_gemma":[0.00024953202,0.0001541567,0.00015299521,0.00003830084,0.000010204641,0.000056967885,0.00031247255,0.009113194,0.014974678,0.006590107,0.96808213,0.0002652745],"about_ca_topic_score_codex":0.00007881214,"about_ca_topic_score_gemma":0.00000226435,"teacher_disagreement_score":0.981365,"about_ca_system_score_codex":0.00031082373,"about_ca_system_score_gemma":0.000019528234,"threshold_uncertainty_score":0.9990797},"labels":[],"label_agreement":null},{"id":"W7099779771","doi":"","title":"Correspondence","year":2006,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Staphylococcus aureus; Identification (biology); Amino acid; Bacteria; Staphylococcus; Bacterial protein","score_opus":0.009490534985629686,"score_gpt":0.22513769952705556,"score_spread":0.21564716454142588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099779771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0109404335,0.0000364979,0.83003765,0.000817691,0.0002452349,0.000051965202,1.2436556e-7,0.00028749765,0.15758291],"genre_scores_gemma":[0.92390645,0.0000014899659,0.044601526,0.0005130163,0.00007132721,0.0000068900235,3.7326035e-7,0.0000041626195,0.030894779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991924,0.000023253599,0.00013854103,0.00023059761,0.00018289835,0.00023230912],"domain_scores_gemma":[0.99937713,0.000076300785,0.000026303043,0.00042069802,0.00006103121,0.00003855829],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016372115,0.00006640499,0.000058506805,0.000064145235,0.00008329295,0.0001479524,0.00073880586,0.00002669403,0.00025259878],"category_scores_gemma":[0.000027162618,0.000058993213,0.000028576973,0.0003941405,0.000031642718,0.00054488546,0.00013185048,0.000050590235,0.002994797],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011982311,0.00002531038,0.00042691673,8.579773e-7,5.962953e-7,0.000022306076,0.00004164704,0.0002624242,0.0036444971,0.97332835,0.015188197,0.0070577045],"study_design_scores_gemma":[0.000081338185,0.000089372494,0.0038725846,0.0000091210895,0.000001751375,0.000041262334,0.000076716395,0.1719527,0.40526807,0.29279467,0.12540042,0.00041196603],"about_ca_topic_score_codex":0.0004646556,"about_ca_topic_score_gemma":0.000114586204,"teacher_disagreement_score":0.912966,"about_ca_system_score_codex":0.000023257347,"about_ca_system_score_gemma":0.00003424866,"threshold_uncertainty_score":0.9977815},"labels":[],"label_agreement":null},{"id":"W7103204945","doi":"","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Open Philanthropy Project; National Science Foundation","keywords":"Preference; Diversity (politics); Preference elicitation; Preference learning; Work (physics)","score_opus":0.19604799976986428,"score_gpt":0.3504283725767246,"score_spread":0.15438037280686032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103204945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88353044,0.0029278114,0.10284851,0.0015766617,0.0026511806,0.0006772112,0.000011200343,0.00013515256,0.0056418376],"genre_scores_gemma":[0.9896781,0.0010564124,0.0012573029,0.00027721626,0.00009247468,0.000040043382,0.000032492815,0.000028825598,0.0075371633],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994331,0.00062689144,0.0016346924,0.0018018476,0.0004838534,0.0011217312],"domain_scores_gemma":[0.9947648,0.0004147591,0.0005030219,0.0036726175,0.0004625275,0.00018228144],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0018736852,0.000495224,0.0007444617,0.0007585824,0.00060796714,0.0009915299,0.0061183427,0.00028486652,0.00034902175],"category_scores_gemma":[0.0010673963,0.00057484367,0.00013377544,0.0031322401,0.00056736596,0.008710913,0.0051127644,0.0012476898,0.00042904017],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114669514,0.0018315193,0.7426101,0.00071823254,0.00026707823,0.00008879056,0.025379024,0.006217018,0.058574,0.055719372,0.0021131556,0.10636702],"study_design_scores_gemma":[0.0012634285,0.0011196573,0.32016113,0.012471907,0.0002678934,0.000015462892,0.029831639,0.4333792,0.15620463,0.016703743,0.02625817,0.002323129],"about_ca_topic_score_codex":0.0020317738,"about_ca_topic_score_gemma":0.0019647444,"teacher_disagreement_score":0.4271622,"about_ca_system_score_codex":0.00029544203,"about_ca_system_score_gemma":0.00064631854,"threshold_uncertainty_score":0.9996703},"labels":[],"label_agreement":null},{"id":"W7104260442","doi":"10.23977/acss.2025.090315","title":"Comparison of Explainability and Scalability of Causal AI and LLMs in AGI","year":2025,"lang":"","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Path (computing); Causal inference; Key (lock); Task (project management); Casual; Scalability; Causal model; Natural language","score_opus":0.02916042801773007,"score_gpt":0.3621837162568269,"score_spread":0.3330232882390968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104260442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60265404,0.048499182,0.34684163,0.00022181863,0.00085356005,0.0008079978,0.000009005632,0.000013218875,0.00009952386],"genre_scores_gemma":[0.9958825,0.001498182,0.0024589705,0.0000555095,0.000044919354,0.000036576967,8.692001e-7,0.000008839134,0.000013614121],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944444,0.0009569304,0.0024016488,0.0012315951,0.00039873854,0.0005666891],"domain_scores_gemma":[0.9965979,0.0015434198,0.00056531763,0.0007571514,0.00038926429,0.00014696427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028333717,0.0004164451,0.0016544843,0.000477964,0.00012663497,0.00021215656,0.00058428175,0.00022652192,0.000003020169],"category_scores_gemma":[0.00016088448,0.00041380295,0.00006709627,0.0011822872,0.0010469565,0.0013424272,0.0008676832,0.0003933447,4.3590705e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012168853,0.000688121,0.685038,0.004752351,0.00003234944,0.000019160885,0.008301348,0.02985011,0.0006355307,0.0267523,0.000018816834,0.24379024],"study_design_scores_gemma":[0.00056984904,0.000692024,0.040498376,0.0023408602,0.000015353655,0.000011236819,0.001324382,0.93618256,0.004966894,0.012774364,0.00025337507,0.00037070038],"about_ca_topic_score_codex":0.0015175422,"about_ca_topic_score_gemma":0.0008503739,"teacher_disagreement_score":0.9063325,"about_ca_system_score_codex":0.0000972653,"about_ca_system_score_gemma":0.00015835672,"threshold_uncertainty_score":0.9998314},"labels":[],"label_agreement":null},{"id":"W7108248275","doi":"","title":"CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Counterfactual thinking; Counterfactual conditional; Causal reasoning; Causal inference; Causal model; Inference; Natural language understanding; Philosophy of language; Natural language; Causation","score_opus":0.05426226973516782,"score_gpt":0.2104052852759768,"score_spread":0.15614301554080898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108248275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35416988,0.00011038732,0.63492036,0.00039165752,0.00076795,0.0004224699,0.0000044322833,0.00017515777,0.009037701],"genre_scores_gemma":[0.97794574,0.00023116698,0.0017529031,0.00044330198,0.00007003913,0.0000022538425,0.000006859559,0.000026438523,0.019521268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622434,0.00036416043,0.00046074128,0.001702433,0.00023727836,0.0010110699],"domain_scores_gemma":[0.9972808,0.00023655132,0.00033953166,0.0013084708,0.00050284265,0.00033179967],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056796224,0.00051824865,0.00042054846,0.0006084715,0.0010286997,0.00051557506,0.0012324244,0.00021357142,0.00021342834],"category_scores_gemma":[0.0000951305,0.00059318077,0.00016536929,0.0039209984,0.00041192482,0.002047,0.00072972826,0.00046102802,0.0005557029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038696147,0.00037018114,0.009708243,0.000100644895,0.0003088432,0.002782212,0.0021212017,0.23079136,0.00075396517,0.7455817,0.0007887009,0.0063059847],"study_design_scores_gemma":[0.0011052305,0.0005641479,0.0029375523,0.0005856856,0.0003327458,0.000031110998,0.0029357655,0.9544689,0.018925268,0.014852197,0.0022826244,0.0009787842],"about_ca_topic_score_codex":0.0011443462,"about_ca_topic_score_gemma":0.00087201444,"teacher_disagreement_score":0.7307295,"about_ca_system_score_codex":0.000807556,"about_ca_system_score_gemma":0.0007092791,"threshold_uncertainty_score":0.99965197},"labels":[],"label_agreement":null},{"id":"W7111079672","doi":"10.48550/arxiv.2512.05998","title":"Going All-In on LLM Accuracy: Fake Prediction Markets, Real Confidence Signals","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Incentive; Framing (construction); Baseline (sea); Binary number; Scoring rule; Framing effect; Confidence interval; Task (project management)","score_opus":0.14548078773014814,"score_gpt":0.24929959811847222,"score_spread":0.10381881038832408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111079672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35298446,0.00015779628,0.5830487,0.00068602356,0.003941125,0.002398181,0.000149086,0.00060941046,0.0560252],"genre_scores_gemma":[0.9824389,0.005154638,0.00048656683,0.00046584383,0.00018921593,0.000009624501,0.00002980345,0.00003730658,0.011188084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99092203,0.0013769162,0.0013269975,0.00422517,0.00050661137,0.0016422563],"domain_scores_gemma":[0.991775,0.0027922816,0.0010373802,0.0031892357,0.0006737008,0.00053244503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024090356,0.0011195134,0.0010852861,0.001546074,0.0006202819,0.00066161645,0.0051869503,0.0010171033,0.00039720588],"category_scores_gemma":[0.0008714496,0.0014902131,0.000552651,0.0031546513,0.00048424993,0.0020782757,0.003516137,0.0022563853,0.0008938472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006179247,0.0007368929,0.0049157063,0.00030822825,0.00022306801,0.0018860966,0.0017158731,0.5925948,0.00048761434,0.38937506,0.0006793624,0.006459399],"study_design_scores_gemma":[0.00055582495,0.0004176354,0.004273589,0.0022814642,0.00015757742,0.00000957529,0.00078695343,0.931662,0.005719052,0.050028615,0.0028749655,0.0012327178],"about_ca_topic_score_codex":0.0024299703,"about_ca_topic_score_gemma":0.00095287105,"teacher_disagreement_score":0.62945443,"about_ca_system_score_codex":0.0018631772,"about_ca_system_score_gemma":0.0014987367,"threshold_uncertainty_score":0.99988407},"labels":[],"label_agreement":null},{"id":"W7112916737","doi":"","title":"Can we interpret gender? Using contrastive explanations to understand gender choices by translation systems","year":2025,"lang":"en","type":"article","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Sentence; Focus (optics); Context (archaeology); Affect (linguistics); Perception; Vocabulary; Interpretation (philosophy); Relevance (law)","score_opus":0.06492066547279625,"score_gpt":0.27015414248254593,"score_spread":0.2052334770097497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7112916737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025099453,0.0009625628,0.96057475,0.0018344516,0.00066210027,0.0008132057,0.00018068787,0.00034143892,0.009531348],"genre_scores_gemma":[0.99357724,0.0033577846,0.0018943199,0.00034130807,0.00003569295,6.242709e-7,0.000027322656,0.000015207106,0.0007505071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99710155,0.00034636352,0.000333998,0.00095622,0.0005549426,0.0007069405],"domain_scores_gemma":[0.9983159,0.00030554045,0.00017739326,0.0004929776,0.00031230345,0.00039591742],"candidate_categories":["metaepi_narrow","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.00031461267,0.0003736691,0.0003625909,0.023049807,0.00086315605,0.00021711212,0.0019531054,0.00036412207,0.000021037113],"category_scores_gemma":[0.000012886839,0.00048412624,0.00026175784,0.031695645,0.00021822493,0.0019767815,0.00041304418,0.00060467265,0.000011368225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041301383,0.00037604207,0.01829944,0.00025517124,0.0013889687,0.00022354248,0.016794153,0.01700815,0.011936138,0.89284503,0.038128845,0.0023314871],"study_design_scores_gemma":[0.0059952256,0.00060227,0.004928973,0.0016725939,0.0017625239,0.000039625596,0.23403625,0.2155913,0.009259328,0.0284128,0.49270964,0.00498948],"about_ca_topic_score_codex":0.0010791993,"about_ca_topic_score_gemma":0.00012304269,"teacher_disagreement_score":0.9684778,"about_ca_system_score_codex":0.00061830133,"about_ca_system_score_gemma":0.00021706684,"threshold_uncertainty_score":0.99976104},"labels":[],"label_agreement":null},{"id":"W7113200082","doi":"","title":"Hallucinations in Large Foundation Models: Characterization, Quantification, Detection, Avoidance, and Mitigation","year":2025,"lang":"en","type":"article","venue":"Scholar Commons (University of South Carolina)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Deception; Generative grammar; Foundation (evidence); Unintended consequences; Scope (computer science); Argument (complex analysis); Perception; Salient","score_opus":0.015952432433731952,"score_gpt":0.22503820833752086,"score_spread":0.2090857759037889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7113200082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38841683,0.000034653927,0.6094587,0.0012593122,0.00008836179,0.00016978676,0.000010339856,0.000057934754,0.0005041144],"genre_scores_gemma":[0.99491364,0.000039153714,0.0046230624,0.000050559705,0.0000076014403,0.0000022703211,0.00003847265,0.000004927637,0.0003203286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888146,0.00017774987,0.00020766104,0.00036218448,0.00018132765,0.00018961483],"domain_scores_gemma":[0.9987642,0.00005926345,0.00017317923,0.00045489683,0.0004957775,0.00005265254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006925628,0.000106985455,0.0001625792,0.0006601147,0.0007032156,0.00010316265,0.00048146787,0.00010287803,0.00000633583],"category_scores_gemma":[0.00012173537,0.00015265518,0.000043300188,0.0015284896,0.00009621493,0.0023327207,0.00018567889,0.00024813373,0.000019612127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046199202,0.0002675231,0.056643926,0.00012199796,0.000048908518,0.000008005663,0.021718511,0.0026109498,0.023010494,0.86594087,0.000037821283,0.029544786],"study_design_scores_gemma":[0.0007160686,0.000047600915,0.3672117,0.00013108744,0.00003199717,0.0000031511722,0.005311508,0.5788528,0.0059150266,0.038236056,0.003223417,0.0003196435],"about_ca_topic_score_codex":0.00013375482,"about_ca_topic_score_gemma":0.0014801954,"teacher_disagreement_score":0.82770485,"about_ca_system_score_codex":0.000104015744,"about_ca_system_score_gemma":0.00010898463,"threshold_uncertainty_score":0.6225097},"labels":[],"label_agreement":null},{"id":"W7115365349","doi":"","title":"Explainable and efficient randomized voting rules","year":2023,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voting; Anti-plurality voting; Bullet voting; Key (lock); Distortion (music); Focus (optics)","score_opus":0.09089123467282531,"score_gpt":0.3162720293881617,"score_spread":0.22538079471533637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115365349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77815884,0.0006710758,0.19809192,0.00840573,0.0012815302,0.0017518145,0.000011278121,0.00095205236,0.010675747],"genre_scores_gemma":[0.9874696,0.0007835101,0.006362847,0.00003136662,0.00027032322,0.000017925327,0.000010868527,0.000025059482,0.0050284644],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950313,0.00045310808,0.00041432015,0.0010045425,0.0017067671,0.0013899768],"domain_scores_gemma":[0.9944556,0.0030700327,0.00018575047,0.00083991396,0.00097225455,0.00047648657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009857606,0.00028055496,0.00072895223,0.0017712932,0.0012514753,0.00022697846,0.0019878247,0.00017724244,0.0007043292],"category_scores_gemma":[0.0019125611,0.00030170704,0.00024106362,0.0032976642,0.0013625349,0.0012104632,0.0024752605,0.00060583436,0.0001240513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0086198915,0.00081854424,0.000889786,0.00023567036,0.0005640287,0.0021699334,0.16413675,0.009743155,0.012542232,0.3427373,0.3978975,0.059645213],"study_design_scores_gemma":[0.015683804,0.00033832548,0.00015966983,0.0003282332,0.00003886068,0.000021097987,0.061835054,0.84070134,0.0058770464,0.055028208,0.019169712,0.00081862125],"about_ca_topic_score_codex":0.00060420536,"about_ca_topic_score_gemma":0.000015747026,"teacher_disagreement_score":0.8309582,"about_ca_system_score_codex":0.00015884708,"about_ca_system_score_gemma":0.00022592903,"threshold_uncertainty_score":0.9999435},"labels":[],"label_agreement":null},{"id":"W7115600894","doi":"10.1109/icidca66325.2025.11280392","title":"Explainable Transform Learning for Interpretable Medical Image Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Interpretability; Deep learning; Workflow; Feature learning; Convolutional neural network; Medical imaging; Representation (politics); Feature engineering; Trustworthiness","score_opus":0.013096046617412321,"score_gpt":0.31308655648431316,"score_spread":0.29999050986690085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115600894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009519643,0.000708484,0.86605537,0.011525921,0.0010405157,0.0010295953,0.000004619211,0.00033753883,0.11834597],"genre_scores_gemma":[0.86480093,0.00044674822,0.029874912,0.0018362837,0.00013919408,0.00034996873,0.00001891752,0.000040112704,0.10249296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99296975,0.00033461794,0.0017272348,0.0018332787,0.0011381827,0.0019969596],"domain_scores_gemma":[0.9953726,0.0015189222,0.0002447314,0.0013225079,0.00094594056,0.0005953007],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040107826,0.00066297257,0.0012646908,0.0016881037,0.0013909098,0.0015845392,0.0033893895,0.00054759707,0.0048107873],"category_scores_gemma":[0.002073024,0.0006638128,0.001262914,0.008019843,0.00043207264,0.002457735,0.00075970497,0.00094731216,0.000322822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031247546,0.0008750207,0.00088297453,0.00073600205,0.0038775115,0.00013019517,0.007328951,0.01300442,0.0009855366,0.5084245,0.00922735,0.45421505],"study_design_scores_gemma":[0.00037825658,0.0003297078,0.000032110303,0.00019146406,0.0008375076,0.0000044593876,0.0028227083,0.8902169,0.038078062,0.015104898,0.051400915,0.00060303754],"about_ca_topic_score_codex":0.001196691,"about_ca_topic_score_gemma":0.0012233484,"teacher_disagreement_score":0.87721246,"about_ca_system_score_codex":0.0004101715,"about_ca_system_score_gemma":0.0013888517,"threshold_uncertainty_score":0.99990916},"labels":[],"label_agreement":null},{"id":"W7116210972","doi":"","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering; International Max Planck Research School for Environmental, Cellular and Molecular Microbiology; McGill University","keywords":"Interpretability; Disjoint sets; Independence (probability theory); Linear subspace; Affect (linguistics); Feature (linguistics); Isolation (microbiology)","score_opus":0.06445692341868224,"score_gpt":0.2979039952585593,"score_spread":0.23344707183987706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116210972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3020915,0.00044393344,0.6919024,0.00066979224,0.001478708,0.0006509634,0.000035238307,0.00010499591,0.0026224658],"genre_scores_gemma":[0.98105043,0.0001283977,0.01508114,0.00060311356,0.00010270593,0.0000034353275,0.000008606678,0.000019084357,0.0030031044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949454,0.001165739,0.00069111475,0.0022686548,0.00016936842,0.0007597284],"domain_scores_gemma":[0.9962489,0.00090747274,0.00028012547,0.001708292,0.0003878527,0.00046732655],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011572236,0.00050485315,0.00057488855,0.0004914764,0.00058993255,0.00078360154,0.00182123,0.00024309495,0.0009695581],"category_scores_gemma":[0.00038200818,0.00063249434,0.00024293465,0.0020858522,0.00046747728,0.0021062666,0.0025084594,0.00039818947,0.00027301113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007254488,0.0009728313,0.08203181,0.00019375053,0.00069416274,0.00026444442,0.037216935,0.009648282,0.008869007,0.6768087,0.0023804319,0.18019418],"study_design_scores_gemma":[0.00071205996,0.0003032913,0.0052906377,0.00042869576,0.000353382,0.0000017733097,0.0076942495,0.65864104,0.019792266,0.29472747,0.01109367,0.000961469],"about_ca_topic_score_codex":0.0019294356,"about_ca_topic_score_gemma":0.000439556,"teacher_disagreement_score":0.6789589,"about_ca_system_score_codex":0.0007130648,"about_ca_system_score_gemma":0.00020632076,"threshold_uncertainty_score":0.9999437},"labels":[],"label_agreement":null},{"id":"W7116441454","doi":"10.1109/tai.2025.3646194","title":"Harnessing Teacher’s Explanation for Improved Knowledge Distillation","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Distillation; Variety (cybernetics); Class (philosophy); Work (physics); Training set","score_opus":0.06975399240409494,"score_gpt":0.34683743239050235,"score_spread":0.2770834399864074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116441454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014215589,0.0004696583,0.97676355,0.004087993,0.011511638,0.0025208308,0.0000922653,0.00047029823,0.002662213],"genre_scores_gemma":[0.9827852,0.00022409634,0.0096269315,0.00038545817,0.0004032006,0.00055719464,0.000014454301,0.00007731997,0.005926132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99343044,0.00043917325,0.00226452,0.002079016,0.00039892155,0.0013879099],"domain_scores_gemma":[0.9948998,0.001392068,0.00053592346,0.0015383867,0.0012993912,0.0003344198],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016684403,0.0009105987,0.00078226614,0.0013984506,0.0024842662,0.0015194224,0.0017004983,0.0006461013,0.000279541],"category_scores_gemma":[0.0002916284,0.0010555376,0.0006470048,0.0033910698,0.0005407283,0.0017614978,0.000021069509,0.0009807762,0.0006769831],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042784726,0.0014635922,0.0000015614105,0.0001659968,0.0001279428,0.0000023846649,0.0027825905,0.041804418,0.011230091,0.06949204,0.00029254757,0.872209],"study_design_scores_gemma":[0.0000671581,0.0003104851,0.0000061221017,0.00032198164,0.00011534067,0.000002736285,0.0008987319,0.58677614,0.37371927,0.034256276,0.0029449558,0.00058079796],"about_ca_topic_score_codex":0.0002895116,"about_ca_topic_score_gemma":0.0013965181,"teacher_disagreement_score":0.98136365,"about_ca_system_score_codex":0.0009861212,"about_ca_system_score_gemma":0.0010012416,"threshold_uncertainty_score":0.9995171},"labels":[],"label_agreement":null},{"id":"W7117130738","doi":"10.1145/3756681.3756981","title":"From Questions to Insights: Exploring XAI Challenges Reported on Stack Overflow Questions","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Consistency (knowledge bases); Interpretability; Usability; Metadata; Exploratory analysis; Face (sociological concept)","score_opus":0.15436798477557145,"score_gpt":0.3395053042173989,"score_spread":0.18513731944182743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117130738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08330562,0.005567649,0.756651,0.05391993,0.011343337,0.0018451378,0.000039541497,0.0015557172,0.085772075],"genre_scores_gemma":[0.9585473,0.0058072954,0.02128891,0.0027811648,0.000774941,0.0006008892,0.000013103384,0.000063385014,0.010122999],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99292505,0.0005250946,0.0017792028,0.0025892763,0.0009679699,0.0012134112],"domain_scores_gemma":[0.9929058,0.0011458382,0.0003237814,0.0039448575,0.0009873107,0.00069242454],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075251824,0.00079389074,0.00077004835,0.0012263354,0.0011723894,0.0010923308,0.002050447,0.0003476035,0.0004344179],"category_scores_gemma":[0.0021478646,0.0008309738,0.00027865902,0.0030396068,0.00020531754,0.0024981257,0.001216277,0.0008352333,0.0024343194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064258646,0.0009871604,0.00006722376,0.000047282218,0.0002424705,0.00024899672,0.014259628,0.008368164,0.0014595992,0.83306646,0.0038996132,0.13728917],"study_design_scores_gemma":[0.0007023954,0.002178276,0.008568535,0.006872252,0.0003380337,0.000017986218,0.019128636,0.19650929,0.16451782,0.32019576,0.27738205,0.0035889978],"about_ca_topic_score_codex":0.0055061164,"about_ca_topic_score_gemma":0.0038213518,"teacher_disagreement_score":0.8752417,"about_ca_system_score_codex":0.0007731247,"about_ca_system_score_gemma":0.0008851385,"threshold_uncertainty_score":0.9999446},"labels":[],"label_agreement":null},{"id":"W7117137071","doi":"10.2139/ssrn.5964045","title":"Explainable AI: XVARS Outperforms SHAP in Terms of Computational Speed and Sampling Robustness","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Robustness (evolution); Computation; Sampling (signal processing); Feature (linguistics); Sensitivity (control systems); Sample size determination; Explanatory power","score_opus":0.030080681289824232,"score_gpt":0.3037943334211514,"score_spread":0.2737136521313272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117137071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2049295,0.0017968826,0.78856313,0.0019561807,0.001020874,0.00077703997,0.000014087236,0.00004283799,0.00089949183],"genre_scores_gemma":[0.9822033,0.0055233724,0.010400698,0.00020603239,0.0002774287,0.000020865298,0.000018915161,0.000047251764,0.001302127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9887358,0.0004395603,0.0026737086,0.0015504241,0.0012194483,0.005381081],"domain_scores_gemma":[0.9961142,0.0005470802,0.0013756101,0.00087024627,0.0007832321,0.00030965733],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007848612,0.000926026,0.0014396786,0.0016458855,0.0007630516,0.00083844044,0.0029871021,0.0006224521,0.00006632133],"category_scores_gemma":[0.00037293407,0.00095517054,0.00040690292,0.0015506463,0.00044183055,0.0016211318,0.0020644919,0.008423271,0.000013882767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001687832,0.0003057716,0.004110759,0.0002893649,0.00024030775,0.000030806583,0.0020539428,0.6905473,0.00013518188,0.23049745,0.0000118561475,0.07160852],"study_design_scores_gemma":[0.0005645512,0.0003536414,0.00086771173,0.0008363196,0.000048783542,0.00041716397,0.0022708338,0.48461893,0.00044154562,0.5088802,0.000073806856,0.0006264945],"about_ca_topic_score_codex":0.00077414786,"about_ca_topic_score_gemma":0.0015704182,"teacher_disagreement_score":0.7781624,"about_ca_system_score_codex":0.0034235965,"about_ca_system_score_gemma":0.010254755,"threshold_uncertainty_score":0.9992899},"labels":[],"label_agreement":null},{"id":"W7117471227","doi":"10.1007/s44248-025-00096-6","title":"Interpretability taxonomy: an approach for artificial intelligence developers technique selection","year":2025,"lang":"en","type":"article","venue":"Discover Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Interpretability; Operationalization; CLARITY; Taxonomy (biology); Categorization; Selection (genetic algorithm); Construct (python library)","score_opus":0.14090403599969797,"score_gpt":0.3543921964187081,"score_spread":0.21348816041901014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117471227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006867464,0.000027941687,0.99484974,0.0003442229,0.00031788755,0.001516034,0.00009491338,0.00023466973,0.0019278444],"genre_scores_gemma":[0.5526999,0.0000047049443,0.44580963,0.00028327797,0.00006139006,0.0007434413,0.00027680895,0.000012064181,0.00010874078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745554,0.00013480325,0.00050734676,0.0012772536,0.00018484525,0.0004402304],"domain_scores_gemma":[0.9971895,0.00015509462,0.00010163933,0.0022864935,0.00018132306,0.00008595455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013774362,0.00022788036,0.00023624962,0.00020153257,0.00028869652,0.000548626,0.0039144685,0.00011988575,0.0000145072545],"category_scores_gemma":[0.00048559313,0.00022248067,0.000059276266,0.0010407643,0.00013829766,0.0033436494,0.001320468,0.00021624935,0.00001698738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109567176,0.0006327768,0.0010216984,0.00012044472,0.000060462145,0.0000015626848,0.00057740504,0.0017057776,0.003882712,0.6292914,0.0017492226,0.36084697],"study_design_scores_gemma":[0.000028145601,0.00008893469,0.000092133414,0.000030623647,0.00001809444,0.0000040106424,0.0006693789,0.8129867,0.123963654,0.051709075,0.010039324,0.00036993553],"about_ca_topic_score_codex":0.00029923068,"about_ca_topic_score_gemma":0.00025096405,"teacher_disagreement_score":0.8112809,"about_ca_system_score_codex":0.00019019932,"about_ca_system_score_gemma":0.00056002726,"threshold_uncertainty_score":0.9072498},"labels":[],"label_agreement":null},{"id":"W7117476511","doi":"10.2139/ssrn.5835882","title":"Cognitive Uncertainty across Humans and Large Language Models: Regard and Recall in Economic Decision Making","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cognition; Construct (python library); Recall; Normative; Representation (politics); Substitution (logic); Vulnerability (computing)","score_opus":0.02406011387766932,"score_gpt":0.33808270456981243,"score_spread":0.3140225906921431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117476511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53794914,0.012838881,0.44699165,0.00030657838,0.00056648167,0.00053998537,0.000051971903,0.00003388179,0.0007214204],"genre_scores_gemma":[0.9603085,0.03729274,0.0011458757,0.00022101897,0.00025074722,0.00003129162,0.000006291929,0.00003738878,0.0007061486],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990215,0.0006231712,0.0015242185,0.0018301182,0.0004582545,0.0053492486],"domain_scores_gemma":[0.9969544,0.0010215556,0.00079551607,0.00070855656,0.0002831062,0.0002369084],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0095654335,0.00076888676,0.0010038544,0.000603386,0.001042473,0.0014863843,0.0015901453,0.00060919416,0.00002689632],"category_scores_gemma":[0.00039996303,0.00082269596,0.00024198493,0.00039039817,0.0002871081,0.0013155927,0.0030057374,0.007542344,0.000023114197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065687485,0.00017821213,0.001399624,0.000100063924,0.00028922857,0.00015471183,0.027713139,0.02594018,0.000018746588,0.2691809,0.0000140668,0.67435426],"study_design_scores_gemma":[0.000825764,0.0002849991,0.00017132834,0.0020005596,0.000048022994,0.00032990007,0.025602773,0.3594935,0.00006495637,0.61044186,0.000104593164,0.00063173566],"about_ca_topic_score_codex":0.0011919136,"about_ca_topic_score_gemma":0.08541854,"teacher_disagreement_score":0.6737225,"about_ca_system_score_codex":0.0041291798,"about_ca_system_score_gemma":0.0052214633,"threshold_uncertainty_score":0.9996938},"labels":[],"label_agreement":null},{"id":"W7117729834","doi":"10.1186/s12874-025-02703-1","title":"Machine learning models explanations as interpretations of evidence: a theoretical framework of explainability and its implications on high-stakes biomedical decision-making","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"European Commission","keywords":"Operationalization; Terminology; Soundness; Interpretation (philosophy); Interpretability; Raising (metalworking)","score_opus":0.4858301340420024,"score_gpt":0.5662124117095355,"score_spread":0.08038227766753309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117729834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04846303,0.0008387243,0.9404163,0.009049136,0.00016522766,0.00041828337,0.0000071062905,0.000052648276,0.00058957445],"genre_scores_gemma":[0.7317074,0.00042054697,0.26754233,0.00015195232,0.000022824792,0.00012338077,0.0000020398406,0.000006981054,0.000022540824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9870662,0.008970654,0.0010052249,0.0007684891,0.0016067524,0.0005826573],"domain_scores_gemma":[0.6945377,0.30244738,0.00019885116,0.0010135912,0.0013807189,0.0004217743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023198903,0.00016599263,0.00055269833,0.001060914,0.00036958922,0.000049989274,0.0017327173,0.00039844352,0.00035228924],"category_scores_gemma":[0.4507954,0.00012701312,0.00010509005,0.0022237727,0.0020735785,0.00031947307,0.0010860423,0.0013190936,0.000013633746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015435115,0.00018365162,0.00033778115,0.000118191696,0.000023902176,0.0000062289328,0.001796502,0.00065402477,0.0003957548,0.89374006,0.00003828951,0.10255124],"study_design_scores_gemma":[0.0000784679,0.00037924448,0.00043182363,0.0009786666,0.000007962699,0.000008254433,0.0007406287,0.27346864,0.0017226476,0.72206026,0.000052560332,0.000070819646],"about_ca_topic_score_codex":0.0001669313,"about_ca_topic_score_gemma":0.00009066329,"teacher_disagreement_score":0.68324435,"about_ca_system_score_codex":0.00011350292,"about_ca_system_score_gemma":0.0016634752,"threshold_uncertainty_score":0.80403227},"labels":[],"label_agreement":null},{"id":"W7117764744","doi":"10.3390/make8010006","title":"Research Frontiers in Machine Learning &amp; Knowledge Extraction","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Eusko Jaurlaritza; Austrian Science Fund","keywords":"Transparency (behavior); Underpinning; Software deployment; Cornerstone; Applications of artificial intelligence; Embedding; Domain (mathematical analysis); Knowledge integration","score_opus":0.04255175253055986,"score_gpt":0.3903736406979469,"score_spread":0.347821888167387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117764744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08758308,0.0252614,0.7846895,0.0017649217,0.003668907,0.0006568379,0.000001470339,0.0008897218,0.09548416],"genre_scores_gemma":[0.9440549,0.0012692849,0.0068110772,0.00002045032,0.00020035943,0.00006657924,0.000022637152,0.000034129745,0.047520578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956366,0.0016956226,0.0005840836,0.0009748755,0.0003247091,0.00078409794],"domain_scores_gemma":[0.99796206,0.00093946775,0.00016164318,0.0004051254,0.00036939868,0.00016230118],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0043021655,0.0003236172,0.00038179875,0.0018211477,0.0012460453,0.00047706792,0.0005140417,0.00027688695,0.000056946225],"category_scores_gemma":[0.001302569,0.00034170615,0.000094818985,0.0026899201,0.0001462243,0.0011137272,0.00039593433,0.0031404207,0.00038148812],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001724195,0.00074392295,0.09421573,0.00023055107,0.000055293196,0.000034227658,0.0060227104,0.0035230923,0.00988131,0.013370038,0.0028378074,0.8689129],"study_design_scores_gemma":[0.00039487233,0.00015426864,0.0061809826,0.00019786617,0.0000128267775,0.000030913194,0.00095370575,0.5254339,0.0023949211,0.0035468969,0.46034122,0.00035764044],"about_ca_topic_score_codex":0.0013454913,"about_ca_topic_score_gemma":0.003050554,"teacher_disagreement_score":0.86855525,"about_ca_system_score_codex":0.00044234254,"about_ca_system_score_gemma":0.0002125682,"threshold_uncertainty_score":0.9999035},"labels":[],"label_agreement":null},{"id":"W7118990336","doi":"10.23977/jaip.2025.080406","title":"A Four-Layer Security Governance Framework for LLM-Based AI Agents","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Corporate governance; Trustworthiness; Computer security model; Security information and event management; Phase (matter); Security domain; Process (computing); Information governance","score_opus":0.09132488724048299,"score_gpt":0.4042829723256977,"score_spread":0.3129580850852147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118990336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016547473,0.0028159136,0.8962426,0.08263525,0.01338398,0.0014519558,0.000041813277,0.00007589687,0.0016978044],"genre_scores_gemma":[0.77008617,0.0013025235,0.20935455,0.01687307,0.001827229,0.00006547385,0.0000017429123,0.00008641375,0.0004028195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9871398,0.0014596537,0.005358282,0.0015790955,0.002447862,0.00201528],"domain_scores_gemma":[0.9696145,0.013014865,0.0060698395,0.0020673897,0.0084731905,0.00076021755],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0096005155,0.0011131702,0.0016498169,0.0009012452,0.0013385761,0.0028797023,0.005245182,0.0009773074,0.00047971058],"category_scores_gemma":[0.04782487,0.0011679406,0.0014301707,0.004406812,0.0007301675,0.007394792,0.00069281773,0.0036785246,0.00043884382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003621709,0.0039120703,0.00005736707,0.0003628593,0.00058478874,0.0005484509,0.0039482075,0.021736728,0.00072610023,0.70469695,0.0071868887,0.2526179],"study_design_scores_gemma":[0.00014830266,0.001829091,0.000020546768,0.0015615015,0.00055257726,0.00012488957,0.0024227356,0.35853213,0.12249458,0.42192248,0.08959388,0.00079729996],"about_ca_topic_score_codex":0.00027329882,"about_ca_topic_score_gemma":0.00012975253,"teacher_disagreement_score":0.7684314,"about_ca_system_score_codex":0.001216779,"about_ca_system_score_gemma":0.0045334995,"threshold_uncertainty_score":0.99996156},"labels":[],"label_agreement":null},{"id":"W7125007218","doi":"10.1109/aiware69974.2025.00027","title":"Promptexp: Multi-Granularity Prompt Explanation of Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Manitoba; Huawei Technologies (Canada)","funders":"","keywords":"Interpretability; Natural language; Language model; Focus (optics); Natural language understanding; Feature (linguistics); Language understanding; Similarity (geometry); Denotation (semiotics)","score_opus":0.03785962162754133,"score_gpt":0.32965572577963026,"score_spread":0.29179610415208895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125007218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0411075,0.0011701564,0.93928945,0.0012337863,0.0008057767,0.0014594448,0.00003348669,0.00021243191,0.014687941],"genre_scores_gemma":[0.95161176,0.00006820864,0.039578795,0.00044702803,0.000041780793,0.000077002616,0.00001464744,0.000018719342,0.008142042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956559,0.0003304031,0.0012442466,0.001115697,0.0007095399,0.0009441929],"domain_scores_gemma":[0.99698484,0.00017882213,0.0003644643,0.0015357372,0.00076657516,0.00016953918],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016472088,0.00043532572,0.00060558255,0.0005947191,0.00036591626,0.00029495492,0.0018461188,0.00031162,0.00029095376],"category_scores_gemma":[0.00027559014,0.00043953475,0.00025493558,0.0019351016,0.0001784327,0.002018112,0.00089739234,0.00041631373,0.00014584966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006030201,0.0024937857,0.0006544293,0.0005989692,0.00012736215,0.000046646357,0.020783268,0.003623269,0.0119832475,0.9134192,0.0009804805,0.04522908],"study_design_scores_gemma":[0.00042210825,0.00010225785,0.00026427157,0.00021259036,0.000030338157,0.0000020975187,0.0021773586,0.7604967,0.22208954,0.013558534,0.00032402267,0.00032022412],"about_ca_topic_score_codex":0.0015588116,"about_ca_topic_score_gemma":0.0013491882,"teacher_disagreement_score":0.9105043,"about_ca_system_score_codex":0.00017089499,"about_ca_system_score_gemma":0.0005257948,"threshold_uncertainty_score":0.9998056},"labels":[],"label_agreement":null},{"id":"W7125191131","doi":"10.18280/mmep.121220","title":"A Fairness-Aware and Bias-Resilient XAI Framework for Equitable Financial Decision-Making","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Work (physics); Measure (data warehouse); Term (time); Payment; Order (exchange)","score_opus":0.04480043148878129,"score_gpt":0.29040803098714196,"score_spread":0.24560759949836067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125191131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011242855,0.003182693,0.9828578,0.00049310696,0.0008303486,0.0010435173,0.000008166488,0.00022501074,0.0001164559],"genre_scores_gemma":[0.6008717,0.00021553643,0.3984074,0.0000746563,0.00008549647,0.0001627139,7.085521e-7,0.000038154536,0.00014368605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959911,0.00003434898,0.0011288224,0.0011155504,0.00041380056,0.0013163966],"domain_scores_gemma":[0.99522716,0.003405189,0.00015235497,0.0007124309,0.00023698642,0.00026586867],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015437191,0.0005858129,0.00081209425,0.00037118117,0.0006608761,0.0011088937,0.00066128105,0.00045697682,0.000014076284],"category_scores_gemma":[0.0016891868,0.00057868456,0.00016498855,0.0008158837,0.00013548047,0.0005002556,0.00074802677,0.00058398355,0.000016223958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018440724,0.000084672145,0.0000051052175,0.002017197,0.000022816877,0.000004288659,0.0015084539,0.52208,0.000018741319,0.4481551,0.000034466048,0.026050683],"study_design_scores_gemma":[0.00009817932,0.00008351507,0.0000015212952,0.0055716923,0.00003772308,0.000006865597,0.00006875485,0.54085946,0.00016439156,0.4524766,0.0003186146,0.00031269953],"about_ca_topic_score_codex":0.00001499244,"about_ca_topic_score_gemma":0.0000023356504,"teacher_disagreement_score":0.5896288,"about_ca_system_score_codex":0.00010325244,"about_ca_system_score_gemma":0.00014780102,"threshold_uncertainty_score":0.99992806},"labels":[],"label_agreement":null},{"id":"W7125360948","doi":"","title":"Opportunities and Challenges for GORE in the era of Learning-based AI:iStar 2024 Panel Report","year":2024,"lang":"en","type":"article","venue":"University of Twente Research Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Panel discussion; Work (physics); Relation (database); International relations; Context (archaeology)","score_opus":0.22669684224444694,"score_gpt":0.3386537402608624,"score_spread":0.11195689801641548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125360948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1358054,0.003509627,0.6766717,0.1502395,0.0005262339,0.002658068,0.00006217451,0.00022045797,0.030306878],"genre_scores_gemma":[0.9966089,0.0016503956,0.0012065804,0.000029115266,0.000010347117,0.0000020122318,0.000020008776,0.0000024027654,0.00047021118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904275,0.00011779112,0.00017490261,0.000098536824,0.00039861634,0.00016742242],"domain_scores_gemma":[0.99894524,0.00039097565,0.00006454168,0.00019847817,0.00036761592,0.000033124532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024920788,0.00004826136,0.000082425446,0.00037192975,0.00013300798,0.000084102765,0.0004112661,0.00004013625,0.000008379544],"category_scores_gemma":[0.00021458216,0.000043642514,0.000036314737,0.00031144632,0.000171156,0.0015024145,0.00012588775,0.00025307338,0.000005107515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018491037,0.00011968218,0.00045032328,0.003644233,0.00005646136,0.00026756353,0.09846522,0.0055902735,0.000120430144,0.4695204,0.007392038,0.41418847],"study_design_scores_gemma":[0.00017977036,0.0004475694,0.0006854115,0.00032818585,0.0000058357396,0.000016017633,0.0792871,0.52503264,0.0010595111,0.0033247578,0.38952756,0.00010565725],"about_ca_topic_score_codex":0.00037063466,"about_ca_topic_score_gemma":0.0001030724,"teacher_disagreement_score":0.86080354,"about_ca_system_score_codex":0.000050494953,"about_ca_system_score_gemma":0.00022852045,"threshold_uncertainty_score":0.17796901},"labels":[],"label_agreement":null},{"id":"W7125585764","doi":"10.1109/cascon66301.2025.00090","title":"Kantian-Utilitarian XAI: Meta-Explained","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Regret; Artifact (error); Session (web analytics); Certification; Code (set theory); TRACE (psycholinguistics)","score_opus":0.06326643969978005,"score_gpt":0.312312165394461,"score_spread":0.24904572569468095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125585764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014109578,0.0045776884,0.7386826,0.02850811,0.004362225,0.0010067045,0.000011527477,0.0005435354,0.22089665],"genre_scores_gemma":[0.86706597,0.000234684,0.028383674,0.0059635835,0.00019207447,0.00011648818,0.0000051588086,0.000038898033,0.097999476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921028,0.0006633067,0.0018991043,0.0023691459,0.000962886,0.0020027442],"domain_scores_gemma":[0.9938449,0.0008820728,0.00029793565,0.0036567352,0.00080767577,0.0005106533],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002380186,0.0009904689,0.0014589417,0.0009253468,0.0012283267,0.001513205,0.0045674033,0.00048124464,0.006880177],"category_scores_gemma":[0.00083160517,0.00090457755,0.0011557038,0.004621786,0.0005682321,0.0022741074,0.0019654746,0.00077984086,0.0041992343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051672854,0.00047941253,0.00020116747,0.00011556847,0.0021441227,0.0001593452,0.0017533096,0.0004270026,0.00070769974,0.9240813,0.021139704,0.048739664],"study_design_scores_gemma":[0.00059524266,0.0005414355,0.00058817456,0.00018358744,0.0026890275,0.000029799925,0.002849207,0.48742324,0.12702821,0.14325765,0.23284699,0.001967438],"about_ca_topic_score_codex":0.002725801,"about_ca_topic_score_gemma":0.0016972983,"teacher_disagreement_score":0.865655,"about_ca_system_score_codex":0.00028034238,"about_ca_system_score_gemma":0.0011917996,"threshold_uncertainty_score":0.99952334},"labels":[],"label_agreement":null},{"id":"W7125638789","doi":"10.1109/cascon66301.2025.00102","title":"Appropriateness of Empathy in AI: A Signal-Cost Perspective","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perspective (graphical); Empathy; Perspective-taking; Qualitative research; Context (archaeology)","score_opus":0.026458128889779508,"score_gpt":0.31934671299122686,"score_spread":0.29288858410144736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125638789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034263477,0.0012060496,0.8626977,0.0048101107,0.0011118639,0.0014952463,0.000006826105,0.000093453215,0.09431524],"genre_scores_gemma":[0.9925299,0.00009164421,0.0032816434,0.0009049418,0.000045948163,0.0000822484,6.888613e-7,0.00001601776,0.003046931],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956566,0.00035281168,0.0012154352,0.0012930766,0.00055517897,0.00092688086],"domain_scores_gemma":[0.99676484,0.00030995312,0.00024737715,0.0012209845,0.0013089495,0.00014789574],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012651327,0.0004283093,0.00073785655,0.0010436589,0.00017935994,0.00030075724,0.0020674018,0.00027534898,0.00040800063],"category_scores_gemma":[0.00033722536,0.0004326804,0.00024048933,0.0051462585,0.00040706736,0.0011106706,0.000982369,0.000559157,0.00020915788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014183823,0.0011950836,0.0016508276,0.00014408698,0.00007739421,0.0000854733,0.045600366,0.006155718,0.0030355598,0.87729526,0.0002985622,0.064319834],"study_design_scores_gemma":[0.00051869714,0.00032218118,0.0016691459,0.0005157527,0.000033293327,0.0000048363645,0.06589554,0.4579847,0.33110988,0.14091925,0.00040040936,0.0006263227],"about_ca_topic_score_codex":0.0066559813,"about_ca_topic_score_gemma":0.0012929218,"teacher_disagreement_score":0.95826644,"about_ca_system_score_codex":0.00063261966,"about_ca_system_score_gemma":0.0013327656,"threshold_uncertainty_score":0.99995875},"labels":[],"label_agreement":null},{"id":"W7125649792","doi":"10.1109/cascon66301.2025.00097","title":"From Confidence to Care: Rule-Based Escalation for Trustworthy Clinical AI","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Trustworthiness; De-escalation; Component (thermodynamics); Audit; Perspective (graphical)","score_opus":0.048098796330586537,"score_gpt":0.39578534997387843,"score_spread":0.3476865536432919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125649792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0116302995,0.0004389839,0.94914705,0.025599832,0.0071240673,0.0023271015,0.00004873732,0.0002465285,0.0034374285],"genre_scores_gemma":[0.85970265,0.000025179466,0.11494219,0.022122305,0.0007675476,0.0002353044,0.000029390258,0.000027842969,0.002147613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993841,0.00041766817,0.0020277512,0.0020828387,0.0006082438,0.0010224822],"domain_scores_gemma":[0.9922836,0.0033134099,0.00028352838,0.00196794,0.0016385842,0.00051293743],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015747491,0.0005065199,0.0007791441,0.00037833903,0.0006537186,0.0011403942,0.0023050718,0.0004878067,0.00040203382],"category_scores_gemma":[0.0018750248,0.0005417716,0.00052937254,0.0017997539,0.00027957128,0.0008865479,0.0005384374,0.00048440634,0.00087701285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005700654,0.00042075725,0.0056096623,0.000114159724,0.00010072585,0.000015997022,0.0025214776,0.01251498,0.0004941188,0.2665647,0.018575657,0.6924977],"study_design_scores_gemma":[0.00083348266,0.00077512005,0.0022635357,0.00046474696,0.00011501019,2.982303e-7,0.0011497219,0.8180461,0.07543452,0.05404931,0.04608483,0.00078334357],"about_ca_topic_score_codex":0.0023202612,"about_ca_topic_score_gemma":0.0011164454,"teacher_disagreement_score":0.84807235,"about_ca_system_score_codex":0.00030205454,"about_ca_system_score_gemma":0.0018404211,"threshold_uncertainty_score":0.99990094},"labels":[],"label_agreement":null},{"id":"W7125811146","doi":"10.21428/594757db.f2451ce9","title":"Faithful Perturbations and Evaluations for Post-Hoc Local Explanation Methods","year":2025,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Fidelity; Noise (video); Perturbation (astronomy); Quality (philosophy); Distribution (mathematics); Worry","score_opus":0.03886993933859015,"score_gpt":0.4173731409240598,"score_spread":0.3785032015854697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125811146","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001165939,0.00017833566,0.9804355,0.010767709,0.0002611571,0.00041343883,0.0000031020518,0.0001366311,0.006638175],"genre_scores_gemma":[0.1757975,0.000017713844,0.8173023,0.001891945,0.000027168577,0.0002200192,0.000012164751,0.0000058573323,0.0047253286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903274,0.00011312117,0.00022706689,0.0003162896,0.00012549518,0.00018531368],"domain_scores_gemma":[0.9982474,0.00087846507,0.000039286566,0.00031225773,0.0004711423,0.000051454055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007913791,0.00009069167,0.00010076819,0.00021664999,0.00031459905,0.000188216,0.0003224182,0.000055473713,0.0000314256],"category_scores_gemma":[0.00053660176,0.00008341971,0.00004096306,0.00048039388,0.00005590635,0.0006049325,0.000111008114,0.00005491726,0.000015549876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003982217,0.000018894643,0.000009842166,0.0000062505273,0.0000081533135,1.4223501e-7,0.0004940331,0.00027752513,0.0011728454,0.6302369,0.0011376918,0.36663368],"study_design_scores_gemma":[0.00011959957,0.00011862122,0.00038750868,0.000010501266,0.000014860793,0.000002048986,0.0017752507,0.82312757,0.024206951,0.13780174,0.012312837,0.00012250371],"about_ca_topic_score_codex":0.00007202955,"about_ca_topic_score_gemma":0.0001681998,"teacher_disagreement_score":0.82285005,"about_ca_system_score_codex":0.00006500743,"about_ca_system_score_gemma":0.00015337022,"threshold_uncertainty_score":0.34017572},"labels":[],"label_agreement":null},{"id":"W7125908856","doi":"10.1109/ase63991.2025.00067","title":"Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Observability; Debugging; Transparency (behavior); Software; Benchmark (surveying); Semantic reasoner; Autonomous agent; Cognition; Model-based reasoning; Class (philosophy)","score_opus":0.07947094746768106,"score_gpt":0.3715199134609973,"score_spread":0.2920489659933162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125908856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023535142,0.0016221553,0.95793146,0.0058983318,0.002574629,0.0026147477,0.000032780124,0.00009896921,0.005691812],"genre_scores_gemma":[0.9340875,0.00019855834,0.060867243,0.001965455,0.000112691356,0.0002297953,0.0000026983964,0.00001982406,0.0025161982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99544334,0.0003840267,0.0012667247,0.0012658121,0.0005957458,0.0010443744],"domain_scores_gemma":[0.9864041,0.009425479,0.0004789244,0.0018351368,0.0016847447,0.00017161036],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025544767,0.00046282855,0.0006670976,0.00014136016,0.0009630133,0.0004737061,0.0026199368,0.0003630746,0.00051768374],"category_scores_gemma":[0.009150789,0.00035654905,0.0005182738,0.0022408254,0.00075662264,0.0006887201,0.0011983401,0.0005668688,0.00007194756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035752222,0.00077103387,0.0033135873,0.00028031308,0.0003453745,0.0000061978644,0.006839274,0.00030672055,0.00011325591,0.8360815,0.000995971,0.15058924],"study_design_scores_gemma":[0.00045025226,0.00068800093,0.0076286774,0.0019252469,0.00028031442,0.0000023630093,0.010975701,0.5351083,0.08052657,0.35802847,0.0037996348,0.00058647303],"about_ca_topic_score_codex":0.0008056013,"about_ca_topic_score_gemma":0.00019033127,"teacher_disagreement_score":0.9105524,"about_ca_system_score_codex":0.00017112156,"about_ca_system_score_gemma":0.0007000282,"threshold_uncertainty_score":0.99988866},"labels":[],"label_agreement":null},{"id":"W7125916013","doi":"10.53106/256299802025120701004","title":"Agentic AI: Evaluating Value Creation Stories of Individual Companies From a Stakeholder Primacy Perspective","year":2025,"lang":"","type":"article","venue":"International Journal of Computer Auditing","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Sustainability; Stakeholder; Perspective (graphical); Value creation; Value (mathematics); Stakeholder theory; Stakeholder analysis; Corporate sustainability","score_opus":0.08257688692908068,"score_gpt":0.3867605592990914,"score_spread":0.30418367237001076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125916013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30233592,0.0014084042,0.68449414,0.0032786757,0.007499984,0.0002396612,0.000042543794,0.00002935944,0.000671302],"genre_scores_gemma":[0.9259354,0.00008513214,0.070776075,0.00085981126,0.0022101619,0.000004439347,0.000011411171,0.0000246354,0.00009297284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99232525,0.00079372904,0.0027381876,0.0006663577,0.0029619108,0.0005145671],"domain_scores_gemma":[0.98442495,0.0020337529,0.0036272607,0.0004602167,0.009303841,0.00015000357],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0026455969,0.0004738028,0.00088931597,0.0012750444,0.00034936683,0.0016037857,0.003632685,0.00015980333,0.00013025299],"category_scores_gemma":[0.0015075004,0.0005069861,0.0004904587,0.0008880507,0.0003874371,0.002643402,0.0013698536,0.0009189831,0.000016521471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005211611,0.0012884535,0.006619654,0.00013822451,0.005927109,0.00036109862,0.114471026,0.19820131,0.00464602,0.2500347,0.0022570817,0.41553417],"study_design_scores_gemma":[0.0021989595,0.0011177576,0.025642773,0.0064913156,0.0006163149,0.00013816431,0.013693524,0.8100533,0.038958132,0.09964478,0.00067511754,0.00076984725],"about_ca_topic_score_codex":0.00057034445,"about_ca_topic_score_gemma":0.00004399996,"teacher_disagreement_score":0.62359947,"about_ca_system_score_codex":0.0011184692,"about_ca_system_score_gemma":0.0017241486,"threshold_uncertainty_score":0.99973816},"labels":[],"label_agreement":null},{"id":"W7126016704","doi":"10.1109/icac69156.2025.11361508","title":"A Novel Objective Function for Counterfactual Explanations Using Conic Optimization","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Counterfactual thinking; Counterfactual conditional; Artificial neural network; Conic section; Benchmark (surveying); Function (biology); Feature (linguistics)","score_opus":0.05987872412210945,"score_gpt":0.32263671678594114,"score_spread":0.2627579926638317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126016704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015320672,0.00019912775,0.9874279,0.00090207614,0.00360423,0.0015835293,0.000040149698,0.00017117285,0.004539744],"genre_scores_gemma":[0.842649,0.00003730137,0.15184517,0.0012726609,0.00016987312,0.00014981162,0.000023997885,0.000027249049,0.0038249374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971431,0.000059509417,0.0007979861,0.0009812695,0.00034493773,0.0006731813],"domain_scores_gemma":[0.9968221,0.0006477351,0.00028042396,0.00063076,0.0015107741,0.00010817563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006374958,0.000360046,0.0003434444,0.0006032,0.0011079216,0.00085959607,0.00066720985,0.00024404896,0.00026417663],"category_scores_gemma":[0.00045472928,0.00040504526,0.00017426723,0.0017587981,0.00016201597,0.0020856815,0.00025345304,0.00020885149,0.000042428306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117451455,0.0002711438,0.000023007904,0.000047932615,0.00013808293,6.116168e-7,0.0012898782,0.7143622,0.0048494027,0.27215496,0.00048452508,0.0062607806],"study_design_scores_gemma":[0.00049345795,0.00028578442,0.000029707437,0.00012670664,0.0001314333,0.000005801198,0.0025198953,0.9659672,0.024880383,0.004204652,0.0009908902,0.00036414043],"about_ca_topic_score_codex":0.00059029466,"about_ca_topic_score_gemma":0.00032277207,"teacher_disagreement_score":0.8411169,"about_ca_system_score_codex":0.0007858805,"about_ca_system_score_gemma":0.0012595799,"threshold_uncertainty_score":0.99984014},"labels":[],"label_agreement":null},{"id":"W7126182001","doi":"10.1109/ieses66335.2025.11359839","title":"Discovering Stable Economic Mechanisms via Causal Representation Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Spurious relationship; Identifiability; Representation (politics); Focus (optics); Stability (learning theory); Causality (physics); Causal model; Causation","score_opus":0.02200929064244272,"score_gpt":0.29610827324122,"score_spread":0.2740989825987773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126182001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01995625,0.0001446234,0.92556715,0.0013407831,0.0032322803,0.00046261598,0.0000017160511,0.00025749864,0.04903707],"genre_scores_gemma":[0.9412001,0.000121331796,0.014915959,0.00027543804,0.00011863988,0.000039441748,0.000005273094,0.000026720954,0.043297093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606794,0.0002947242,0.0009510013,0.0013715965,0.00032477858,0.0009899458],"domain_scores_gemma":[0.9980139,0.0003361038,0.00027907497,0.001059696,0.0001344673,0.00017675135],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00094551384,0.0003985901,0.00044383662,0.00041540724,0.0009000165,0.0015789199,0.0012374446,0.00018325451,0.0010884517],"category_scores_gemma":[0.00016406506,0.00045860655,0.00017614207,0.0009086668,0.000112574024,0.003083877,0.0012820449,0.0005014334,0.0015571859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030253035,0.000071990056,0.00055518287,0.000048391885,0.00008209044,0.000028378716,0.001943925,0.21344341,0.017129285,0.71476334,0.00036480092,0.051538944],"study_design_scores_gemma":[0.00011092736,0.00010538977,0.00010926016,0.00006671776,0.000022466567,0.0000047974627,0.0017046817,0.6548106,0.27022916,0.07126661,0.0012438832,0.0003255071],"about_ca_topic_score_codex":0.0072054793,"about_ca_topic_score_gemma":0.0009544776,"teacher_disagreement_score":0.92124385,"about_ca_system_score_codex":0.0006942918,"about_ca_system_score_gemma":0.0005251523,"threshold_uncertainty_score":0.9998247},"labels":[],"label_agreement":null},{"id":"W7126202239","doi":"10.18280/isi.301203","title":"Interpretable Multi-Label Classification of Human- and Large Language Model-Generated Texts Using Transformer Embeddings and Explainable Artificial Intelligence","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformer; Natural language; Pattern recognition (psychology); Applications of artificial intelligence; Language model","score_opus":0.0527775078637612,"score_gpt":0.32499608989838263,"score_spread":0.27221858203462146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126202239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36491424,0.0007518201,0.63236326,0.000048387286,0.0002180321,0.00069725723,0.00003920957,0.00007878715,0.00088901445],"genre_scores_gemma":[0.9689489,0.00018755136,0.030351121,0.00013714631,0.00002681563,0.00006532625,0.00004227566,0.00002217021,0.00021866613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957466,0.0001843722,0.0021656053,0.00059535075,0.0004295064,0.00087853556],"domain_scores_gemma":[0.9973013,0.00012684877,0.00082198455,0.00060952414,0.00095755135,0.00018282034],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016676207,0.0005334048,0.0006668593,0.001043389,0.0011957769,0.0012077027,0.00063105166,0.0004041661,0.00003168186],"category_scores_gemma":[0.0003840988,0.00059050677,0.00009354353,0.0017232405,0.0006259945,0.008935631,0.00031001115,0.0003969896,0.000013375027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016438353,0.00038364308,0.00040354178,0.002609644,0.00014514233,0.000005208074,0.14881076,0.0085207205,0.17180574,0.21527512,0.000025842071,0.45185024],"study_design_scores_gemma":[0.00021739444,0.00013164183,0.00009804288,0.0009530384,0.0000723353,0.0000127235835,0.014131597,0.83294374,0.13984844,0.011141498,0.000027862458,0.00042167158],"about_ca_topic_score_codex":0.0006272178,"about_ca_topic_score_gemma":0.00017791026,"teacher_disagreement_score":0.824423,"about_ca_system_score_codex":0.0004599974,"about_ca_system_score_gemma":0.00041868773,"threshold_uncertainty_score":0.9998291},"labels":[],"label_agreement":null},{"id":"W7126373971","doi":"10.21428/594757db.ef6e3518","title":"Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Object detection; Object (grammar); Pattern recognition (psychology); Noise (video); Feature (linguistics)","score_opus":0.026624635875226114,"score_gpt":0.26201295299512556,"score_spread":0.23538831711989944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126373971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061540622,0.00005443231,0.9344421,0.0012848944,0.00022962494,0.00044215057,0.0000017576338,0.00035420086,0.0016501871],"genre_scores_gemma":[0.9761279,0.00000461113,0.022803655,0.0001478948,0.000068901965,0.0001847251,0.0000028897098,0.000013078771,0.0006463162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998906,0.000030561263,0.00018619974,0.0004353548,0.00019490496,0.00024694952],"domain_scores_gemma":[0.99919736,0.00035209698,0.000038380414,0.0002264218,0.000115662086,0.00007004657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030624613,0.00013025728,0.000100718986,0.0002715739,0.0002587324,0.0004264217,0.00016468609,0.00005028695,0.000012163709],"category_scores_gemma":[0.000069081274,0.00010179669,0.000032626427,0.0006375905,0.000040116967,0.00048262457,0.000050785868,0.00008707677,0.000026866468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000619242,0.000110027184,0.00003942991,0.00023731147,0.00009374232,0.000029849942,0.01075588,0.019668335,0.12427779,0.5886126,0.0012036945,0.25490937],"study_design_scores_gemma":[0.000093509065,0.00012215877,0.00008317936,0.0000701488,0.0000059506015,0.0000201849,0.001154427,0.8277305,0.16426675,0.0014084394,0.0048748893,0.00016985563],"about_ca_topic_score_codex":0.00006749105,"about_ca_topic_score_gemma":0.00010836542,"teacher_disagreement_score":0.9145873,"about_ca_system_score_codex":0.00010103923,"about_ca_system_score_gemma":0.000069564325,"threshold_uncertainty_score":0.41511485},"labels":[],"label_agreement":null},{"id":"W7126404571","doi":"10.21428/594757db.7137edbd","title":"Interpreting time series forecasting models using model classreliance","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Probabilistic logic; Benchmark (surveying); Feature (linguistics); Time series; Series (stratigraphy); Probabilistic forecasting","score_opus":0.08815879048809915,"score_gpt":0.2877683400219979,"score_spread":0.19960954953389876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126404571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068737795,0.00024122375,0.96929735,0.00081338844,0.0003136012,0.00011714839,0.0000015271536,0.0008521332,0.021489821],"genre_scores_gemma":[0.61562675,0.0000067651276,0.38047117,0.00023693478,0.000058443147,0.000008133923,5.392374e-7,0.000023722005,0.0035675312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983054,0.000035056324,0.00034563677,0.0005712838,0.00025245838,0.00049018016],"domain_scores_gemma":[0.9991992,0.00012984031,0.00004490508,0.00043056012,0.00010560085,0.00008987883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043781963,0.00018919216,0.00016245789,0.00016233133,0.00019748711,0.00082368386,0.0007687578,0.00007090744,0.000032189684],"category_scores_gemma":[0.00006579366,0.0001753452,0.00008732989,0.00064508396,0.00005859956,0.0039198794,0.0004857037,0.0001984868,0.00021121067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035440125,0.000009620002,0.0000038452663,0.00003636758,0.000011820265,0.000048277212,0.0018099722,0.6346922,0.008970202,0.33982646,0.00054060435,0.014047087],"study_design_scores_gemma":[0.000009512627,0.000021202577,4.859981e-8,0.00018341852,0.000003477948,0.000047461006,0.00007327912,0.8595435,0.017684681,0.122131966,0.00010992055,0.00019155533],"about_ca_topic_score_codex":0.000059996775,"about_ca_topic_score_gemma":0.000012425495,"teacher_disagreement_score":0.60875297,"about_ca_system_score_codex":0.00012784374,"about_ca_system_score_gemma":0.0001769433,"threshold_uncertainty_score":0.79428023},"labels":[],"label_agreement":null},{"id":"W7126407450","doi":"10.21428/594757db.df69c52e","title":"Diminishing Simplicity Bias using GAN Generated UnbiasedAugmentations","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spurious relationship; Robustness (evolution); Simplicity; Artificial neural network; Set (abstract data type); Selection bias; Adversarial system; Feature (linguistics)","score_opus":0.1903398970780317,"score_gpt":0.36161331553486903,"score_spread":0.17127341845683733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126407450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22996093,0.00007699198,0.7634948,0.0009658546,0.0005391351,0.00011507857,0.000002416867,0.00061342475,0.004231381],"genre_scores_gemma":[0.95495814,0.0000076229744,0.043448925,0.0007449126,0.00011052919,0.000008653289,0.00000422411,0.000014979603,0.000702022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985747,0.00007572418,0.00029121345,0.00045976162,0.00024891802,0.00034970918],"domain_scores_gemma":[0.9991208,0.00022979318,0.000033320186,0.00041070668,0.00008998133,0.00011544391],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034640412,0.00013997866,0.00011012906,0.00018264547,0.00027926307,0.0013087854,0.0005504288,0.000051043204,0.00014100959],"category_scores_gemma":[0.00008373891,0.0001290414,0.00006546303,0.0012570233,0.0000404696,0.0013997895,0.00014590127,0.00013816466,0.00033128474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028504417,0.000097059536,0.00034437628,0.000042148105,0.000058650763,0.00023381514,0.0033694655,0.039065417,0.14692579,0.7541508,0.0038347142,0.051874917],"study_design_scores_gemma":[0.000018012575,0.000021948606,0.00005638559,0.000023668,0.00000666215,0.000018099208,0.00019244847,0.77426356,0.21795784,0.005304785,0.001978622,0.00015797146],"about_ca_topic_score_codex":0.0007468899,"about_ca_topic_score_gemma":0.00015469648,"teacher_disagreement_score":0.748846,"about_ca_system_score_codex":0.000121826735,"about_ca_system_score_gemma":0.0001557146,"threshold_uncertainty_score":0.99972796},"labels":[],"label_agreement":null},{"id":"W7126416440","doi":"10.21428/594757db.2df690ff","title":"Guided AbsoluteGrad : Magnitude of GradientsMatters to Explanation’s Localization and Saliency","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Metric (unit); Noise (video); Variance (accounting); Pattern recognition (psychology); Image (mathematics); Quality (philosophy); Magnitude (astronomy); Image quality","score_opus":0.02409225435880597,"score_gpt":0.2889745048541691,"score_spread":0.2648822504953631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126416440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027804714,0.00012540772,0.9640268,0.0032682426,0.00037516566,0.00017941774,0.000001645604,0.00019733976,0.004021267],"genre_scores_gemma":[0.96748215,0.000029981984,0.030541126,0.0009308111,0.000025769166,0.000020355137,0.0000028401737,0.000009801352,0.00095716066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989493,0.00002777644,0.0002800231,0.00032660863,0.00022836727,0.00018793928],"domain_scores_gemma":[0.9994372,0.000065138054,0.0000268406,0.00026781953,0.00010964675,0.00009332775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002426995,0.00009485326,0.000099099634,0.00027138056,0.000057973655,0.0001812775,0.00035380802,0.000029394281,0.00004533151],"category_scores_gemma":[0.000057818084,0.00008444347,0.000026887687,0.0007314256,0.000031836396,0.0005850878,0.00013484833,0.00003938769,0.00013916453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027296367,0.000049311824,0.0007881611,0.000096997705,0.000018486287,0.000022361724,0.005700029,0.0016338623,0.0038253684,0.90823984,0.028515887,0.051106952],"study_design_scores_gemma":[0.00013242433,0.00030635035,0.0020607074,0.00023005658,0.000020522899,0.000048983613,0.0009759089,0.77853066,0.122077845,0.061466936,0.033557944,0.0005916558],"about_ca_topic_score_codex":0.00033725603,"about_ca_topic_score_gemma":0.00011858176,"teacher_disagreement_score":0.9396774,"about_ca_system_score_codex":0.00004346803,"about_ca_system_score_gemma":0.000034659293,"threshold_uncertainty_score":0.3443505},"labels":[],"label_agreement":null},{"id":"W7126433731","doi":"10.21428/594757db.ec493180","title":"Advancing NHL Analytics through Explainable AI","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Key (lock); Bridge (graph theory); Analytics; League; Reliability (semiconductor); Applications of artificial intelligence","score_opus":0.025191467099174466,"score_gpt":0.31295471272661907,"score_spread":0.2877632456274446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126433731","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008683366,0.0006773818,0.924136,0.0067809206,0.00089142984,0.00012710689,6.982603e-7,0.0009430149,0.065575145],"genre_scores_gemma":[0.8255276,0.00015222473,0.14964804,0.004184771,0.00028663283,0.00003104824,0.000002206583,0.000036813457,0.020130653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806637,0.000039439285,0.0003179928,0.00059761945,0.0003398839,0.0006387228],"domain_scores_gemma":[0.9988078,0.00020056278,0.00002713866,0.0007282254,0.00012367211,0.00011261374],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004213531,0.00018276775,0.00017176595,0.00014971719,0.00019809708,0.0008148696,0.0009125306,0.000068504225,0.0002694625],"category_scores_gemma":[0.0000983671,0.00016083627,0.0001023552,0.0013426127,0.000049342005,0.0030137254,0.00034099736,0.00023329827,0.0018182801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012991471,0.00002867381,0.000032060885,0.000042612344,0.000018310924,0.00022836008,0.001402666,0.002547127,0.00092662335,0.95172405,0.024881162,0.018167049],"study_design_scores_gemma":[0.000025327316,0.00007009535,0.0000055290675,0.00005389627,0.0000073915226,0.000031972766,0.00057850784,0.51518697,0.063362055,0.14867117,0.27173892,0.00026816904],"about_ca_topic_score_codex":0.00029505783,"about_ca_topic_score_gemma":0.00010588187,"teacher_disagreement_score":0.8246593,"about_ca_system_score_codex":0.00014981769,"about_ca_system_score_gemma":0.0001772852,"threshold_uncertainty_score":0.99895895},"labels":[],"label_agreement":null},{"id":"W7127268639","doi":"10.1109/ccece64018.2025.11364378","title":"Cross-Domain Intent Decomposition - Interpretable Machine Reasoning","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada)","funders":"","keywords":"Knowledge representation and reasoning; Domain knowledge; Expert system; Ontology; Context (archaeology); Domain (mathematical analysis); Decomposition; Representation (politics); Knowledge-based systems","score_opus":0.013341247929102977,"score_gpt":0.33096704769655394,"score_spread":0.317625799767451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127268639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031976163,0.0012683789,0.8407655,0.00325059,0.0035346372,0.00060173415,0.000008026543,0.00034641146,0.11824857],"genre_scores_gemma":[0.91389817,0.00013847182,0.053812496,0.002737602,0.00010996568,0.00005808458,0.000011224017,0.00003138205,0.029202584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945219,0.00039515275,0.0014763311,0.0016276988,0.0005854267,0.0013934771],"domain_scores_gemma":[0.99653715,0.00035758314,0.00031309735,0.0017970167,0.00066912716,0.00032601607],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018318349,0.00063878496,0.00064429955,0.0006520493,0.0011033411,0.0029779049,0.0026741014,0.0002984534,0.002073965],"category_scores_gemma":[0.0003922413,0.00065730227,0.00036793714,0.0022878007,0.0004349642,0.0024863356,0.0022799005,0.00076336664,0.0012540065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000200654,0.0005375328,0.0053471588,0.00014476894,0.00018015642,0.00011050128,0.0026242598,0.0023277693,0.007013301,0.8535435,0.0020924837,0.12587789],"study_design_scores_gemma":[0.00035103524,0.00030265487,0.0010519532,0.0010060973,0.000041009167,0.000043523603,0.0006200132,0.8475155,0.09705974,0.041699365,0.0095952535,0.0007138209],"about_ca_topic_score_codex":0.002174798,"about_ca_topic_score_gemma":0.00046899618,"teacher_disagreement_score":0.881922,"about_ca_system_score_codex":0.00075233204,"about_ca_system_score_gemma":0.0004413607,"threshold_uncertainty_score":0.99958783},"labels":[],"label_agreement":null},{"id":"W7129262759","doi":"10.1109/iscs69371.2025.11386435","title":"XAI-Driven Security Systems: Enhancing Trust and Clarity in Automated Threat Detection and Response","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"CLARITY; NIST; Benchmark (surveying); Artificial neural network; Triage; Fidelity; Applications of artificial intelligence; Intrusion detection system","score_opus":0.013681537813101285,"score_gpt":0.2819360209874464,"score_spread":0.26825448317434514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129262759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84597665,0.0016947244,0.14815165,0.0007331688,0.0009769945,0.0009427422,0.0000042751285,0.0005183688,0.0010014492],"genre_scores_gemma":[0.9980883,0.0003203159,0.0007335934,0.0001613959,0.000037969294,0.000048667087,5.333639e-7,0.000014800422,0.0005944323],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995061,0.0014170136,0.0010581001,0.0013170361,0.00034891767,0.000797942],"domain_scores_gemma":[0.9975263,0.00096241303,0.00019967115,0.00080668036,0.00027888946,0.00022605679],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003235965,0.00043583135,0.0006123405,0.0007892799,0.00064444984,0.0011846583,0.0005195156,0.00048642667,0.000019290914],"category_scores_gemma":[0.00081063237,0.00046209252,0.000062274354,0.002044544,0.0003242239,0.0014645226,0.00084108923,0.0006286869,0.000028236986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077440105,0.0019789482,0.08697726,0.0052264594,0.0005351377,0.0013444938,0.10013032,0.008261813,0.44148463,0.20807987,0.0006288726,0.13760819],"study_design_scores_gemma":[0.00035647754,0.00027779664,0.01738182,0.00056321605,0.00002729721,0.00004780045,0.0034467934,0.9020555,0.071615115,0.003622797,0.0002024712,0.00040291675],"about_ca_topic_score_codex":0.0068029654,"about_ca_topic_score_gemma":0.010874724,"teacher_disagreement_score":0.8937937,"about_ca_system_score_codex":0.0005558306,"about_ca_system_score_gemma":0.00039189344,"threshold_uncertainty_score":0.9998522},"labels":[],"label_agreement":null},{"id":"W7129457470","doi":"10.1109/iceconf65644.2025.11379388","title":"Explainable AI-Integrated Training Recommendation Framework for Skill Development","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pan Am Clinic","funders":"","keywords":"Flexibility (engineering); Openness to experience; Training (meteorology); Reinforcement learning; Active learning (machine learning); Dreyfus model of skill acquisition","score_opus":0.06887642800011412,"score_gpt":0.3522186550347798,"score_spread":0.28334222703466566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129457470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001077436,0.00016917182,0.95849705,0.018013228,0.004340803,0.0017644784,0.00000925071,0.00041987383,0.015708689],"genre_scores_gemma":[0.27929634,0.000066392204,0.69007957,0.00807735,0.00017943118,0.0006248722,0.00006318991,0.00004880069,0.021564055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99412525,0.0002553141,0.0017466504,0.0016944484,0.00040508847,0.0017732575],"domain_scores_gemma":[0.9954106,0.0015925056,0.0003704297,0.0010199457,0.0013015417,0.00030495803],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024476405,0.0007067969,0.0007351889,0.0007701726,0.0017606604,0.0015105513,0.0018158279,0.0005644586,0.0012932755],"category_scores_gemma":[0.001964949,0.0007350331,0.00025512782,0.0030785818,0.00015045362,0.0018602773,0.0005707566,0.00076560356,0.00037735928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057000532,0.00020242081,0.00003670185,0.00009555413,0.0000968487,0.00000426235,0.010509191,0.00033276004,0.00008020254,0.4651983,0.005760126,0.5176266],"study_design_scores_gemma":[0.0003463071,0.00024017596,0.000044330074,0.0008056415,0.000039050075,0.000004139777,0.014261097,0.29823315,0.107041806,0.19032942,0.3877802,0.0008746897],"about_ca_topic_score_codex":0.00020262349,"about_ca_topic_score_gemma":0.00026269947,"teacher_disagreement_score":0.51675195,"about_ca_system_score_codex":0.0009741902,"about_ca_system_score_gemma":0.0028355175,"threshold_uncertainty_score":0.99961966},"labels":[],"label_agreement":null},{"id":"W7130543099","doi":"10.1109/fllm67465.2025.11391103","title":"Agent-guided Causal Discovery with a Small Language Model","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Spurious relationship; Causal model; Language model; Equivalence (formal languages); Task (project management); Causal structure; Causal inference; Benchmark (surveying)","score_opus":0.049363500757075615,"score_gpt":0.2976340889346764,"score_spread":0.24827058817760078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130543099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07999989,0.0004529926,0.84789675,0.003086803,0.0006231258,0.0006126085,0.000009034486,0.00024031124,0.06707851],"genre_scores_gemma":[0.78322124,0.000061328254,0.049285725,0.0031159997,0.00008199771,0.000051517618,0.000004029134,0.000030583284,0.16414756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99586815,0.00015999025,0.00079700304,0.0014088656,0.00054507237,0.0012209227],"domain_scores_gemma":[0.99710864,0.00019204411,0.00018115996,0.001959461,0.00030380083,0.00025487156],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058594724,0.00056899106,0.0005196348,0.0003989087,0.0004482595,0.0017027095,0.002113354,0.00019867803,0.00013618406],"category_scores_gemma":[0.00013116995,0.00047814875,0.00018384389,0.0017793594,0.0003088341,0.0018776412,0.001173055,0.00043788156,0.00037148493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001327795,0.00063162047,0.00051480695,0.00019627908,0.00023768518,0.0006165481,0.010622174,0.11128369,0.006419592,0.82388407,0.006945826,0.03851495],"study_design_scores_gemma":[0.000299649,0.00019337784,0.000061548766,0.00023919524,0.00006950964,0.000019294794,0.0020090134,0.91093206,0.07801414,0.006868807,0.0006767093,0.0006166799],"about_ca_topic_score_codex":0.0026481699,"about_ca_topic_score_gemma":0.003516628,"teacher_disagreement_score":0.81701523,"about_ca_system_score_codex":0.0002785265,"about_ca_system_score_gemma":0.0013775299,"threshold_uncertainty_score":0.999767},"labels":[],"label_agreement":null},{"id":"W7130549209","doi":"10.1109/fllm67465.2025.11390932","title":"Explainable AI via Large Language Models: Translating Neural Network Behavior into Interpretable Decision Trees","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Artificial Intelligence in Medicine (Canada); Université TÉLUQ","funders":"","keywords":"Artificial neural network; Decision tree; Fidelity; Deep neural networks; Audit; Deep learning; Language model; Language understanding","score_opus":0.019354306108045678,"score_gpt":0.3086205793526522,"score_spread":0.2892662732446065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130549209","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03987705,0.0064129033,0.93366796,0.0015860539,0.003079139,0.0013577446,0.000007637952,0.000536755,0.013474747],"genre_scores_gemma":[0.9325958,0.00010002968,0.057758108,0.002658135,0.00028265192,0.00022905675,0.000010760463,0.0000714755,0.0062939883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915173,0.0005093507,0.0020495548,0.0021593475,0.00097390875,0.00279051],"domain_scores_gemma":[0.99562854,0.0007272905,0.00031894373,0.0023376402,0.00052556786,0.00046203856],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021634214,0.0009975961,0.0010863269,0.0006390861,0.0018730208,0.0019330417,0.0034388062,0.0005322348,0.0008852165],"category_scores_gemma":[0.00018904898,0.0010085972,0.00057652267,0.0037216658,0.00022424803,0.005641191,0.0018172687,0.0011805983,0.00026748402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019533547,0.00077417056,0.0009336804,0.00012125745,0.00008512397,0.00032807415,0.02277741,0.21973452,0.0019395074,0.0868404,0.0029416585,0.6633289],"study_design_scores_gemma":[0.00047822236,0.00029187373,0.00006230286,0.0006264674,0.00012919624,0.000018778643,0.0045624305,0.9281839,0.0077010207,0.05580566,0.001260075,0.0008800465],"about_ca_topic_score_codex":0.004151366,"about_ca_topic_score_gemma":0.010545578,"teacher_disagreement_score":0.89271873,"about_ca_system_score_codex":0.0004251238,"about_ca_system_score_gemma":0.0004444491,"threshold_uncertainty_score":0.9994264},"labels":[],"label_agreement":null},{"id":"W7130623201","doi":"","title":"Redundancy as the shadow of explainability: a trade-off principle for AI-intensive systems","year":2025,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Redundancy (engineering); Shadow (psychology); Computation; Robustness (evolution)","score_opus":0.034064787207979404,"score_gpt":0.32914292912673326,"score_spread":0.29507814191875387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130623201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3421615,0.00070612226,0.36792883,0.1913595,0.0023379193,0.0150084505,0.00024430722,0.00093309855,0.07932029],"genre_scores_gemma":[0.98592466,0.00008381559,0.00056470645,0.00020356663,0.000052403477,0.000030608877,0.00000864935,0.000015189789,0.013116397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961487,0.00061903935,0.00044798246,0.00082828046,0.00097159925,0.0009843762],"domain_scores_gemma":[0.9946488,0.0012355447,0.00016879385,0.0014526565,0.0022621097,0.00023209336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002279605,0.00023535288,0.00041317986,0.00064110593,0.0010479568,0.00020815968,0.002635505,0.0001737313,0.000029956629],"category_scores_gemma":[0.0015676853,0.00021136049,0.0002546792,0.002228508,0.0007272217,0.00088840513,0.0011613293,0.0006468735,0.00003243612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001630985,0.00018149601,0.00078458886,0.0002304185,0.00010976938,0.00021489203,0.0019179033,0.00032618755,0.0002827023,0.98292446,0.01026406,0.0026004317],"study_design_scores_gemma":[0.0020186128,0.0029319397,0.005268527,0.0011759581,0.00012947292,0.00006385804,0.11128793,0.0536204,0.04811092,0.09201166,0.6820283,0.0013524411],"about_ca_topic_score_codex":0.0039021831,"about_ca_topic_score_gemma":0.00013549595,"teacher_disagreement_score":0.8909128,"about_ca_system_score_codex":0.00038798005,"about_ca_system_score_gemma":0.0014023914,"threshold_uncertainty_score":0.861903},"labels":[],"label_agreement":null},{"id":"W7130712466","doi":"10.1109/swc65939.2025.00211","title":"EQDAT-RE: An Explainable Qualitative Data Analysis for Transparent Requirements Engineering","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Pipeline (software); Automation; Natural language; Domain (mathematical analysis); Counterfactual thinking; Requirements engineering; Software; Embedding","score_opus":0.35074698674812743,"score_gpt":0.46560931701399794,"score_spread":0.1148623302658705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130712466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018605922,0.00069345144,0.9890812,0.0033491063,0.0012734324,0.0014610658,0.00029240444,0.00026347276,0.0017252552],"genre_scores_gemma":[0.8346148,0.00015057616,0.15771197,0.00087534747,0.00014128572,0.0002949077,0.00051585294,0.000045034594,0.005650191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99217147,0.00049707346,0.0017709984,0.0028672335,0.0008601066,0.0018331473],"domain_scores_gemma":[0.9916235,0.0011725656,0.00030657876,0.0055265,0.0007478823,0.0006229349],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005734157,0.00070262933,0.0010675445,0.0013886641,0.0007947152,0.0012910913,0.006823504,0.00023892545,0.00042395308],"category_scores_gemma":[0.0014459993,0.0007596908,0.00037892052,0.0065619852,0.00015660815,0.005674264,0.0013608112,0.0003086071,0.000057714624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003045546,0.0019198515,0.00047838726,0.0009341714,0.0068575763,0.00004400209,0.06805509,0.22763874,0.0025159365,0.6421678,0.00839531,0.040688585],"study_design_scores_gemma":[0.0003646085,0.00035339975,0.000071447204,0.00012960668,0.0010514081,3.493032e-7,0.0177777,0.9428435,0.019125096,0.005631041,0.011891024,0.0007608059],"about_ca_topic_score_codex":0.0015934358,"about_ca_topic_score_gemma":0.0024274206,"teacher_disagreement_score":0.83275425,"about_ca_system_score_codex":0.00044767806,"about_ca_system_score_gemma":0.0007822559,"threshold_uncertainty_score":0.99974567},"labels":[],"label_agreement":null},{"id":"W7131063994","doi":"10.1145/3774816.3774823","title":"Concept-Level Local Explanations of Kidney Transplant Survival Predictions by Black-Box ML Models","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Kidney transplant; Process (computing); Outcome (game theory); Feature (linguistics); Kidney transplantation; Simplicity; Clinical decision making","score_opus":0.045807193728527484,"score_gpt":0.2810144085754511,"score_spread":0.23520721484692364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131063994","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046345993,0.00035484,0.93538237,0.009296799,0.0023099072,0.00076333963,0.0017144979,0.000228186,0.04948659],"genre_scores_gemma":[0.975761,0.0005216394,0.0055535035,0.0014378988,0.000078714074,0.000064447435,0.00011879961,0.000029488769,0.016434534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994526,0.0003841296,0.0017443734,0.0012741368,0.0010145847,0.0010567515],"domain_scores_gemma":[0.99595535,0.00063097675,0.0002899446,0.001411797,0.00091167283,0.00080028374],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077169936,0.00057476864,0.0007546608,0.0005397117,0.00064135215,0.00028047955,0.0022181957,0.00040427022,0.0007419982],"category_scores_gemma":[0.00022985497,0.0006117356,0.00034434465,0.0024302925,0.0014633442,0.0018253874,0.00034386356,0.0005570348,0.00012757625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005293083,0.00087697356,0.00008736725,0.00011850037,0.00026788726,0.000014134415,0.007557395,0.11718304,0.001324449,0.78166705,0.08284522,0.00800505],"study_design_scores_gemma":[0.00045686742,0.00021088385,0.000025696307,0.00031430324,0.00012942296,0.000005339199,0.0029300225,0.8894198,0.081371196,0.02021869,0.0044226153,0.0004951504],"about_ca_topic_score_codex":0.002846059,"about_ca_topic_score_gemma":0.00059105846,"teacher_disagreement_score":0.9752975,"about_ca_system_score_codex":0.00026249362,"about_ca_system_score_gemma":0.0023693808,"threshold_uncertainty_score":0.9996334},"labels":[],"label_agreement":null},{"id":"W7131085793","doi":"10.1109/iccvw69036.2025.00072","title":"Are Medical Image Generative Models Biologically Trustworthy?","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Generative grammar; Generative model; Perception; Trustworthiness; Focus (optics); Computational model; Cognition","score_opus":0.05275318530772239,"score_gpt":0.3201313267330086,"score_spread":0.2673781414252862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131085793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006864446,0.0012012136,0.8658531,0.027604863,0.0017660562,0.0005789157,0.000009023735,0.00033141678,0.09579101],"genre_scores_gemma":[0.8904127,0.0010971578,0.06896835,0.021059845,0.0004544212,0.00011776769,0.00000529342,0.000028934524,0.017855557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933641,0.000750266,0.0014001097,0.0019282178,0.0011374401,0.0014198693],"domain_scores_gemma":[0.9956878,0.0006698011,0.00043632256,0.0015719467,0.0009853775,0.0006487976],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018546234,0.0006640667,0.00087119517,0.00038124976,0.00079150486,0.0009542359,0.0038562373,0.000740397,0.0036081788],"category_scores_gemma":[0.0016495783,0.00054439984,0.00036710274,0.0023720686,0.001046114,0.0016371661,0.0023525984,0.00093641697,0.001128313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044928496,0.00050419196,0.00024952175,0.000040927698,0.00012183922,0.00059677387,0.00068513723,0.0028934502,0.00073213276,0.87626755,0.012417747,0.105445825],"study_design_scores_gemma":[0.00019191722,0.000120376586,0.00016464874,0.00018308545,0.000022409653,0.000013066223,0.00066311494,0.8036273,0.01807486,0.17363626,0.00277139,0.0005315681],"about_ca_topic_score_codex":0.00024628645,"about_ca_topic_score_gemma":0.0005407712,"teacher_disagreement_score":0.88354826,"about_ca_system_score_codex":0.00022792954,"about_ca_system_score_gemma":0.0011819307,"threshold_uncertainty_score":0.9997007},"labels":[],"label_agreement":null},{"id":"W7131181425","doi":"10.1109/iccvw69036.2025.00780","title":"PRISM: Pruning for Rank-adaptive Interpretable Segmentation Model with Application to Historical Document Multiband Images","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Autoencoder; Pruning; Non-negative matrix factorization; Pattern recognition (psychology); Multispectral image; Rank (graph theory); Matrix decomposition; Segmentation; Feature (linguistics)","score_opus":0.018286423382902862,"score_gpt":0.2942341274000022,"score_spread":0.27594770401709934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131181425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010617414,0.00022470557,0.98440474,0.005508392,0.00042200327,0.0044124443,0.000004009836,0.0001644355,0.0037975456],"genre_scores_gemma":[0.48473513,0.000022741484,0.49324104,0.0008839399,0.00004012005,0.0012803712,0.0000049016203,0.00002299038,0.019768747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964233,0.000100079444,0.0008416223,0.0013835831,0.00049093814,0.0007604584],"domain_scores_gemma":[0.99769753,0.00031486672,0.00027049053,0.0008573998,0.0006239696,0.0002357206],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077452394,0.00044228364,0.00046490092,0.0004081706,0.00059857185,0.0005969099,0.0009947632,0.00014043975,0.00001562726],"category_scores_gemma":[0.00010119388,0.00041338356,0.00011786683,0.0011943143,0.00007868176,0.0016693003,0.00041250882,0.00022208801,0.000050013903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014825208,0.000580543,0.000111692505,0.00019436258,0.00019859482,0.0000039624642,0.014636369,0.38481915,0.043267474,0.12482746,0.009259231,0.42061865],"study_design_scores_gemma":[0.00044824672,0.00058744854,0.00000953398,0.00015835762,0.00007174892,0.0000013271338,0.0008151762,0.82531977,0.16191405,0.008339192,0.0019412987,0.00039384738],"about_ca_topic_score_codex":0.0009904682,"about_ca_topic_score_gemma":0.00018979872,"teacher_disagreement_score":0.49116367,"about_ca_system_score_codex":0.0026375367,"about_ca_system_score_gemma":0.0004823221,"threshold_uncertainty_score":0.9998318},"labels":[],"label_agreement":null},{"id":"W7131274198","doi":"10.1109/apsec66846.2025.00116","title":"XRepair - Unifying Retrieval, Repair, and Evaluation for Explainable LLM-Based Vulnerability Fixes","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Metadata; Vulnerability (computing); Identifier; Documentation; Identification (biology); Code (set theory); Software","score_opus":0.06671973611514004,"score_gpt":0.3608470590231114,"score_spread":0.2941273229079714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131274198","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10110877,0.0030040778,0.87307423,0.0069955923,0.0020602609,0.0051361667,0.000016156484,0.00086934154,0.007735399],"genre_scores_gemma":[0.94329596,0.00010011262,0.04865161,0.0016081171,0.00014028151,0.0003760596,0.000016749129,0.000035957506,0.005775143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99228793,0.0011757301,0.0016179088,0.00246905,0.0010964272,0.0013529713],"domain_scores_gemma":[0.99118143,0.00310747,0.00039006534,0.0023709403,0.002634733,0.00031536366],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013712809,0.00066189485,0.0007572477,0.00064481096,0.002100415,0.0010786897,0.0011347524,0.0004512512,0.0003838272],"category_scores_gemma":[0.0069754687,0.0006990094,0.00045163056,0.0027119746,0.0005446393,0.0020014758,0.00064042705,0.00045354888,0.000036987338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027272855,0.0040253056,0.010528317,0.0062002693,0.0006538279,0.000046033725,0.0057677235,0.064832285,0.0065300167,0.59565413,0.041857965,0.26117685],"study_design_scores_gemma":[0.000837719,0.00078021834,0.00054311013,0.00029535685,0.00018350598,0.0000021201045,0.001182183,0.8607725,0.071759306,0.052130543,0.010904206,0.00060924306],"about_ca_topic_score_codex":0.0007999657,"about_ca_topic_score_gemma":0.00038915928,"teacher_disagreement_score":0.8421872,"about_ca_system_score_codex":0.0009149197,"about_ca_system_score_gemma":0.0024320772,"threshold_uncertainty_score":0.9999583},"labels":[],"label_agreement":null},{"id":"W7131400021","doi":"10.1109/icdm65498.2025.00155","title":"Score-Based Integrated Gradient for Root Cause Explanations of Outliers","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Counterfactual thinking; Outlier; Heuristics; Anomaly detection; Root (linguistics); Multilinear map; Heuristic; Heteroscedasticity","score_opus":0.054162337959693524,"score_gpt":0.31513467822827856,"score_spread":0.26097234026858507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131400021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026763815,0.00020378627,0.9591144,0.004857629,0.0021974116,0.0016104002,0.000057608173,0.00015605976,0.0050389105],"genre_scores_gemma":[0.9668959,0.000018033417,0.02673681,0.00077097723,0.000032153454,0.00022625214,0.000027865228,0.000021670383,0.0052703707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962724,0.00017119525,0.0013028281,0.0009666077,0.00044318513,0.0008438141],"domain_scores_gemma":[0.99567544,0.000878423,0.000347971,0.001321113,0.001548289,0.00022877516],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009149442,0.00042471045,0.0005612501,0.0010338748,0.00047197635,0.0003245927,0.0017209231,0.00020832101,0.00017922212],"category_scores_gemma":[0.00093161705,0.0004121974,0.00034574256,0.003115096,0.00040401216,0.00058352767,0.00022931701,0.00025095296,0.000054106917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015893362,0.00093651714,0.0029842465,0.00025656566,0.00023345425,0.000011985562,0.0016757344,0.013881515,0.001647568,0.9228522,0.009943693,0.045417573],"study_design_scores_gemma":[0.0005132888,0.00048741206,0.0004101717,0.00034606908,0.00010887649,9.408247e-7,0.0011954766,0.7104271,0.26608714,0.01297868,0.007043835,0.00040102506],"about_ca_topic_score_codex":0.0012251317,"about_ca_topic_score_gemma":0.004098076,"teacher_disagreement_score":0.940132,"about_ca_system_score_codex":0.00039434686,"about_ca_system_score_gemma":0.0016919211,"threshold_uncertainty_score":0.999833},"labels":[],"label_agreement":null},{"id":"W7133027813","doi":"","title":"Interpretable and Constrained Machine Learning via Combinatorial Optimization","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Domain (mathematical analysis); Variety (cybernetics); Transformative learning; Instance-based learning; Computational learning theory; Domain knowledge; Deep learning","score_opus":0.01533767424158137,"score_gpt":0.3045177227674565,"score_spread":0.2891800485258751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133027813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005052735,0.0023879327,0.95645225,0.0006750416,0.0063168006,0.0010166492,0.0000058709566,0.00029498833,0.027797742],"genre_scores_gemma":[0.9156608,0.0013528768,0.024411341,0.00017314221,0.00026443446,0.00008940512,0.00039715398,0.000078018194,0.057572808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961544,0.0004199871,0.0008307237,0.0012904118,0.0005437565,0.00076069694],"domain_scores_gemma":[0.99722636,0.000515364,0.00063342,0.0005910756,0.00078009954,0.00025369006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079922023,0.0006902717,0.00077224936,0.0005051601,0.0008958384,0.0009756475,0.0009606241,0.0005720952,0.00073309446],"category_scores_gemma":[0.0009555978,0.0008182852,0.00015016487,0.0012052711,0.00014248134,0.0008602208,0.0004176703,0.0011578535,0.00007342101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011520894,0.0007462995,0.00035284093,0.0019192807,0.0006103705,0.00018344258,0.11001772,0.48000157,0.0114981895,0.28281826,0.00038434746,0.11031559],"study_design_scores_gemma":[0.00042671757,0.00037464633,0.0000063724965,0.00056716806,0.00010524505,0.0000132444075,0.0037453477,0.9750282,0.015581277,0.0020305228,0.0014406083,0.00068061205],"about_ca_topic_score_codex":0.0012027202,"about_ca_topic_score_gemma":0.00013065971,"teacher_disagreement_score":0.93204087,"about_ca_system_score_codex":0.00018992428,"about_ca_system_score_gemma":0.00058002217,"threshold_uncertainty_score":0.9994268},"labels":[],"label_agreement":null},{"id":"W7133325949","doi":"10.1109/icinvents64613.2025.11402497","title":"Explainable Quantum Machine Learning Through Interpretation of Variational Circuit Outcomes in Classification Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Quantum; Noise (video); Interpretation (philosophy); Limit (mathematics); Stability (learning theory); Polynomial","score_opus":0.04850518302860403,"score_gpt":0.31543103803816164,"score_spread":0.2669258550095576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133325949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01388492,0.00046618294,0.9497938,0.0034030334,0.0012059766,0.00070838665,0.0000079571955,0.00011496466,0.030414736],"genre_scores_gemma":[0.9863382,0.00014808572,0.0068898275,0.00044373889,0.000027151078,0.00008841038,0.000030436835,0.000020730542,0.006013431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99481773,0.00068276573,0.0019820016,0.0010798837,0.0007204606,0.0007171517],"domain_scores_gemma":[0.9963964,0.001228722,0.00073563866,0.000882989,0.0006781499,0.00007806056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017853713,0.00043615908,0.0007392965,0.0008506619,0.0003560064,0.00034501165,0.0013534514,0.00029847462,0.00040748637],"category_scores_gemma":[0.0016512213,0.00046160005,0.00021779223,0.0027809134,0.00021099462,0.00261319,0.00045716573,0.0006924215,0.00013738399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006275001,0.00057575374,0.033658437,0.00016603208,0.00008204408,0.000007204419,0.010048965,0.025199752,0.0021459819,0.9048867,0.00007325965,0.023093086],"study_design_scores_gemma":[0.0003333764,0.00018012871,0.016305374,0.00023593813,0.00002751741,0.000001838444,0.0028970344,0.8496227,0.005079021,0.124504045,0.0004878825,0.00032513318],"about_ca_topic_score_codex":0.004148841,"about_ca_topic_score_gemma":0.00062889484,"teacher_disagreement_score":0.9724533,"about_ca_system_score_codex":0.0005474092,"about_ca_system_score_gemma":0.00067914533,"threshold_uncertainty_score":0.9997836},"labels":[],"label_agreement":null},{"id":"W7134189966","doi":"10.1109/bigdata66926.2025.11401674","title":"Feature-Level Explainability in EEG-Based Fatigue Detection Using LASSO and Functional Connectivity","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Roots Exchange","keywords":"Pattern recognition (psychology); Lasso (programming language); Functional connectivity; Feature (linguistics); Artificial neural network","score_opus":0.09276624520698203,"score_gpt":0.3149499553937328,"score_spread":0.22218371018675076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134189966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36913452,0.00015851295,0.62539434,0.0026073784,0.0012068634,0.0006068874,0.0000059284316,0.000087580236,0.00079798646],"genre_scores_gemma":[0.98937327,0.000009522275,0.009246555,0.00064225955,0.00005894066,0.000056578803,0.0000021391882,0.000015652491,0.00059507333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99551976,0.00075068575,0.0006672557,0.0016404127,0.00053458905,0.0008872774],"domain_scores_gemma":[0.9967373,0.00135488,0.00021803117,0.0008861504,0.00060401385,0.00019961789],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022668599,0.00051020307,0.0005528189,0.0008003005,0.0008412896,0.0006319284,0.00045896997,0.0004485176,0.00008722075],"category_scores_gemma":[0.0014955223,0.0005548251,0.00015639635,0.00284641,0.00043430584,0.0015898551,0.00048000796,0.0007759717,0.00001412689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00116594,0.0026036312,0.16321667,0.000974521,0.00017241493,0.00011905512,0.0019056894,0.13097423,0.051912032,0.31580144,0.00033897965,0.3308154],"study_design_scores_gemma":[0.00047260337,0.00014287418,0.09925167,0.00014489845,0.000020959988,0.000007596377,0.0005354536,0.7565128,0.12864177,0.013577221,0.0002694446,0.0004227111],"about_ca_topic_score_codex":0.0032127332,"about_ca_topic_score_gemma":0.012744846,"teacher_disagreement_score":0.6255386,"about_ca_system_score_codex":0.0012378662,"about_ca_system_score_gemma":0.0010589751,"threshold_uncertainty_score":0.99969035},"labels":[],"label_agreement":null},{"id":"W7134275419","doi":"10.1145/3742413.3801713","title":"10.1145/3742413.3801713","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Component (thermodynamics); MEDLINE","score_opus":0.010430657922570636,"score_gpt":0.198582123939732,"score_spread":0.18815146601716137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134275419","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006183335,0.00004244627,0.0016039476,0.0012276882,0.000010375678,0.0001981609,0.0000020963219,0.00040352752,0.9958934],"genre_scores_gemma":[0.0012529858,4.4317568e-7,0.0029645155,0.00029179186,0.000105875835,0.000023173501,0.0000018202784,0.000016205508,0.9953432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984756,0.00005776465,0.00024182914,0.0004456609,0.00029430463,0.00048481455],"domain_scores_gemma":[0.9987425,0.000080030404,0.000032304364,0.00083560584,0.0000834346,0.00022612173],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026116677,0.00016327246,0.00016322618,0.000111702175,0.00016376935,0.00022051936,0.0012865083,0.000061269166,0.9547409],"category_scores_gemma":[0.000052349606,0.00016610458,0.00006590375,0.0006406567,0.000038532577,0.0005326901,0.00017658326,0.0001097703,0.9902503],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013228658,0.000049892606,2.1478775e-7,0.0000024754925,0.0000063826697,0.00002445393,0.00010468948,0.0004951193,0.00019420836,0.00037057747,0.07487684,0.9238619],"study_design_scores_gemma":[0.000041685624,0.00012398192,0.000008290856,0.000010097455,0.0000028619477,0.000011468575,0.0000016954402,0.022254668,0.0029296938,0.0003321697,0.9740652,0.00021821701],"about_ca_topic_score_codex":0.00007047788,"about_ca_topic_score_gemma":7.122533e-7,"teacher_disagreement_score":0.9236437,"about_ca_system_score_codex":0.000053501248,"about_ca_system_score_gemma":0.00004955223,"threshold_uncertainty_score":0.6773548},"labels":[],"label_agreement":null},{"id":"W7134952711","doi":"10.1109/icdmw69685.2025.00443","title":"Achieving Robust and Faithful Explanations via Conditional Pairwise Contrast","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Pairwise comparison; Contrast (vision); Pattern recognition (psychology); Conditional independence; Feature (linguistics)","score_opus":0.02446883306104261,"score_gpt":0.26459415228338695,"score_spread":0.24012531922234434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134952711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009285506,0.0008356898,0.9471722,0.013064502,0.0009525361,0.00056761294,0.00003172963,0.00019984465,0.02789037],"genre_scores_gemma":[0.9772541,0.00014640517,0.013183053,0.0025771097,0.00013227868,0.000062830695,0.000022103128,0.000015403253,0.0066067483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659,0.00023640583,0.0008574789,0.0010545341,0.00047666288,0.0007849168],"domain_scores_gemma":[0.9974007,0.0009124045,0.00018317402,0.0006973882,0.0005106535,0.00029566555],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076255767,0.00041154108,0.00041713525,0.0005208651,0.0012090082,0.0010794479,0.00092939544,0.00020879606,0.001014261],"category_scores_gemma":[0.00034097282,0.000437393,0.0001287353,0.0012646471,0.00050827774,0.0018144966,0.0006212108,0.00041321295,0.00029349423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002048104,0.00028302474,0.002766912,0.000074272124,0.0001236908,0.00004918078,0.0010422317,0.004097483,0.0015806056,0.93038106,0.006777103,0.05280395],"study_design_scores_gemma":[0.0005629896,0.00019798281,0.011613264,0.0002709178,0.00009404452,0.000057465277,0.0021358433,0.9182021,0.009595145,0.04710788,0.0093083605,0.0008539782],"about_ca_topic_score_codex":0.0003612669,"about_ca_topic_score_gemma":0.00056785066,"teacher_disagreement_score":0.9679686,"about_ca_system_score_codex":0.00017391538,"about_ca_system_score_gemma":0.00046587278,"threshold_uncertainty_score":0.9999575},"labels":[],"label_agreement":null},{"id":"W7140608172","doi":"10.1109/3ict68299.2025.11442144","title":"Towards Transparent Diagnostics: Explainable AI Across Biomedical Signals","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature (linguistics); Identification (biology); Key (lock); Set (abstract data type)","score_opus":0.045445306759806466,"score_gpt":0.3596954544006999,"score_spread":0.31425014764089343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140608172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005174065,0.0042314935,0.93034756,0.035935435,0.0054670796,0.0011561172,0.00006865619,0.00047774712,0.017141834],"genre_scores_gemma":[0.9637146,0.0028020914,0.0072482163,0.010718857,0.00043747644,0.0002785264,0.000018523142,0.000053073505,0.014728628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901556,0.0004937119,0.0022018056,0.0023146379,0.0016484144,0.0031858794],"domain_scores_gemma":[0.99422675,0.0013016147,0.00025633487,0.0022475987,0.0010010469,0.00096664106],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002522857,0.0009766397,0.0011760084,0.0005571795,0.0014871737,0.0022003613,0.004575751,0.000702775,0.002624496],"category_scores_gemma":[0.0010769834,0.0009524609,0.0005499982,0.0043853447,0.0012727359,0.0019076943,0.0016345337,0.0010443375,0.0018536346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013401189,0.0030585506,0.0006208255,0.0006722104,0.0004912464,0.0009769765,0.015217706,0.0028020616,0.0017836064,0.32208407,0.06848254,0.5836762],"study_design_scores_gemma":[0.0010827495,0.001328055,0.00067334424,0.0013347499,0.00020714391,0.00003219414,0.0075311563,0.35877034,0.2828308,0.074050955,0.27007475,0.0020837518],"about_ca_topic_score_codex":0.0024272797,"about_ca_topic_score_gemma":0.00044953707,"teacher_disagreement_score":0.95854056,"about_ca_system_score_codex":0.0005814119,"about_ca_system_score_gemma":0.0020218815,"threshold_uncertainty_score":0.9998128},"labels":[],"label_agreement":null},{"id":"W7144060738","doi":"10.47363/jaicc/icaic2025/2025(4)18","title":"A Method to Test the Ethics of Some AI Classifiers - The Example of School Dropouts Problem","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence & Cloud Computing","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"Categorical variable; Emulation; Relation (database); Element (criminal law); Artificial neural network; Test (biology)","score_opus":0.1042684580024157,"score_gpt":0.3924652265520924,"score_spread":0.28819676854967674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7144060738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02283944,0.0013237672,0.9242472,0.045810666,0.0040062605,0.0012846858,0.0000096429,0.000040342024,0.0004380112],"genre_scores_gemma":[0.90264744,0.00017901267,0.09156314,0.0038790451,0.0014778562,0.000013092715,4.2826602e-7,0.000055881745,0.00018411363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9841535,0.00317831,0.0073502692,0.0011245909,0.0026070527,0.0015862832],"domain_scores_gemma":[0.9678367,0.01783759,0.0052952194,0.0022606887,0.006191025,0.00057882693],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.027294789,0.00084608136,0.0017606197,0.0010752451,0.0017523479,0.0010237512,0.008112699,0.0005916397,0.00009030097],"category_scores_gemma":[0.009967267,0.00059226004,0.0011030362,0.0064635337,0.0013967373,0.0009787739,0.002314346,0.005035572,0.00007515625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002580581,0.00095787755,0.00034438912,0.00030134464,0.0003539041,0.000038805243,0.02908596,0.19068907,0.015717033,0.4715668,0.0011362053,0.28955057],"study_design_scores_gemma":[0.00007631307,0.0018123465,0.00011419977,0.0025082955,0.00027311422,0.00008607313,0.012445121,0.43840832,0.33192053,0.20667748,0.0051444257,0.0005337747],"about_ca_topic_score_codex":0.0023215506,"about_ca_topic_score_gemma":0.00028855834,"teacher_disagreement_score":0.879808,"about_ca_system_score_codex":0.00049730705,"about_ca_system_score_gemma":0.004670797,"threshold_uncertainty_score":0.99965286},"labels":[],"label_agreement":null},{"id":"W7153895348","doi":"10.1145/3772318.3808890","title":"10.1145/3772318.3808890","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Component (thermodynamics); Key (lock); Training (meteorology)","score_opus":0.01015365149003846,"score_gpt":0.1978542969357854,"score_spread":0.18770064544574694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7153895348","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066273904,0.00004394281,0.0013928491,0.0012854242,0.000010773707,0.00019764325,0.0000021048265,0.00040970463,0.9959948],"genre_scores_gemma":[0.0011241733,4.882535e-7,0.0035652313,0.00030988565,0.0001094632,0.00002244773,0.0000018737802,0.000016337042,0.9948501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846226,0.00005745725,0.0002447804,0.00044891748,0.0002971749,0.0004894054],"domain_scores_gemma":[0.99874985,0.00007967288,0.0000319818,0.0008278653,0.00008239084,0.00022820964],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026405873,0.00016408491,0.0001644622,0.00011315594,0.00015421794,0.00021406726,0.0012734245,0.00006161362,0.9575798],"category_scores_gemma":[0.00005270407,0.00016690174,0.00006649675,0.0006730649,0.000039169103,0.00052726816,0.00017274384,0.00010950444,0.9919852],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013864594,0.000051470066,1.7751184e-7,0.0000024556443,0.0000065823956,0.000024903567,0.00010020169,0.0006806419,0.00021602503,0.00044732195,0.08019934,0.918257],"study_design_scores_gemma":[0.000043398963,0.000145154,0.000010500244,0.000010451922,0.000002917612,0.0000116116025,0.0000016932299,0.012911549,0.0033987982,0.0003556974,0.9828869,0.00022129255],"about_ca_topic_score_codex":0.00006794763,"about_ca_topic_score_gemma":7.1631524e-7,"teacher_disagreement_score":0.91803575,"about_ca_system_score_codex":0.00005488648,"about_ca_system_score_gemma":0.00005238875,"threshold_uncertainty_score":0.68060553},"labels":[],"label_agreement":null},{"id":"W7154007040","doi":"10.1145/3772318.3809007","title":"10.1145/3772318.3809007","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); User interface; Interface (matter); Component (thermodynamics)","score_opus":0.01031343120523157,"score_gpt":0.19993620169338663,"score_spread":0.18962277048815507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154007040","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006607244,0.000043230393,0.0016493438,0.0011354309,0.000010783396,0.00019586385,0.0000020228604,0.0004089964,0.9958936],"genre_scores_gemma":[0.0010257505,4.619849e-7,0.0038405203,0.00031618576,0.00010946093,0.000020933949,0.0000018496679,0.00001633486,0.9946685],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984617,0.000055526085,0.0002450417,0.00044500176,0.00029789572,0.00049482123],"domain_scores_gemma":[0.9987526,0.00008270747,0.000031876425,0.00081742246,0.000083565596,0.00023181307],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027853652,0.00016296827,0.00016243695,0.000116832154,0.00015227564,0.00020486632,0.00125312,0.00006267083,0.9560151],"category_scores_gemma":[0.00005371647,0.00016601042,0.00006597028,0.000680458,0.000039314145,0.0005174612,0.0001719352,0.000110405555,0.9921975],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014348847,0.0000506413,1.974804e-7,0.0000024792591,0.0000065050135,0.000025962501,0.00009658537,0.0006830112,0.00022260284,0.00043477395,0.073908,0.9245549],"study_design_scores_gemma":[0.000042871357,0.0001419842,0.000011666387,0.000010282185,0.000002835006,0.000011618612,0.0000017245465,0.012423585,0.0036458522,0.00035350796,0.98313403,0.00022003955],"about_ca_topic_score_codex":0.000067537345,"about_ca_topic_score_gemma":7.060477e-7,"teacher_disagreement_score":0.9243348,"about_ca_system_score_codex":0.00005540926,"about_ca_system_score_gemma":0.000050110666,"threshold_uncertainty_score":0.67697084},"labels":[],"label_agreement":null},{"id":"W7154013659","doi":"10.1145/3772318.3808889","title":"10.1145/3772318.3808889","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.010157990412153917,"score_gpt":0.19788962397169468,"score_spread":0.18773163355954076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154013659","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006785135,0.000044141852,0.0013746123,0.0012612768,0.000010767844,0.0001975155,0.0000021048183,0.00040955917,0.9960215],"genre_scores_gemma":[0.0011220957,4.8478535e-7,0.003560827,0.00030959104,0.00010927127,0.000022447733,0.0000018758429,0.000016315053,0.9948571],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846405,0.00005744383,0.00024459744,0.00044831575,0.00029682304,0.0004887702],"domain_scores_gemma":[0.99875206,0.00007964196,0.000031959353,0.000826001,0.0000823348,0.00022800783],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026362244,0.00016395666,0.00016429629,0.00011306454,0.00015417772,0.00021389981,0.001271841,0.00006157094,0.95908695],"category_scores_gemma":[0.00005261899,0.00016679525,0.000066461456,0.0006722535,0.00003916773,0.00052690785,0.0001724711,0.00010941126,0.99200994],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013785266,0.000051277762,1.7853857e-7,0.0000024407036,0.000006552622,0.000024788727,0.00009786191,0.0006769652,0.0002161869,0.00044432931,0.07801986,0.9204458],"study_design_scores_gemma":[0.000043335684,0.00014512335,0.000010738219,0.000010421525,0.0000029158848,0.000011610513,0.0000016614827,0.01282229,0.0033949194,0.0003491653,0.9829866,0.00022116002],"about_ca_topic_score_codex":0.00006792205,"about_ca_topic_score_gemma":7.1472124e-7,"teacher_disagreement_score":0.9202246,"about_ca_system_score_codex":0.000054875523,"about_ca_system_score_gemma":0.00005235487,"threshold_uncertainty_score":0.68017125},"labels":[],"label_agreement":null},{"id":"W7154039155","doi":"10.1145/3772318.3809003","title":"10.1145/3772318.3809003","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Component (thermodynamics); Session key; Attendance","score_opus":0.01004772885008773,"score_gpt":0.19735999020170159,"score_spread":0.18731226135161386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154039155","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006424665,0.000044136297,0.0013874851,0.0012057489,0.000011082096,0.0002000595,0.00000205028,0.00039244923,0.9961145],"genre_scores_gemma":[0.0009783191,4.7824625e-7,0.0037357062,0.0003203213,0.000100726174,0.00002276424,0.0000018144557,0.000016331815,0.9948235],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846846,0.000059970072,0.00024327823,0.0004469824,0.00029385305,0.00048745022],"domain_scores_gemma":[0.99875563,0.00007740744,0.00003184804,0.00082380907,0.00008387478,0.00022741767],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026708757,0.00016362338,0.00016371823,0.00011136581,0.00015340706,0.00021180077,0.0012385577,0.000061428,0.95756066],"category_scores_gemma":[0.000055667646,0.00016655089,0.0000650423,0.0006907291,0.000038817187,0.00052052265,0.00016353963,0.00010863309,0.9921845],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013569233,0.000052511557,1.8770196e-7,0.0000025195602,0.00000673452,0.000024879944,0.00009739877,0.00067986513,0.0002130872,0.00047562373,0.08691023,0.9115234],"study_design_scores_gemma":[0.000043293418,0.00014331733,0.000010038512,0.0000100741145,0.0000029087696,0.000011621468,0.0000016719937,0.011915635,0.0034425438,0.00036616775,0.9838318,0.00022089825],"about_ca_topic_score_codex":0.0000623453,"about_ca_topic_score_gemma":6.544701e-7,"teacher_disagreement_score":0.9113025,"about_ca_system_score_codex":0.000054390246,"about_ca_system_score_gemma":0.000053525833,"threshold_uncertainty_score":0.67917484},"labels":[],"label_agreement":null},{"id":"W7154151203","doi":"10.1145/3772318.3809054","title":"10.1145/3772318.3809054","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Personalization; Component (thermodynamics); Key (lock)","score_opus":0.0102177920855491,"score_gpt":0.19793756099147972,"score_spread":0.18771976890593062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154151203","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006551736,0.000043396114,0.0013792109,0.0012889876,0.000010749035,0.00019761448,0.0000021084616,0.0004090461,0.9960137],"genre_scores_gemma":[0.0011375075,4.870503e-7,0.0035084593,0.0003128543,0.00010919068,0.000022527513,0.0000018859945,0.000016366743,0.99489075],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846315,0.00005774838,0.00024443667,0.00044887068,0.00029682377,0.00048895646],"domain_scores_gemma":[0.9987478,0.00008218872,0.00003197577,0.0008276056,0.00008218588,0.00022819174],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002629864,0.00016396717,0.00016436043,0.00011357554,0.00015432165,0.00021873992,0.0012914108,0.00006146493,0.9586604],"category_scores_gemma":[0.000054272037,0.00016681064,0.0000664884,0.0006772676,0.000039397077,0.0005374404,0.00017614292,0.00010929114,0.992269],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013722309,0.000050839608,1.7822056e-7,0.0000024499193,0.0000065133004,0.00002464366,0.0000978629,0.0006649373,0.0002035449,0.00043647978,0.08157475,0.91692406],"study_design_scores_gemma":[0.000043238342,0.00014332925,0.000011007034,0.000010245136,0.0000029138796,0.0000117258305,0.0000016631,0.012782976,0.0033363795,0.00036223338,0.98307306,0.00022123106],"about_ca_topic_score_codex":0.00006711161,"about_ca_topic_score_gemma":7.0037976e-7,"teacher_disagreement_score":0.91670287,"about_ca_system_score_codex":0.00005500772,"about_ca_system_score_gemma":0.000054050684,"threshold_uncertainty_score":0.6802341},"labels":[],"label_agreement":null},{"id":"W7154168698","doi":"10.1145/3772318.3808976","title":"10.1145/3772318.3808976","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Component (thermodynamics); Key (lock); Training (meteorology)","score_opus":0.0102177920855491,"score_gpt":0.19793756099147972,"score_spread":0.18771976890593062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154168698","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006473311,0.000043639182,0.0013781934,0.0012735897,0.000010636449,0.00019745273,0.0000020782895,0.00040907424,0.996038],"genre_scores_gemma":[0.0011240507,4.8525686e-7,0.0035656039,0.00030926065,0.00010938894,0.000022459537,0.0000018604549,0.000016317266,0.9948506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984628,0.000057433743,0.0002446595,0.00044871977,0.00029708806,0.00048929465],"domain_scores_gemma":[0.9987503,0.0000796682,0.000031979296,0.000827444,0.00008237311,0.00022820408],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002637353,0.00016404704,0.00016431282,0.00011309846,0.00015451654,0.00021391062,0.0012741851,0.00006162467,0.9587592],"category_scores_gemma":[0.000052625346,0.00016687013,0.0000664692,0.00067255105,0.000039164617,0.0005266694,0.00017282856,0.00010946828,0.9921706],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001383464,0.0000513658,1.7325458e-7,0.0000024561584,0.0000065653335,0.000024651477,0.00010083451,0.0006673168,0.00021896766,0.0004328455,0.082064144,0.9164168],"study_design_scores_gemma":[0.00004335468,0.00014529025,0.000010294831,0.000010554476,0.000002896778,0.000011645836,0.000001698952,0.013154701,0.0034075554,0.0003580118,0.98263276,0.00022124487],"about_ca_topic_score_codex":0.00006714277,"about_ca_topic_score_gemma":6.846374e-7,"teacher_disagreement_score":0.9161956,"about_ca_system_score_codex":0.000054774424,"about_ca_system_score_gemma":0.000052388546,"threshold_uncertainty_score":0.6804766},"labels":[],"label_agreement":null},{"id":"W7154179099","doi":"10.1145/3772318.3809093","title":"10.1145/3772318.3809093","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Generative grammar; Generative model; Key (lock)","score_opus":0.0102177920855491,"score_gpt":0.19793756099147972,"score_spread":0.18771976890593062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154179099","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062140555,0.000042980362,0.0013591208,0.0012728883,0.000010713307,0.00019600525,0.0000020880736,0.00040711468,0.9960877],"genre_scores_gemma":[0.0010534769,4.8185626e-7,0.003572105,0.00030960466,0.00010563036,0.00002244289,0.0000018695266,0.000016332397,0.99491805],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984627,0.000057774745,0.00024456158,0.00044855432,0.00029750174,0.00048894587],"domain_scores_gemma":[0.9987506,0.00007965125,0.000031977237,0.00082705414,0.00008264612,0.0002280318],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026281166,0.00016409672,0.00016445927,0.00011298424,0.00015337772,0.0002127901,0.0012719225,0.000061144456,0.9567596],"category_scores_gemma":[0.000052217416,0.00016684497,0.000066506145,0.0006735291,0.00003914329,0.0005256508,0.0001726434,0.000109437235,0.9925628],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014067266,0.000052464886,1.869358e-7,0.0000025140193,0.000006700628,0.000025316294,0.00009998774,0.00069357624,0.0002102655,0.0004805447,0.08278594,0.91562843],"study_design_scores_gemma":[0.0000433707,0.00014523564,0.000011224333,0.000010403836,0.0000029247217,0.000011763001,0.0000017008308,0.012637083,0.0033313767,0.0003588208,0.98322463,0.0002214578],"about_ca_topic_score_codex":0.00006807359,"about_ca_topic_score_gemma":6.714507e-7,"teacher_disagreement_score":0.915407,"about_ca_system_score_codex":0.000054820808,"about_ca_system_score_gemma":0.000051984458,"threshold_uncertainty_score":0.680374},"labels":[],"label_agreement":null},{"id":"W7154187481","doi":"10.1145/3772318.3808938","title":"10.1145/3772318.3808938","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Agency (philosophy); Control (management); Conversation analysis","score_opus":0.01019186479669566,"score_gpt":0.19793436628715833,"score_spread":0.18774250149046268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154187481","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008060626,0.00003647467,0.0013721051,0.001285922,0.000010792959,0.00019795813,0.0000021580793,0.0004104609,0.99587804],"genre_scores_gemma":[0.0009639568,4.774481e-7,0.0042329803,0.00031300852,0.00010811324,0.000022017504,0.0000019059427,0.00001631194,0.99434125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846476,0.000057327652,0.00024424016,0.00044823167,0.00029659475,0.00048885174],"domain_scores_gemma":[0.9987527,0.000079370155,0.00003193395,0.00082581467,0.000082185485,0.00022797848],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002625192,0.00016396548,0.00016417868,0.00011275711,0.00015334733,0.00021397298,0.0012720342,0.00006157708,0.9573405],"category_scores_gemma":[0.000052450407,0.00016681077,0.00006642981,0.0006702845,0.000039069637,0.00052682654,0.0001726414,0.00010940061,0.99206036],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015085861,0.00005085153,1.7551315e-7,0.0000024231067,0.0000065726726,0.000024730165,0.00010440837,0.00067407824,0.00024319912,0.00043617425,0.078984134,0.91945815],"study_design_scores_gemma":[0.00004697808,0.00014899645,0.000009576633,0.000010373715,0.0000029002351,0.000011720521,0.0000017074681,0.01580545,0.0032581969,0.00035718293,0.9801259,0.00022098506],"about_ca_topic_score_codex":0.00006689753,"about_ca_topic_score_gemma":7.977316e-7,"teacher_disagreement_score":0.9192372,"about_ca_system_score_codex":0.00005482213,"about_ca_system_score_gemma":0.00005222798,"threshold_uncertainty_score":0.68023455},"labels":[],"label_agreement":null},{"id":"W7154513624","doi":"10.1109/amcai66110.2025.11474378","title":"Uncertainty Aware Tri-Modal Fusion with Faithful Explainability for Five-Stage Alzheimer's Disease Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sensor fusion; Pattern recognition (psychology); Fusion; Feature (linguistics); Disease","score_opus":0.05141286173734849,"score_gpt":0.3249236268883966,"score_spread":0.2735107651510481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154513624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040274363,0.0008265134,0.9328112,0.01565931,0.0012802474,0.005526081,0.00017985115,0.00046402653,0.0029783885],"genre_scores_gemma":[0.9808343,0.000104836865,0.0071898275,0.0011196225,0.00018014768,0.0010753557,0.00009552126,0.000049913444,0.009350446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924009,0.0005473013,0.0015134239,0.002937444,0.0009905336,0.0016104254],"domain_scores_gemma":[0.9921079,0.0012293131,0.00056293537,0.003186705,0.0020938069,0.0008193183],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017696928,0.00093970174,0.0008403429,0.0005346337,0.0018668108,0.0010899372,0.0025269631,0.00036713047,0.00036462877],"category_scores_gemma":[0.00077801605,0.00082290295,0.00046923652,0.0025846476,0.00077716063,0.0021391416,0.0008157188,0.00052648433,0.00011240705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005266926,0.0026166558,0.0058448515,0.00092731684,0.00042660732,0.000078702906,0.003653542,0.052685488,0.0005229302,0.6381939,0.0048174923,0.28496557],"study_design_scores_gemma":[0.0010305269,0.00075762375,0.005095204,0.00033377905,0.00033428843,0.0000014628577,0.0051879887,0.9490748,0.00635137,0.0154914595,0.015304235,0.0010372275],"about_ca_topic_score_codex":0.0012760692,"about_ca_topic_score_gemma":0.0010462448,"teacher_disagreement_score":0.94056,"about_ca_system_score_codex":0.0007702284,"about_ca_system_score_gemma":0.0029192565,"threshold_uncertainty_score":0.999947},"labels":[],"label_agreement":null},{"id":"W7160191965","doi":"10.1109/iccv51701.2025.02250","title":"SIC: Similarity-Based Interpretable Image Classification with Neural Networks","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial neural network; Pattern recognition (psychology); Contextual image classification; Feature (linguistics); Image (mathematics); Image processing","score_opus":0.022572401664415064,"score_gpt":0.2823163670605541,"score_spread":0.25974396539613903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160191965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023885558,0.0002818357,0.9372429,0.012423873,0.0014258776,0.0008893967,0.0000036280746,0.00040657216,0.04493732],"genre_scores_gemma":[0.9569063,0.000026773641,0.03162132,0.0062330896,0.000120982586,0.000087537184,0.000012100098,0.000035762383,0.0049561374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495655,0.000435873,0.001030942,0.0016467232,0.00059039757,0.0013394945],"domain_scores_gemma":[0.99563926,0.0005809669,0.00033544766,0.0022434546,0.00090576767,0.00029510347],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009798832,0.00064683915,0.00058322743,0.00046563894,0.00078936416,0.0022135314,0.0024575945,0.00032698206,0.00045760706],"category_scores_gemma":[0.00018017323,0.0005827232,0.00021541794,0.003316633,0.0006470243,0.0022625825,0.0005766626,0.0009290846,0.00018005655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007700629,0.0015032792,0.0042527546,0.00033645393,0.00024039313,0.00027267024,0.0011335338,0.3322639,0.0037490088,0.41898233,0.01289562,0.22360002],"study_design_scores_gemma":[0.00031408187,0.00038002848,0.00077479484,0.00024051749,0.00007467473,0.000004826709,0.0004069409,0.98102725,0.011616858,0.0018929447,0.0026602286,0.00060688757],"about_ca_topic_score_codex":0.00044539766,"about_ca_topic_score_gemma":0.0005252782,"teacher_disagreement_score":0.9545177,"about_ca_system_score_codex":0.00033393104,"about_ca_system_score_gemma":0.00072051375,"threshold_uncertainty_score":0.9996624},"labels":[],"label_agreement":null},{"id":"W7160819649","doi":"10.66372/jger.v3i1.4","title":"Evaluating the Quality of Large Language Model-Generated Explanations in Recommendation Tasks: A Multi-Dimensional Comparative Analysis","year":2025,"lang":"","type":"article","venue":"Journal of Global Engineering Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality (philosophy); Annotation; Natural language; Recommender system; Language model","score_opus":0.1448898721347533,"score_gpt":0.4794434752699744,"score_spread":0.3345536031352211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160819649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071060285,0.07356106,0.8516451,0.0026594407,0.0004127714,0.0004976654,0.000072170995,0.000013207322,0.00007828501],"genre_scores_gemma":[0.9605001,0.0035952958,0.035341047,0.00048104717,0.000028403347,0.000013008249,0.000012814588,0.000004467425,0.00002379014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99534124,0.00081682095,0.0025980992,0.00029147655,0.0006125495,0.00033979834],"domain_scores_gemma":[0.99639064,0.0005128229,0.0013740812,0.00043696334,0.0011960077,0.000089481466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007907164,0.00026114675,0.0011504637,0.0003304569,0.00011824328,0.00008252749,0.0008001577,0.0000788588,0.00005113778],"category_scores_gemma":[0.0018732976,0.00020656727,0.00046446957,0.005852523,0.000036563062,0.0005371322,0.00020134954,0.0004388655,0.0000041922917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020555388,0.00026994135,0.00025614997,0.0005855627,0.0005686917,0.0000050329295,0.000728571,0.978587,0.0012450234,0.010054293,0.00017627637,0.007502944],"study_design_scores_gemma":[0.0002991604,0.00007525106,0.0016502923,0.0031987505,0.00050666986,0.000006013388,0.00019829784,0.9932262,0.00049001264,0.00009101983,0.00010025302,0.00015813367],"about_ca_topic_score_codex":0.00014771709,"about_ca_topic_score_gemma":0.00031938334,"teacher_disagreement_score":0.8894398,"about_ca_system_score_codex":0.0005641965,"about_ca_system_score_gemma":0.0005514522,"threshold_uncertainty_score":0.8423569},"labels":[],"label_agreement":null},{"id":"W7165533022","doi":"10.25163/engineering.2110817","title":"Interpretable AI in EHR-Based Clinical Decision Support: A Scoping Review of Models, Methods, and Trends","year":2024,"lang":"","type":"article","venue":"Applied IT & Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Webster University","keywords":"Interpretability; Random forest; Clinical decision support system; Decision tree; Logistic regression; Closing (real estate); Health informatics; Sample (material); Domain (mathematical analysis)","score_opus":0.059665147258468235,"score_gpt":0.4198410829038592,"score_spread":0.36017593564539097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7165533022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037560015,0.08024248,0.91584665,0.0005368842,0.00097480055,0.000599831,0.0000038771714,0.00015070497,0.0012692118],"genre_scores_gemma":[0.5221668,0.036885425,0.43889055,0.0015551222,0.00014754076,0.00017730106,0.0000065911827,0.00010212406,0.000068577996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946597,0.00014347676,0.0025806786,0.0013085874,0.0005058217,0.0008017063],"domain_scores_gemma":[0.9964275,0.0019828104,0.00019842428,0.0009989745,0.000113248454,0.00027906752],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0064171143,0.0005029781,0.0012526144,0.00090349856,0.000057894787,0.00035784635,0.0009203681,0.00027284573,0.00020821745],"category_scores_gemma":[0.00046841055,0.00053753395,0.00027010308,0.002735196,0.00010761114,0.00089477387,0.00063389784,0.00091277814,0.000031123902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028668972,0.000095850424,0.0000050306758,0.0139045045,0.000044367916,0.00006331468,0.0006426272,0.084112346,0.0020485783,0.025727957,0.0003678023,0.87295896],"study_design_scores_gemma":[0.00014733397,0.00011632782,0.000007882209,0.12607867,0.000055383873,0.0000090672465,0.000025732726,0.86498094,0.0057045715,0.0013536497,0.0011038425,0.0004166266],"about_ca_topic_score_codex":0.000037900656,"about_ca_topic_score_gemma":0.000018266917,"teacher_disagreement_score":0.8725423,"about_ca_system_score_codex":0.00013172776,"about_ca_system_score_gemma":0.00039387043,"threshold_uncertainty_score":0.99970764},"labels":[],"label_agreement":null}]}