{"meta":{"query_hash":"9bc908a09f7e","filters":{"venue":"ITC 2016 Conference"},"cohort_total":23,"direct_labels_cover":0,"predictions_cover":23,"exported":23,"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/9bc908a09f7e","api":"https://metacan.xera.ac/api/v1/cohort?venue=ITC+2016+Conference"},"results":[{"id":"W2467740042","doi":"","title":"PAPER: The Power and Potential of Psychological Assessment Around the World -- Rethinking Traditional Paradigms","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Educational and Psychological Assessments","field":"Psychology","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":"Presentation (obstetrics); Sine qua non; Transformative learning; Psychology; Process (computing); Public relations; Engineering ethics; Power (physics); Political science; Computer science; Engineering; Pedagogy; Medicine","score_opus":0.10710727184053166,"score_gpt":0.38994936403258673,"score_spread":0.2828420921920551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467740042","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":[0.76517844,0.00023407806,0.002039354,0.052508377,0.0017704159,0.00035333209,0.00007578848,0.0000363122,0.17780393],"genre_scores_gemma":[0.9900266,0.00006268856,0.0002731716,0.002237374,0.00025893192,0.00009398778,0.0000063150333,0.000008592267,0.0070323716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99823785,0.0003676187,0.00034790838,0.0004126683,0.0003473847,0.00028655858],"domain_scores_gemma":[0.9981272,0.0010451784,0.00019329702,0.00045734431,0.00009471196,0.000082244784],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000608953,0.00017451895,0.00018545908,0.000038715367,0.00020570241,0.000055736473,0.0005113199,0.00010676382,0.012773966],"category_scores_gemma":[0.0000296993,0.00006777656,0.000087084154,0.00012639613,0.00071834517,0.00011511193,0.00005521597,0.0002911604,0.00013599025],"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":[0.00011558595,0.00057652313,0.017693436,0.000003275623,0.00011217457,0.00000896262,0.0005198269,3.3044122e-7,0.0035573621,0.93754953,0.024707822,0.0151551515],"study_design_scores_gemma":[0.0005685475,0.00019712278,0.7977884,0.000050667986,0.000021623122,0.00005365859,0.0003128928,0.0000023704608,0.000014791487,0.18359368,0.017259998,0.00013629989],"about_ca_topic_score_codex":0.000022597871,"about_ca_topic_score_gemma":0.000010901266,"teacher_disagreement_score":0.7800949,"about_ca_system_score_codex":0.000020603307,"about_ca_system_score_gemma":0.000055764383,"threshold_uncertainty_score":0.9881285},"labels":[],"label_agreement":null},{"id":"W2477167192","doi":"","title":"POSTER: Bayesian Estimation of the Polychoric Correlation Coefficient with Skewed and Sparse Data","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Advanced Statistical Modeling Techniques","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":"Polychoric correlation; Statistics; Skewness; Mathematics; Econometrics; Bayesian probability; Contingency table; Correlation; Sample size determination; Population; Data set","score_opus":0.0324205745307385,"score_gpt":0.2770568380063151,"score_spread":0.2446362634755766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2477167192","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":[0.0020847055,0.000022890365,0.99594736,0.0012964002,0.00008188389,0.00019052021,0.000033228727,0.000081939215,0.00026105242],"genre_scores_gemma":[0.8274838,0.0000122056745,0.17234491,0.000038183676,0.0000052148516,0.000004482673,0.0000023037335,0.000004431458,0.00010449353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990964,0.000052706437,0.0001766614,0.00032356038,0.00021718594,0.00013350534],"domain_scores_gemma":[0.9984867,0.00019821094,0.00014130687,0.0010084749,0.00011701691,0.00004830529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015490972,0.00009511618,0.0001062367,0.000036482088,0.00006070968,0.000037879814,0.0008159645,0.00003520627,0.0000062064237],"category_scores_gemma":[0.00018331075,0.00004747151,0.0000078835365,0.00012827097,0.0001525042,0.00042862078,0.00040752313,0.000055205997,0.000005405722],"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":[0.000049214665,0.00007194674,0.0017026775,0.000023220127,0.000012320029,0.00000299919,0.0002709144,0.0004050612,0.0033325716,0.32029715,0.00064840046,0.6731835],"study_design_scores_gemma":[0.00031524003,0.000137286,0.0050512273,0.0003338811,0.000011075913,0.000014266805,0.0000034480581,0.9520726,0.0023695277,0.039414153,0.0001247299,0.00015252366],"about_ca_topic_score_codex":0.000026234215,"about_ca_topic_score_gemma":0.000012199986,"teacher_disagreement_score":0.9516676,"about_ca_system_score_codex":0.000018796894,"about_ca_system_score_gemma":0.0000979525,"threshold_uncertainty_score":0.19358319},"labels":[],"label_agreement":null},{"id":"W2490078899","doi":"","title":"SYMPOSIUM: The Validity of Testing: Perceptions of Stakeholders","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","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":"Perception; Psychology; Computer science","score_opus":0.24014471523629496,"score_gpt":0.3671960779230274,"score_spread":0.12705136268673242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490078899","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":[0.8165427,0.000012580697,0.0014276658,0.004427387,0.00025926254,0.00023882109,0.000024655445,0.000031849464,0.17703508],"genre_scores_gemma":[0.99355185,0.0001492319,0.00017996063,0.000019342366,0.00007338949,0.0000073423034,4.0409554e-7,0.000003753814,0.006014707],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901444,0.00015130415,0.00018366071,0.00012326491,0.00034924617,0.00017809779],"domain_scores_gemma":[0.99864423,0.0006396754,0.0001519098,0.00020533342,0.00031140738,0.000047428268],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005381899,0.00006789997,0.00012437049,0.000028352742,0.00017384582,0.000020881147,0.00041813514,0.00004697196,0.0011245683],"category_scores_gemma":[0.0002634643,0.000036545793,0.000052589494,0.00015124667,0.0006907726,0.00013301933,0.000052324427,0.00004369314,0.000055898894],"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":[0.000011075261,0.00013286382,0.7741662,0.0000148019135,0.000033000502,5.3833816e-7,0.011980481,6.834846e-7,0.1389858,0.05503018,0.0072473176,0.012397032],"study_design_scores_gemma":[0.0011449053,0.0003679672,0.924099,0.0004862216,0.00012499465,7.959905e-7,0.037971415,0.000027661248,0.0046740267,0.010088572,0.02055263,0.00046180698],"about_ca_topic_score_codex":0.0009855132,"about_ca_topic_score_gemma":0.0003486647,"teacher_disagreement_score":0.17700918,"about_ca_system_score_codex":0.000024885823,"about_ca_system_score_gemma":0.00030554834,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W2498349618","doi":"","title":"POSTER: Detecting Differential Item Functioning: A Comparison of Two Effect Size Measures in Logistic Regression Analysis","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Mental Health Research Topics","field":"Psychology","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":"Differential item functioning; Juvenile delinquency; Psychology; Context (archaeology); Logistic regression; Neighbourhood (mathematics); Odds; Scale (ratio); Statistics; Social psychology; Item response theory; Developmental psychology; Psychometrics; Mathematics; Geography","score_opus":0.16116164982751477,"score_gpt":0.4685125216579524,"score_spread":0.30735087183043763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498349618","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":[0.9886867,0.00022612618,0.007092237,0.00017776867,0.00047750527,0.0003843427,0.000015780499,0.000043387357,0.0028961445],"genre_scores_gemma":[0.99812275,0.000012105464,0.000050719547,0.000015101351,0.00007281834,0.000060704773,0.0000045834227,0.000014251176,0.00164696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99694526,0.001021336,0.00060956477,0.00046434507,0.0004476268,0.0005118434],"domain_scores_gemma":[0.9962847,0.0025704338,0.00031939804,0.0005176351,0.00014890217,0.00015893253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007411567,0.0002040222,0.00060264464,0.000331995,0.000088836845,0.00002673059,0.0003025283,0.00014090698,0.002977445],"category_scores_gemma":[0.0011249953,0.00012517645,0.00012212331,0.00041952814,0.0001546767,0.000071723836,0.00011728821,0.0002780403,0.00021603824],"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":[0.00071858737,0.00015039624,0.7976173,0.00007782305,0.0001506472,0.000011869842,0.0004809309,0.0000016230833,0.02206213,0.00035803096,0.00010157583,0.17826909],"study_design_scores_gemma":[0.0046776654,0.0012994757,0.97310376,0.0010078736,0.00023929373,0.0000066996754,0.00025123247,0.00095842377,0.01754766,0.0003257336,0.00021986541,0.0003623009],"about_ca_topic_score_codex":0.0014587368,"about_ca_topic_score_gemma":0.0013387813,"teacher_disagreement_score":0.17790678,"about_ca_system_score_codex":0.00013341676,"about_ca_system_score_gemma":0.000080754915,"threshold_uncertainty_score":0.997934},"labels":[],"label_agreement":null},{"id":"W2546985950","doi":"","title":"PAPER: Making Sense of the Gender Gap in Reading on the PISA 2009","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"School Choice and Performance","field":"Social Sciences","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":"Gender gap; Reading (process); Psychology; Socioeconomic status; Set (abstract data type); Latent class model; Developmental psychology; Scale (ratio); Demography; Statistics; Geography; Mathematics; Population; Computer science; Political science","score_opus":0.1094491655318233,"score_gpt":0.3346620453961246,"score_spread":0.2252128798643013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546985950","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":[0.7238502,0.00008133961,0.000052493095,0.012964445,0.0003722841,0.00020222025,0.00000934002,0.000022326694,0.2624454],"genre_scores_gemma":[0.99475026,0.00024797916,0.000013886507,0.00094385777,0.00018243291,0.000007927142,7.007127e-8,0.000004726196,0.003848876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99893445,0.00021783168,0.00015213272,0.00014448127,0.00029767113,0.00025343886],"domain_scores_gemma":[0.9990359,0.0004607016,0.00010030059,0.0003025009,0.00007053083,0.000030058314],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007727345,0.00007725752,0.0000924558,0.00002932634,0.00021418344,0.000033286655,0.0003564747,0.00006485399,0.0010402002],"category_scores_gemma":[0.0004110332,0.00003343193,0.000040385978,0.00016878155,0.00022028877,0.0001841836,0.000045241057,0.00012248867,0.00017623292],"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":[0.00011993412,0.000092574825,0.32432804,0.00003118202,0.00003406244,0.000009837868,0.029106218,0.000009353528,0.032683145,0.5041266,0.037046563,0.07241249],"study_design_scores_gemma":[0.0011894569,0.0000969508,0.579034,0.0027366618,0.000030050502,0.0000053047543,0.009877698,0.00010684316,0.010512296,0.04535957,0.35029683,0.00075435865],"about_ca_topic_score_codex":0.00077134836,"about_ca_topic_score_gemma":0.0022857105,"teacher_disagreement_score":0.45876706,"about_ca_system_score_codex":0.000043792064,"about_ca_system_score_gemma":0.0002230065,"threshold_uncertainty_score":0.999873},"labels":[],"label_agreement":null},{"id":"W2547516676","doi":"","title":"POSTER: Enhancements of Simulated Science Laboratory Assessments","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Innovative Teaching and Learning Methods","field":"Psychology","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; University of Calgary","funders":"","keywords":"Intervention (counseling); Computer science; Mathematics education; Psychology","score_opus":0.06923889265197267,"score_gpt":0.45057729212756237,"score_spread":0.3813383994755897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547516676","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":[0.89992386,0.000033375563,0.034511622,0.00014517063,0.0009340897,0.00012467688,0.000025226034,0.00007188531,0.06423008],"genre_scores_gemma":[0.99111116,0.0000036155104,0.0012435337,0.00012938901,0.000038984737,0.0000056238314,0.0000013854092,0.000013353803,0.0074529266],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9981074,0.00050407485,0.00030890974,0.00039674106,0.00031541198,0.0003675055],"domain_scores_gemma":[0.9982319,0.00024612324,0.00026265948,0.0005019039,0.000687219,0.00007022844],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002053995,0.00014167205,0.00020599723,0.00019594825,0.00011044791,0.000021516786,0.00047466517,0.00007800115,0.0027480477],"category_scores_gemma":[0.00037132978,0.00009421947,0.000025842146,0.0004563478,0.0005291723,0.00020392778,0.00009121605,0.00016528275,0.00050549675],"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":[0.00009355276,0.00015115707,0.06502398,0.000009488851,0.00005136681,0.0000052642563,0.0009624665,5.1316783e-7,0.8162204,0.013043726,0.00059154065,0.10384651],"study_design_scores_gemma":[0.0040735644,0.0012024712,0.6859627,0.00085035304,0.00004242998,0.000005462348,0.00036378906,0.00006261855,0.27033862,0.0025446333,0.03369269,0.0008607043],"about_ca_topic_score_codex":0.00007995015,"about_ca_topic_score_gemma":8.1186835e-7,"teacher_disagreement_score":0.6209387,"about_ca_system_score_codex":0.00005614777,"about_ca_system_score_gemma":0.00034246547,"threshold_uncertainty_score":0.9981636},"labels":[],"label_agreement":null},{"id":"W2555581813","doi":"","title":"POSTER: Factor Structure, Wording Effects, and Reliability Estimates in Health and Housing Specific Self-efficacy Scales with Individuals who are Homeless or Vulnerably Housed","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Homelessness and Social Issues","field":"Health Professions","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":"Polychoric correlation; Exploratory factor analysis; Confirmatory factor analysis; Likert scale; Psychology; Ordinal Scale; Structural equation modeling; Ordinal data; Scale (ratio); Factor analysis; Internal consistency; Statistics; Psychometrics; Competence (human resources); Clinical psychology; Econometrics; Mathematics; Social psychology; Developmental psychology; Correlation","score_opus":0.04124889507717,"score_gpt":0.35342926676075886,"score_spread":0.31218037168358886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555581813","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":[0.99628365,0.0011135736,0.00036171448,0.00056808273,0.00015837885,0.0011480208,0.00014556579,0.00017300811,0.00004801073],"genre_scores_gemma":[0.9970917,0.0019124141,0.0006466982,0.00008340127,0.00010419994,0.000045705954,0.000004977817,0.00004826742,0.000062597406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99708235,0.0007443454,0.00056274375,0.00061878713,0.00026339907,0.00072838395],"domain_scores_gemma":[0.99634683,0.0024087604,0.00041495598,0.0003346786,0.00016314254,0.00033160317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048801408,0.0003445077,0.0011752659,0.00014922742,0.00065532664,0.000096903605,0.00018380786,0.00025206248,0.00007914889],"category_scores_gemma":[0.0003385223,0.00019221359,0.000022509903,0.00020847819,0.00023713302,0.00033467766,0.00016040615,0.0004321899,0.000008543738],"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":[0.00014694889,0.00006533395,0.9530087,0.0012648044,0.000018975099,0.000010888436,0.014730974,4.0150093e-7,0.00021977648,0.00029457588,0.000013198344,0.030225432],"study_design_scores_gemma":[0.0032411902,0.00022590141,0.98124135,0.007532658,0.000010069105,8.103326e-7,0.0063141636,0.000014333602,0.00026689563,0.00044779712,0.0003140407,0.00039080487],"about_ca_topic_score_codex":0.00073060393,"about_ca_topic_score_gemma":0.0036862302,"teacher_disagreement_score":0.029834626,"about_ca_system_score_codex":0.00016904972,"about_ca_system_score_gemma":0.00045053742,"threshold_uncertainty_score":0.78382427},"labels":[],"label_agreement":null},{"id":"W2566375536","doi":"","title":"SYMPOSIUM: Testing in Linguistic Diversity Contexts","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","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 Victoria; University of British Columbia","funders":"","keywords":"Linguistics; Linguistic diversity; Diversity (politics); Computer science; Natural language processing; Sociology; Anthropology; Philosophy","score_opus":0.061896280785448295,"score_gpt":0.23108295730309403,"score_spread":0.16918667651764574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566375536","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":[0.78598714,0.00015795135,0.00030159854,0.0001792171,0.013306311,0.0002674836,0.0002047732,0.00021700644,0.19937849],"genre_scores_gemma":[0.9842482,0.00002595649,0.000039873437,0.00012906211,0.0031812685,0.0000018814926,0.0000026285793,0.000007896716,0.012363191],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904436,0.000042085925,0.00018270791,0.00026589987,0.0001795322,0.0002854301],"domain_scores_gemma":[0.99791765,0.00024135159,0.0000927783,0.00020796995,0.0014562154,0.000084039086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017465632,0.00013938211,0.00018527811,0.00009847639,0.00033795458,0.00012902288,0.000329648,0.000044419456,0.0015243721],"category_scores_gemma":[0.0066585927,0.00010247865,0.000043792934,0.000028953835,0.0002746304,0.00016807887,0.0003839986,0.00009047265,0.0007214698],"study_design_candidate":"observational","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":[0.00008516033,0.0002953664,0.6920885,0.00013660686,0.00006946119,0.0002861476,0.10622559,7.297303e-7,0.00043164656,0.1671336,0.023502976,0.009744241],"study_design_scores_gemma":[0.02071882,0.0014387087,0.25333637,0.0086357985,0.00079672824,0.000009892685,0.050783925,0.00083834305,0.0029800995,0.2692926,0.383,0.008168748],"about_ca_topic_score_codex":0.0071058646,"about_ca_topic_score_gemma":0.0060010334,"teacher_disagreement_score":0.4387521,"about_ca_system_score_codex":0.00006687386,"about_ca_system_score_gemma":0.00007795234,"threshold_uncertainty_score":0.9995059},"labels":[],"label_agreement":null},{"id":"W2599662706","doi":"","title":"PAPER: Examining Validity Evidence for Multidimensional Forced Choice Measures using Four Scoring Approaches","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Advanced Statistical Modeling Techniques","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":"Two-alternative forced choice; Item response theory; Psychology; Test (biology); Normative; Likert scale; Classical test theory; Rank (graph theory); Statistics; Psychometrics; Social psychology; Mathematics; Cognitive psychology; Clinical psychology; Developmental psychology","score_opus":0.690729672794958,"score_gpt":0.3971126026713275,"score_spread":0.29361707012363053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599662706","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":[0.013665717,0.000119454264,0.98453707,0.0004201433,0.00024446842,0.00046057467,0.000015852953,0.00045061435,0.00008613729],"genre_scores_gemma":[0.5067876,0.000019651881,0.49290097,0.00006252174,0.00007168877,0.00006314383,4.4003846e-7,0.000014416563,0.00007956489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974527,0.00014385731,0.0004225292,0.0009042761,0.0004875613,0.00058908627],"domain_scores_gemma":[0.99483323,0.0035149076,0.0002138418,0.0008091579,0.00044208296,0.00018674966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008550921,0.0002954145,0.00032585976,0.00009291959,0.00027068026,0.0001028782,0.0009346049,0.00011614047,0.000012747783],"category_scores_gemma":[0.0038324874,0.00021168597,0.000076781704,0.00013711382,0.00014598573,0.0016714006,0.00043874327,0.00013622694,0.000013739591],"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":[0.000075529846,0.00006167037,0.001846205,0.0000858636,0.00003330616,0.000010480098,0.00018049676,0.00044621807,0.35425246,0.22543979,0.00022600612,0.41734198],"study_design_scores_gemma":[0.0011074352,0.00038946464,0.0021343238,0.0028426761,0.000042219563,0.000033770724,0.00001735852,0.8235944,0.07054983,0.09708646,0.0010719083,0.0011301856],"about_ca_topic_score_codex":0.00007490507,"about_ca_topic_score_gemma":0.000018184943,"teacher_disagreement_score":0.82314813,"about_ca_system_score_codex":0.00014021804,"about_ca_system_score_gemma":0.00030090805,"threshold_uncertainty_score":0.8632303},"labels":[],"label_agreement":null},{"id":"W2602631024","doi":"","title":"WORKSHOP: Testing Multigroup and Multilevel Assessment Scale Equivalence across Nations and Cultures","year":2015,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Advanced Statistical Modeling Techniques","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 Ottawa","funders":"","keywords":"Scale (ratio); Mainstream; Equivalence (formal languages); Multilevel model; Set (abstract data type); Level of measurement; Extant taxon; Psychology; Social science; Geography; Political science; Sociology; Mathematics; Statistics; Computer science; Cartography","score_opus":0.14311314071787276,"score_gpt":0.41575796760203926,"score_spread":0.27264482688416647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602631024","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":[0.016144354,0.00014251842,0.9816127,0.0004539592,0.000083304076,0.00019390427,0.000032288972,0.00033232983,0.001004677],"genre_scores_gemma":[0.50987136,0.000026248461,0.4898548,0.00005964536,0.000014279464,0.000025638989,0.000001239119,0.0000048212023,0.00014191386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985782,0.00005496081,0.00022774657,0.0005238846,0.0002802758,0.00033491408],"domain_scores_gemma":[0.9982505,0.000615506,0.00009640826,0.0003609405,0.00042729257,0.00024937803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003395415,0.00017625275,0.00017687438,0.000047214526,0.00023495755,0.00032539162,0.0004850508,0.000077644356,0.0000023099738],"category_scores_gemma":[0.0011045951,0.00014939223,0.000012676288,0.00014571707,0.00023313508,0.0006636737,0.00068091584,0.00020271505,0.000006990317],"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":[0.000012526989,0.00015881355,0.009249905,0.000075913624,0.000017870158,0.000028987311,0.0044670766,0.00030344728,0.007374264,0.24010627,0.0011251022,0.7370798],"study_design_scores_gemma":[0.00048353843,0.0000912626,0.011752117,0.00028140933,0.0000058331375,0.00003111038,0.00020263447,0.86201584,0.0005766498,0.12372346,0.000444409,0.0003917387],"about_ca_topic_score_codex":0.000092285794,"about_ca_topic_score_gemma":0.000052544474,"teacher_disagreement_score":0.8617124,"about_ca_system_score_codex":0.000044424785,"about_ca_system_score_gemma":0.000109392204,"threshold_uncertainty_score":0.6092039},"labels":[],"label_agreement":null},{"id":"W2605338221","doi":"","title":"SYMPOSIUM: Continuous Testing: Psychometric Challenges and Opportunities","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Fungal Infections and Studies","field":"Medicine","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":"Psychometric testing; Psychology; Computer science; Psychometrics; Data science; Clinical psychology; Cronbach's alpha","score_opus":0.20318485710955597,"score_gpt":0.29992223470879903,"score_spread":0.09673737759924306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605338221","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":[0.39838335,0.029007182,0.00075550855,0.041475404,0.00063064584,0.000471061,0.000030011899,0.00035093076,0.5288959],"genre_scores_gemma":[0.9415244,0.043826558,0.00021911085,0.00016299632,0.000109219836,0.000024900677,5.580371e-7,0.000010816052,0.014121436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992918,0.000022456243,0.00015496703,0.00022174165,0.00011399318,0.00019504003],"domain_scores_gemma":[0.9990531,0.00028475578,0.000055320135,0.00019577933,0.0002887663,0.00012224028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012746365,0.00013072597,0.0002561995,0.00017091067,0.00007764915,0.000018229191,0.00004559627,0.000057481193,0.000107189364],"category_scores_gemma":[0.0002540967,0.000074803094,0.000028355198,0.00007814794,0.0001768379,0.00008403661,0.00004402061,0.00006378113,0.0000590504],"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":[0.00004875888,0.00012717275,0.021340165,0.000108005814,0.00010053336,0.00003247638,0.00031644458,1.1764462e-8,0.018247403,0.01450379,0.004614207,0.94056106],"study_design_scores_gemma":[0.0056035984,0.0041159997,0.48545304,0.00301086,0.00031492935,0.0008660806,0.0020238936,0.00003740618,0.0029187882,0.0044635385,0.49015763,0.0010342335],"about_ca_topic_score_codex":0.000029651736,"about_ca_topic_score_gemma":0.0000074991135,"teacher_disagreement_score":0.9395268,"about_ca_system_score_codex":0.000016575936,"about_ca_system_score_gemma":0.00007062976,"threshold_uncertainty_score":0.30503818},"labels":[],"label_agreement":null},{"id":"W2611906781","doi":"","title":"POSTER: The Impact of Group Imbalance on Logistic Regression Analyses with Assessment Data","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Advanced Statistical Modeling Techniques","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":"Statistics; Covariate; Skewness; Type I and type II errors; Logistic regression; Mathematics; Sample size determination; Econometrics; Variables; Wald test; Regression analysis; Analysis of covariance; Variable (mathematics); Statistical hypothesis testing","score_opus":0.22700990350077827,"score_gpt":0.4714656255143577,"score_spread":0.24445572201357946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611906781","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":[0.0028997413,0.00003510119,0.99492025,0.0007714132,0.000038066086,0.00016781891,0.00011426342,0.0001229372,0.0009303924],"genre_scores_gemma":[0.8822815,0.00006591344,0.11749758,0.000049432772,0.000016022394,0.000011524912,0.000006627967,0.000007771885,0.000063627434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846935,0.00012833807,0.00024779682,0.00052940956,0.00036466648,0.00026043924],"domain_scores_gemma":[0.9964623,0.0007385316,0.0002398996,0.0022860547,0.0001962506,0.00007700228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000283622,0.00019192016,0.00024403809,0.000053694213,0.00007274141,0.000064922635,0.0023483222,0.00004247233,0.000026282169],"category_scores_gemma":[0.00021993565,0.00007018404,0.000035777844,0.00015478898,0.00023830919,0.00044017722,0.0006066037,0.00012387548,0.000013233003],"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":[0.00038191697,0.00056953187,0.013098739,0.00005192386,0.00021189057,0.000091787784,0.00014387339,0.00028133078,0.08575829,0.47254217,0.0079069175,0.4189616],"study_design_scores_gemma":[0.002354508,0.0072389496,0.20567952,0.005194171,0.000101301186,0.00008095299,0.000025274978,0.3838249,0.015113062,0.37840626,0.0003806016,0.0016004866],"about_ca_topic_score_codex":0.00015827487,"about_ca_topic_score_gemma":0.000013102921,"teacher_disagreement_score":0.8793818,"about_ca_system_score_codex":0.00006560954,"about_ca_system_score_gemma":0.00020561932,"threshold_uncertainty_score":0.4363806},"labels":[],"label_agreement":null},{"id":"W2612009109","doi":"","title":"WORKSHOP: Keeping up with The Standards: How to Design and Evaluate Reliability and Validity Studies","year":2015,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Facilitator; Context (archaeology); Psychology; Reliability (semiconductor); Internal validity; Validity; Standards for Educational and Psychological Testing; External validity; Construct validity; Applied psychology; Presentation (obstetrics); Quality (philosophy); Psychometrics; Social psychology; Clinical psychology; Medicine; Higher education; Education theory; Political science","score_opus":0.8179560533686604,"score_gpt":0.5321420139146238,"score_spread":0.2858140394540366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612009109","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":[0.49653202,0.0015022913,0.4876419,0.012664554,0.00041177,0.00047072503,0.000009304247,0.000044877463,0.0007225571],"genre_scores_gemma":[0.95658046,0.0001881148,0.04183149,0.00027876796,0.00005153591,0.000027546934,1.0098402e-7,0.000006471372,0.0010355383],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99581313,0.001634576,0.0002732321,0.0006472954,0.0013360751,0.0002956933],"domain_scores_gemma":[0.9415124,0.053522065,0.00032579713,0.0010379427,0.0032543647,0.0003474494],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033442546,0.0001720968,0.0004076062,0.00012484139,0.0002578949,0.0005455052,0.0005007699,0.000051488103,0.000018674067],"category_scores_gemma":[0.20047598,0.000079351346,0.000021831846,0.0007834493,0.00042553034,0.00026309988,0.00039745405,0.00016312169,0.000007800534],"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":[0.0008649618,0.00003518998,0.06090876,0.000031400912,0.000097430326,0.00001455367,0.013390371,0.0007208069,0.0002061473,0.0008619975,0.16517875,0.75768965],"study_design_scores_gemma":[0.006195587,0.0041373237,0.1689964,0.0012127141,0.00030193056,0.00014734258,0.14593473,0.03297914,0.0015090209,0.4797201,0.1564362,0.0024295386],"about_ca_topic_score_codex":0.000027035785,"about_ca_topic_score_gemma":0.00002619643,"teacher_disagreement_score":0.7552601,"about_ca_system_score_codex":0.000049738115,"about_ca_system_score_gemma":0.00028881477,"threshold_uncertainty_score":0.9952743},"labels":[],"label_agreement":null},{"id":"W2612770846","doi":"","title":"PAPER: Examining Position Effects in Large-Scale Assessments Using an SEM Approach","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Rasch model; Position (finance); Reading (process); Test (biology); Structural equation modeling; Scale (ratio); Psychology; Item response theory; Sample (material); Computer science; Statistics; Econometrics; Psychometrics; Social psychology; Cognitive psychology; Artificial intelligence; Natural language processing; Mathematics; Developmental psychology; Linguistics","score_opus":0.5208722029508508,"score_gpt":0.4857174030503449,"score_spread":0.035154799900505906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612770846","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":[0.5533232,0.000044817294,0.43886203,0.000043073418,0.00029833496,0.0001344717,0.0000070255346,0.00003918216,0.007247882],"genre_scores_gemma":[0.9056558,0.000013043511,0.09369549,0.00011982871,0.00007727382,0.000014115393,0.000002023892,0.000011482873,0.00041091096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99628264,0.001097265,0.00054591533,0.00076796446,0.0008068817,0.00049931096],"domain_scores_gemma":[0.9901865,0.008464304,0.00029885623,0.0006846544,0.00021502405,0.00015064314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058084074,0.00018647233,0.0003757898,0.00045168924,0.00013718006,0.00023844,0.00074153877,0.00013679526,0.0002713588],"category_scores_gemma":[0.009192256,0.00010997777,0.00004584712,0.0009916147,0.00006886846,0.0010176696,0.00020184058,0.00014592934,0.00006615875],"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":[0.000039889102,0.0002664862,0.39375198,0.000014697493,0.000010661427,0.0000206189,0.0004008595,0.00003911964,0.08100749,0.0012987583,0.00018086011,0.5229686],"study_design_scores_gemma":[0.002051625,0.00039416313,0.9253656,0.00045337493,0.000015924312,0.000037021604,0.0015444871,0.039032042,0.001930774,0.0280202,0.00060062244,0.00055411656],"about_ca_topic_score_codex":0.00007791627,"about_ca_topic_score_gemma":0.000022032134,"teacher_disagreement_score":0.53161365,"about_ca_system_score_codex":0.000076061224,"about_ca_system_score_gemma":0.0001232979,"threshold_uncertainty_score":0.99915373},"labels":[],"label_agreement":null},{"id":"W2615639425","doi":"","title":"PAPER: Measuring Teachers’ Assessment Literacy and Conceptions of Assessment in a High Performative Canadian Context: A Construct Validity Study","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","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 Calgary","funders":"","keywords":"Performative utterance; Psychology; Literacy; Context (archaeology); Construct (python library); Construct validity; Mathematics education; Pedagogy; Psychometrics; Computer science; Developmental psychology","score_opus":0.06347086988825551,"score_gpt":0.3642921981591032,"score_spread":0.3008213282708477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615639425","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":[0.9735556,0.000034476445,0.00021651539,0.0015913589,0.00023566118,0.000846194,0.00007134222,0.000026709075,0.023422124],"genre_scores_gemma":[0.9987574,0.00016295812,0.0004137175,0.000057153735,0.00005312171,0.00008425936,0.0000041023877,0.00000847936,0.0004588002],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99745417,0.0007943056,0.00043826835,0.00033215928,0.0005293044,0.00045177474],"domain_scores_gemma":[0.9985779,0.00048055296,0.00020730359,0.0002244985,0.00024325031,0.000266525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016239885,0.00019121366,0.0003735815,0.00018199666,0.0004095314,0.00015143791,0.00032065224,0.000091532704,0.0013935344],"category_scores_gemma":[0.00012111214,0.00014436727,0.000038331476,0.0001810391,0.00052930036,0.0008351086,0.00008833069,0.00025271453,0.000015390284],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074952923,0.00014456129,0.90734804,0.0000058244764,0.000044141634,0.000006021572,0.043360785,1.4300763e-7,0.00036677392,0.024255592,0.000090078844,0.024370544],"study_design_scores_gemma":[0.0018445962,0.00018916815,0.92934096,0.00017679967,0.000034990484,7.6917064e-7,0.06501064,0.000016651104,0.000017440603,0.000843911,0.0022818935,0.00024221481],"about_ca_topic_score_codex":0.24541543,"about_ca_topic_score_gemma":0.3824903,"teacher_disagreement_score":0.13707487,"about_ca_system_score_codex":0.0005345712,"about_ca_system_score_gemma":0.0022653146,"threshold_uncertainty_score":0.99951935},"labels":[],"label_agreement":null},{"id":"W2616059813","doi":"","title":"SYMPOSIUM: The ITC Guidelines for Test Adaptation, version 2.0","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Mathematics, Computing, and Information Processing","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 Ottawa","funders":"","keywords":"Test (biology); Adaptation (eye); Computer science; Psychology; Geology","score_opus":0.09135627759384762,"score_gpt":0.3022145433295347,"score_spread":0.21085826573568706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616059813","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":[0.00043905314,0.00004801892,0.9766048,0.016854715,0.00039360684,0.00020847275,0.000007219545,0.00014347113,0.0053006085],"genre_scores_gemma":[0.7884156,0.00020550012,0.19440699,0.0042816335,0.00041818433,0.000073454416,0.000005653309,0.000020558591,0.01217243],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988674,0.000020618212,0.00042571177,0.00021391158,0.00024636244,0.00022597861],"domain_scores_gemma":[0.9972217,0.00064834376,0.0002854449,0.0004603028,0.0013330514,0.000051129373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005512121,0.000129079,0.00012302355,0.000055670767,0.0002965489,0.00026746767,0.0009804525,0.000046476274,0.000054263834],"category_scores_gemma":[0.0009783319,0.00006625213,0.0000511699,0.00011718206,0.000061212966,0.0009497067,0.00016668349,0.000041109255,0.00027847147],"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":[0.000012040549,0.000080133905,0.00032589695,0.00021400231,0.000026309723,9.154821e-7,0.004908843,0.0001527912,0.0070521026,0.2661697,0.3738108,0.34724644],"study_design_scores_gemma":[0.0008409377,0.00011004796,0.00014631236,0.00056395814,0.000012165932,0.000014753242,0.00023301289,0.70266056,0.00760727,0.03948659,0.24795239,0.00037203333],"about_ca_topic_score_codex":0.000011851859,"about_ca_topic_score_gemma":0.0000024372316,"teacher_disagreement_score":0.78797656,"about_ca_system_score_codex":0.000024583345,"about_ca_system_score_gemma":0.00024429229,"threshold_uncertainty_score":0.35792804},"labels":[],"label_agreement":null},{"id":"W2617029349","doi":"","title":"POSTER: Common Misconceptions and the Misuses of Standardized Assessments","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Teacher Education and Assessments","field":"Social Sciences","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 Calgary; University of Alberta","funders":"","keywords":"Scrutiny; Argument (complex analysis); Perception; Psychology; Public relations; Sample (material); Public opinion; Test (biology); Public policy; Social psychology; Political science; Medicine; Law; Politics","score_opus":0.06636221969219422,"score_gpt":0.42757827779907426,"score_spread":0.36121605810688007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617029349","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":[0.8480616,0.00023675493,0.002385152,0.031247897,0.0005421648,0.0005127127,0.000098006916,0.00006117933,0.116854526],"genre_scores_gemma":[0.99165285,0.00033005542,0.00014395958,0.00013421633,0.000044544475,0.000017817254,0.0000012044185,0.000003893437,0.007671448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895316,0.0003636489,0.0001656108,0.00012432762,0.00024548368,0.00014776096],"domain_scores_gemma":[0.99912417,0.000362654,0.00012590158,0.00016970317,0.0001458378,0.000071736664],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00054965203,0.00006738134,0.00014591747,0.000024714382,0.0002082697,0.00006361958,0.00022319668,0.00003987617,0.00093057303],"category_scores_gemma":[0.00011373515,0.000035222125,0.000034306777,0.00006223337,0.00089109543,0.00017261186,0.00004070166,0.00004779112,0.000021920281],"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":[0.00025872927,0.00029755817,0.25089434,0.000022821388,0.00015356595,0.0000012178837,0.034735274,4.897326e-8,0.00740608,0.4282934,0.0148287695,0.2631082],"study_design_scores_gemma":[0.014583235,0.00020253086,0.27413726,0.0008594551,0.00017444183,0.0000031859574,0.046723444,0.000009396682,0.0037154283,0.04732871,0.6115038,0.00075913494],"about_ca_topic_score_codex":0.0010927028,"about_ca_topic_score_gemma":0.0005142697,"teacher_disagreement_score":0.59667504,"about_ca_system_score_codex":0.000034634573,"about_ca_system_score_gemma":0.00043208062,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W2619373123","doi":"","title":"INVITED SYPOSIUM: The Life and Work of Dr. Thomas David Oakland","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Early Childhood Education and Development","field":"Social Sciences","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":"Tribute; Management; Honor; Library science; Test (biology); Political science; Sociology; Psychology; Law","score_opus":0.03728799600135992,"score_gpt":0.28968563677974063,"score_spread":0.2523976407783807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619373123","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":[0.73102736,0.0007630984,0.0005174516,0.22982377,0.00067307195,0.0003971978,0.0000105008385,0.00007085693,0.036716666],"genre_scores_gemma":[0.99064875,0.00056268275,0.000121281584,0.0011722841,0.00010657731,0.0000088502,6.790005e-7,0.000004125948,0.0073747914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991909,0.00012296713,0.00015360063,0.0001438711,0.00021464295,0.00017396726],"domain_scores_gemma":[0.99918026,0.00029929663,0.000089860936,0.00016425169,0.00013162907,0.00013469484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004129575,0.00007075779,0.00010079526,0.000032314845,0.0002064572,0.000058636047,0.00022081521,0.000055802986,0.00027996072],"category_scores_gemma":[0.0003635152,0.000036675563,0.000019279025,0.00015088622,0.00037156403,0.00011209354,0.000046805144,0.000049694183,0.000052909425],"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":[0.000047229707,0.0001000697,0.5595311,0.0000150088845,0.000074811105,0.0000012394432,0.07718142,1.6469528e-7,0.0016880454,0.049733162,0.2411622,0.07046556],"study_design_scores_gemma":[0.0004537723,0.00003143751,0.6108893,0.00021888534,0.000015313666,6.748413e-7,0.002989945,5.340401e-7,0.0005704154,0.0048708394,0.37974194,0.00021693931],"about_ca_topic_score_codex":0.00048634058,"about_ca_topic_score_gemma":0.00027454767,"teacher_disagreement_score":0.25962135,"about_ca_system_score_codex":0.000015339536,"about_ca_system_score_gemma":0.00046985917,"threshold_uncertainty_score":0.30653736},"labels":[],"label_agreement":null},{"id":"W2619791510","doi":"","title":"PAPER: Adjusting for Cumulative French Language Exposure in the WISC V French Canadian Norms","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Language Development and Disorders","field":"Psychology","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":"French; Psychology; Demography; Population; Neighbourhood (mathematics); Geography; Developmental psychology; Sociology; Mathematics","score_opus":0.027126692773121748,"score_gpt":0.29363266078983663,"score_spread":0.2665059680167149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619791510","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":[0.76997143,0.0011214697,0.0016896187,0.0051749875,0.00083309645,0.0010383669,0.00021292052,0.00007631534,0.21988177],"genre_scores_gemma":[0.98436886,0.000010536457,0.00023982565,0.0010618023,0.000120909,0.0001982835,0.00003360664,0.000016599022,0.01394955],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99858904,0.00009640696,0.00025242203,0.0003450766,0.00014619617,0.0005708837],"domain_scores_gemma":[0.99893326,0.00041005207,0.0000828464,0.00037619323,0.00008664601,0.00011103119],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003688615,0.00018788899,0.00017683396,0.00012720854,0.000111198955,0.000042113777,0.0004582238,0.00014272878,0.004784262],"category_scores_gemma":[0.00021341289,0.000099673234,0.0000517965,0.00015868695,0.000082535335,0.000155582,0.00002737257,0.00012436879,0.00041059163],"study_design_candidate":"observational","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":[0.00005751435,0.00014217634,0.1422314,0.000037793154,0.00011492411,0.00019194705,0.16851108,9.2977587e-7,0.0017251233,0.017611492,0.08796002,0.5814156],"study_design_scores_gemma":[0.0049493774,0.00028652238,0.888192,0.00030941443,0.00004233087,0.000021156326,0.031914838,0.000028293358,0.00018121318,0.005276039,0.06781013,0.0009886754],"about_ca_topic_score_codex":0.18416972,"about_ca_topic_score_gemma":0.5110241,"teacher_disagreement_score":0.7459606,"about_ca_system_score_codex":0.000057826346,"about_ca_system_score_gemma":0.00031773187,"threshold_uncertainty_score":0.9961255},"labels":[],"label_agreement":null},{"id":"W2623451806","doi":"","title":"POSTER: A Comprehensive Review of the Historical Contributions into Language Acquisition and Development Over the Last Century are Formulated Here to Provide an Understanding of how Normal Language Develops and Difficulties Occur","year":2016,"lang":"en","type":"review","venue":"ITC 2016 Conference","topic":"Language Development and Disorders","field":"Psychology","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":"Reading (process); Cognitive science; Perception; Cognition; Psychology; Modalities; Process (computing); Language development; Language acquisition; Cognitive psychology; Linguistics; Computer science; Mathematics education; Developmental psychology; Sociology; Neuroscience","score_opus":0.04355742069082458,"score_gpt":0.32360935669070734,"score_spread":0.28005193599988276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623451806","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":[0.007975484,0.98927325,0.00024201587,0.0004325305,0.00024342925,0.0014696973,0.00018170444,0.000027694405,0.00015419183],"genre_scores_gemma":[0.049166106,0.94944775,0.00013502914,0.0004456619,0.000051069917,0.00015789342,0.00015134283,0.00003611405,0.00040900393],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815166,0.0003385326,0.0005645123,0.00038092915,0.00026017678,0.00030417994],"domain_scores_gemma":[0.9983373,0.00026783993,0.00065630407,0.00039844282,0.00023135656,0.00010872458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022757669,0.0003754593,0.0009515983,0.00010725782,0.00017531657,0.000041796942,0.0003576072,0.00020998581,0.00016432213],"category_scores_gemma":[0.000125465,0.00018714504,0.00010485667,0.00020930824,0.00015775472,0.00012107124,0.00028254386,0.00020534986,0.000010375734],"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":[0.00012154206,0.00020750889,0.0011713995,0.05391643,0.00083174347,0.00004405296,0.05194153,3.131289e-8,0.00014179121,0.0021678216,0.00851703,0.8809391],"study_design_scores_gemma":[0.0016250779,0.00014812525,0.011501765,0.1253317,0.0005289152,0.000091133414,0.023654737,4.7241986e-7,0.000042742584,0.00003541148,0.8359563,0.001083632],"about_ca_topic_score_codex":0.00013304563,"about_ca_topic_score_gemma":0.00022471642,"teacher_disagreement_score":0.8798555,"about_ca_system_score_codex":0.00036745344,"about_ca_system_score_gemma":0.0003911086,"threshold_uncertainty_score":0.7631553},"labels":[],"label_agreement":null},{"id":"W2736595548","doi":"","title":"POSTER: A Validity Argument Approach to Collaborative Development of the Colleges Mathematics Assessment Program","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","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":"York University; University of Toronto","funders":"","keywords":"Argument (complex analysis); Test (biology); Mathematics education; Computer science; Psychology","score_opus":0.08059059746095346,"score_gpt":0.3733509050348911,"score_spread":0.2927603075739377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736595548","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":[0.5015751,0.00002957166,0.0077163638,0.005548357,0.000671582,0.0047310945,0.000055451772,0.00013857958,0.47953388],"genre_scores_gemma":[0.94571674,0.000031403786,0.046641488,0.000049371054,0.000053346623,0.0003832296,0.0000013731276,0.0000095871765,0.0071134586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789023,0.00021713618,0.00037616264,0.00027944022,0.00087970664,0.00035729224],"domain_scores_gemma":[0.99862915,0.00018160148,0.00024669364,0.00030456134,0.000503567,0.00013441945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008781064,0.00017016113,0.00026140705,0.000049115086,0.0004083374,0.00010847879,0.0007081878,0.00007716592,0.00014971885],"category_scores_gemma":[0.00010647258,0.00009108636,0.000060013394,0.00040715226,0.00026287592,0.00013826841,0.0002574499,0.00006597025,0.00005158593],"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":[0.00010160263,0.0063780695,0.14502732,0.00020881074,0.00051230984,0.0000024876792,0.23388965,0.0000015659311,0.0127717005,0.41276556,0.019654948,0.16868596],"study_design_scores_gemma":[0.0038634138,0.00084798335,0.37214988,0.0017922749,0.00020443829,0.0000017565382,0.1001458,0.000051307157,0.02399788,0.008331245,0.486701,0.0019129973],"about_ca_topic_score_codex":0.000048309736,"about_ca_topic_score_gemma":0.00025699922,"teacher_disagreement_score":0.47242042,"about_ca_system_score_codex":0.00024362016,"about_ca_system_score_gemma":0.0017719534,"threshold_uncertainty_score":0.3714394},"labels":[],"label_agreement":null},{"id":"W2742582834","doi":"","title":"POSTER: Overclaiming as Convenient Proxy for Confidence and Overconfidence","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Statistics Education and Methodologies","field":"Mathematics","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":"Overconfidence effect; Confidence interval; Proxy (statistics); Vocabulary; Respondent; Psychology; Test (biology); Self-confidence; Social psychology; Statistics; Mathematics; Linguistics","score_opus":0.21118577158893947,"score_gpt":0.42812657072379057,"score_spread":0.2169407991348511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742582834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17778969,0.00031913683,0.80400115,0.0052558747,0.0018751125,0.0017163167,0.00029651198,0.0002537873,0.008492418],"genre_scores_gemma":[0.92903614,0.00035960544,0.05299064,0.0004686157,0.000097093216,0.00018025578,0.000002852889,0.000026122014,0.0168387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987344,0.000099246725,0.00030681773,0.00037925254,0.00017784216,0.00030245353],"domain_scores_gemma":[0.99426496,0.0047050277,0.00019375839,0.00034501543,0.00036265422,0.00012859146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059368525,0.00017855324,0.00026271906,0.00005984185,0.00010161249,0.00007590805,0.00021427362,0.00008792287,0.0005013402],"category_scores_gemma":[0.0070177573,0.00012039635,0.000040630577,0.000041136573,0.00023955596,0.00016421713,0.00007981591,0.00006337132,0.00009387419],"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":[0.00005752261,0.00003587683,0.0011935728,0.00013515711,0.00002229326,0.000002748455,0.00077442353,1.0740476e-8,0.020486787,0.94585407,0.011532003,0.019905541],"study_design_scores_gemma":[0.0010218067,0.00023047862,0.001873931,0.0006837817,0.000052152212,0.00005789109,0.00064485543,0.000045560162,0.037755683,0.9380193,0.019271372,0.00034323026],"about_ca_topic_score_codex":0.000049453727,"about_ca_topic_score_gemma":0.000011650694,"teacher_disagreement_score":0.75124645,"about_ca_system_score_codex":0.000037665002,"about_ca_system_score_gemma":0.00032653636,"threshold_uncertainty_score":0.8401418},"labels":[],"label_agreement":null},{"id":"W2761268105","doi":"","title":"POSTER: What work habits are being assessed across Canada?","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Agricultural and Financial Auditing","field":"Agricultural and Biological Sciences","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":"Queen's University","funders":"","keywords":"Context (archaeology); Work (physics); Psychology; Medical education; Geography; Medicine","score_opus":0.020165917419981368,"score_gpt":0.20148767723297017,"score_spread":0.18132175981298881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761268105","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":[0.9852729,0.00013589894,0.000012856352,0.0130471485,0.00044636233,0.00012584962,0.000065209795,0.00007063959,0.00082312105],"genre_scores_gemma":[0.9955892,0.00013805968,0.000011176364,0.0006092319,0.00045086135,0.000014959444,0.0000140267,0.0000010838831,0.0031713773],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985342,0.000043863558,0.00023489083,0.0003742371,0.0002617282,0.0005510698],"domain_scores_gemma":[0.9990964,0.00026072277,0.00019599771,0.00006747393,0.00022246466,0.00015695863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011492157,0.00020310767,0.00022613413,0.000002242483,0.00035220926,0.00022124853,0.00037773457,0.00010486718,0.00044900362],"category_scores_gemma":[0.00010850274,0.000053594027,0.00006401738,0.00021265169,0.00006337248,0.0006092523,0.00014804227,0.00009973196,0.00014609637],"study_design_candidate":"observational","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":[0.000023095412,0.000026962334,0.09509261,0.0000056619106,0.0000098417695,0.000030951505,0.000076734716,9.7665925e-8,0.09902852,0.00021623303,0.004143078,0.80134624],"study_design_scores_gemma":[0.00012438097,0.0000460141,0.95145625,0.00061022263,0.000004316888,0.0000064363203,0.0004903549,5.803147e-7,0.0061327717,0.00028385207,0.04050746,0.00033734355],"about_ca_topic_score_codex":0.05111282,"about_ca_topic_score_gemma":0.48626825,"teacher_disagreement_score":0.85636365,"about_ca_system_score_codex":0.00007042998,"about_ca_system_score_gemma":0.000046044464,"threshold_uncertainty_score":0.9552059},"labels":[],"label_agreement":null}]}