{"meta":{"query_hash":"49b792a6fb40","filters":{"venue":"Behavior Research Methods"},"cohort_total":304,"direct_labels_cover":3,"predictions_cover":304,"exported":304,"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/49b792a6fb40","api":"https://metacan.xera.ac/api/v1/cohort?venue=Behavior+Research+Methods"},"results":[{"id":"W1842016767","doi":"10.3758/s13428-015-0636-6","title":"Ratings of age of acquisition of 299 words across 25 languages: Is there a cross-linguistic order of words?","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":94,"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":"Age of Acquisition; Linguistics; Natural language processing; Computer science; Word order; Psychology; Order (exchange); Artificial intelligence; Cognition; Philosophy","score_opus":0.30354275651506313,"score_gpt":0.597421963177566,"score_spread":0.2938792066625029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842016767","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":[0.99686086,0.00044790568,0.0005450896,0.000036296293,0.00015251605,0.0005112554,0.00020319886,0.00002394164,0.0012189625],"genre_scores_gemma":[0.97945666,0.000029139173,0.01930267,0.00004933878,0.000067532965,0.000037543,0.000010231616,0.00003228422,0.0010145864],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949623,0.0023148,0.0008071538,0.00050373597,0.0008789761,0.000533037],"domain_scores_gemma":[0.9956587,0.0018488195,0.00044542793,0.0007754334,0.0011319246,0.00013968366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006516132,0.00018894234,0.0006067973,0.00025753406,0.00008708284,0.000026065396,0.0007713814,0.0002049793,0.00022876132],"category_scores_gemma":[0.011969895,0.0001558231,0.00016546622,0.0011355182,0.0019287189,0.000097263764,0.00041965386,0.00048102628,0.000003903889],"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":[0.00019644604,0.00038968297,0.007825589,0.00020065159,0.000007864918,0.00029175272,0.022760963,0.0000023363425,0.9604589,0.00011596409,0.000028636854,0.0077212164],"study_design_scores_gemma":[0.00081250485,0.0006420249,0.0051801973,0.00013530531,0.000022968276,0.000041351148,0.0034927488,0.000014368085,0.9889147,0.00038112755,0.00023307286,0.00012959863],"about_ca_topic_score_codex":0.00078920025,"about_ca_topic_score_gemma":0.000026766073,"teacher_disagreement_score":0.028455835,"about_ca_system_score_codex":0.000030719315,"about_ca_system_score_gemma":0.00023783858,"threshold_uncertainty_score":0.9963527},"labels":[],"label_agreement":null},{"id":"W1963917975","doi":"10.3758/brm.38.2.344","title":"An SPSS implementation of the nonrecursive outlier deletion procedure with shiftingz score criterion (Van Selst &amp; Jolicoeur, 1994)","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"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":"Outlier; Computer science; Univariate; Popularity; Simple (philosophy); Data mining; Database; Restructuring; Artificial intelligence; Machine learning; Psychology","score_opus":0.11959399906640342,"score_gpt":0.5160720460885306,"score_spread":0.3964780470221272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963917975","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":[0.31132844,0.000052665873,0.6870266,0.00033833185,0.00009843652,0.00089388416,0.000010562209,0.000049745697,0.00020130222],"genre_scores_gemma":[0.30195624,0.000005588505,0.69743353,0.00004501155,0.00010666441,0.00020949851,0.000015259413,0.000028486491,0.00019970656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934628,0.003654263,0.00044018574,0.0007051111,0.0010730173,0.0006645946],"domain_scores_gemma":[0.9976627,0.00021857365,0.00021794393,0.0011585873,0.00058619084,0.00015597211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055869278,0.00023310521,0.00028127784,0.00029821173,0.00043632562,0.00027380584,0.0012799908,0.0001357614,0.00004169697],"category_scores_gemma":[0.000089136265,0.00015935778,0.00010351118,0.0013332486,0.0002509446,0.0006333599,0.00029842663,0.00057084486,0.0000032768596],"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":[0.00006022935,0.0005037858,0.027521895,0.00009622674,0.0000152342145,0.0000136143335,0.0039815125,0.000019725265,0.23077105,0.025052471,0.0006393085,0.71132493],"study_design_scores_gemma":[0.0019929965,0.0015155287,0.51777166,0.00030048346,0.00012022908,0.00017810639,0.0009004364,0.0020447646,0.42872405,0.038485814,0.006956401,0.0010095207],"about_ca_topic_score_codex":0.0011115365,"about_ca_topic_score_gemma":0.00064772926,"teacher_disagreement_score":0.7103154,"about_ca_system_score_codex":0.00011980222,"about_ca_system_score_gemma":0.00033904647,"threshold_uncertainty_score":0.64984214},"labels":[],"label_agreement":null},{"id":"W1968422660","doi":"10.3758/s13428-013-0426-y","title":"ANGST: Affective norms for German sentiment terms, derived from the affective norms for English words","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":172,"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":"German; Valence (chemistry); Psychology; Arousal; Linguistics; Cognitive psychology; Social psychology","score_opus":0.11837886767040291,"score_gpt":0.5231030567677374,"score_spread":0.4047241890973345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968422660","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":[0.7985059,0.0003356008,0.18791856,0.00020296461,0.0017863559,0.006691558,0.000490469,0.00015476905,0.00391382],"genre_scores_gemma":[0.9167628,0.00001876975,0.056267463,0.0003139326,0.0024866452,0.020011254,0.0005314787,0.00017293938,0.0034346886],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924732,0.0044834493,0.00037461292,0.00095946464,0.00059328374,0.0011160077],"domain_scores_gemma":[0.98957783,0.008285307,0.00015901431,0.0009762919,0.00075803034,0.00024352147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00938779,0.0003524845,0.0005114708,0.00023592626,0.00067997037,0.00019366652,0.0006649167,0.00031997927,0.0006399651],"category_scores_gemma":[0.002084315,0.00023642194,0.0004281479,0.0004248565,0.00036757172,0.00018793269,0.00019982018,0.0007107732,0.00007171126],"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":[0.0013008958,0.0011193616,0.0046354556,0.000054558757,0.0004218902,0.000017752074,0.044398632,4.4661843e-7,0.068518884,0.0024039133,0.0066104443,0.8705178],"study_design_scores_gemma":[0.013764964,0.004545403,0.55161864,0.00018786833,0.0012770733,0.000023057954,0.03360972,0.0003230081,0.28823572,0.035391215,0.06931114,0.00171218],"about_ca_topic_score_codex":0.00092795456,"about_ca_topic_score_gemma":0.00031828386,"teacher_disagreement_score":0.8688056,"about_ca_system_score_codex":0.00019928876,"about_ca_system_score_gemma":0.00006247592,"threshold_uncertainty_score":0.96410066},"labels":[],"label_agreement":null},{"id":"W1969265184","doi":"10.3758/s13428-014-0474-y","title":"Comment on Hoffman and Rovine (2007): SPSS MIXED can estimate models with heterogeneous variances","year":2014,"lang":"en","type":"letter","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","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":"Lakehead University","funders":"","keywords":"Syntax; Computer science; Statistics; Homogeneous; Multilevel model; Econometrics; Natural language processing; Mathematics; Machine learning","score_opus":0.35452185905389183,"score_gpt":0.5775459775008415,"score_spread":0.22302411844694964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969265184","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":[0.0063753994,0.00037648858,0.008021796,0.96772605,0.0018354517,0.0022236146,0.000103551094,0.00029136552,0.013046297],"genre_scores_gemma":[0.016355567,0.000878816,0.15041137,0.80056316,0.013018314,0.0035416847,0.00029439753,0.00061020936,0.01432652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9864419,0.00916051,0.00038455921,0.0010120973,0.0015009572,0.0014999536],"domain_scores_gemma":[0.9966316,0.0017574693,0.00018189065,0.000681207,0.00039462445,0.00035318115],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007235133,0.0004215268,0.0007333125,0.00038478093,0.0011346355,0.00033655114,0.0009755263,0.00097537314,0.00024180135],"category_scores_gemma":[0.00032257452,0.00034362727,0.00012746913,0.00039391662,0.0018742791,0.000103446146,0.00020895633,0.002743005,0.000032008607],"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":[0.00013338741,0.00020115849,0.00025806567,0.00006223909,0.000087556735,0.0006594086,0.0030452982,0.0000071926092,0.000047413454,0.0028926544,0.92579114,0.066814505],"study_design_scores_gemma":[0.00046549263,0.0012239316,0.00028062446,0.00012696593,0.000070364586,0.000026608292,0.0003832286,0.00006571127,0.00009358273,0.0053004613,0.99147654,0.0004864862],"about_ca_topic_score_codex":0.014740514,"about_ca_topic_score_gemma":0.0017301501,"teacher_disagreement_score":0.16716291,"about_ca_system_score_codex":0.00037752732,"about_ca_system_score_gemma":0.00027222166,"threshold_uncertainty_score":0.9999016},"labels":[],"label_agreement":null},{"id":"W1970590570","doi":"10.3758/brm.41.3.765","title":"Streams and patterns in behavior as challenges for future technologies","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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":"Dalhousie University","funders":"","keywords":"STREAMS; Computer science; Operating system","score_opus":0.5247012113643312,"score_gpt":0.6969705412938351,"score_spread":0.17226932992950383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970590570","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":[0.9746836,0.009983913,0.00020851966,0.007871395,0.00036879705,0.004235938,0.00006247992,0.0002036868,0.0023817094],"genre_scores_gemma":[0.9060258,0.0074189943,0.07087535,0.00011671519,0.00043020246,0.011288533,0.00004006954,0.00009466386,0.0037096497],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949127,0.0018371393,0.00041531783,0.00081121986,0.00061575236,0.0014079141],"domain_scores_gemma":[0.99779224,0.0008587074,0.00005840199,0.0008473701,0.00018248781,0.00026076895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006572747,0.00023383027,0.000382902,0.00082139304,0.000227597,0.00006425729,0.0006139293,0.00050186494,0.00030906565],"category_scores_gemma":[0.00048292926,0.00021163515,0.0000713205,0.00044776648,0.00026176492,0.00012254097,0.0002201473,0.0013575116,0.000031328924],"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":[0.00014197579,0.000793014,0.020079682,0.00007913535,0.0000050497715,0.00020077615,0.0013001282,1.1512483e-8,0.0013488831,0.009258651,0.00016763921,0.96662503],"study_design_scores_gemma":[0.0016634293,0.0031329226,0.93048894,0.0000811614,0.000016567017,0.000085303975,0.03227548,0.000006146936,0.0038888722,0.0055396073,0.022506356,0.00031520834],"about_ca_topic_score_codex":0.0003483116,"about_ca_topic_score_gemma":0.00024725558,"teacher_disagreement_score":0.96630985,"about_ca_system_score_codex":0.0002101467,"about_ca_system_score_gemma":0.00009642105,"threshold_uncertainty_score":0.8630231},"labels":[],"label_agreement":null},{"id":"W1974991592","doi":"10.3758/s13428-013-0403-5","title":"Concreteness ratings for 40 thousand generally known English word lemmas","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":1876,"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":"Concreteness; Word (group theory); Crowdsourcing; Psychology; Set (abstract data type); Cognitive psychology; Computer science; Word lists by frequency; Natural language processing; Linguistics; World Wide Web","score_opus":0.2074451318612571,"score_gpt":0.5283622746603649,"score_spread":0.32091714279910777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974991592","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":[0.94160306,0.001294585,0.028808909,0.00021701072,0.0016736253,0.0036305357,0.00005763825,0.00023752275,0.022477137],"genre_scores_gemma":[0.39667588,0.0000758351,0.49784443,0.0005335434,0.0037716762,0.025703428,0.0002644492,0.0003073359,0.07482344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993359,0.0037288007,0.00047563104,0.0007455293,0.00056218903,0.0011288482],"domain_scores_gemma":[0.995378,0.0018038237,0.000108714565,0.0007386946,0.0016478163,0.00032295164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0076167434,0.00026147504,0.0004208743,0.0003314559,0.00041474611,0.0002871913,0.00055238575,0.00032274926,0.0065035042],"category_scores_gemma":[0.0016268212,0.00022250264,0.0002267028,0.0005293091,0.00030520314,0.00025673767,0.00015155134,0.0006870313,0.0002844815],"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":[0.00025145043,0.00025246892,0.0014250746,0.000053152216,0.0000768622,0.000056112094,0.0073945345,2.449917e-7,0.114251696,0.0041846763,0.02150461,0.8505491],"study_design_scores_gemma":[0.014181997,0.003277736,0.1567021,0.00022364757,0.00068109273,0.00019118108,0.04388869,0.00027393675,0.24553668,0.02014469,0.51179814,0.0031001237],"about_ca_topic_score_codex":0.0010105597,"about_ca_topic_score_gemma":0.000028943894,"teacher_disagreement_score":0.847449,"about_ca_system_score_codex":0.00007053392,"about_ca_system_score_gemma":0.00012375176,"threshold_uncertainty_score":0.9944047},"labels":[],"label_agreement":null},{"id":"W1977005518","doi":"10.3758/bf03192711","title":"A comparison of the randomization test with theF test when error is skewed","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":30,"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":"Randomization; Resampling; Statistics; Test (biology); Mathematics; Skew; Type I and type II errors; Restricted randomization; Permutation (music); Computer science; Medicine; Randomized controlled trial; Surgery; Biology","score_opus":0.22585174721536294,"score_gpt":0.5473035776803988,"score_spread":0.3214518304650359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977005518","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":[0.014984184,0.00020498286,0.9749549,0.0073603727,0.00004043876,0.0012448253,0.000015534519,0.00007002657,0.0011247032],"genre_scores_gemma":[0.2546078,0.0000072470334,0.7433104,0.000043798296,0.000055957134,0.00040229768,0.0000023615403,0.00001143794,0.0015587198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754363,0.00074674556,0.0003129062,0.0003442485,0.000734863,0.00031759054],"domain_scores_gemma":[0.99633217,0.002000005,0.00012512713,0.00095892005,0.00048702108,0.00009676361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028257852,0.00011091009,0.00021410032,0.00012560491,0.0004453827,0.00008620125,0.0012685367,0.000060853938,0.0000734082],"category_scores_gemma":[0.0005530832,0.00006915597,0.00007350272,0.001058184,0.00028342093,0.00026067448,0.00035399993,0.00036312576,0.000018687037],"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":[0.000083945655,0.00614025,0.2039126,0.000042616302,0.000035567886,0.0000028510333,0.009331742,0.0003459568,0.104146585,0.01685259,0.01063922,0.6484661],"study_design_scores_gemma":[0.005477252,0.0007888982,0.35515207,0.00012545384,0.00007326999,0.000046345343,0.00064242294,0.38095248,0.19143644,0.00403266,0.060717963,0.0005547261],"about_ca_topic_score_codex":0.00006711032,"about_ca_topic_score_gemma":0.000024855728,"teacher_disagreement_score":0.64791137,"about_ca_system_score_codex":0.00007092531,"about_ca_system_score_gemma":0.000203791,"threshold_uncertainty_score":0.34255686},"labels":[],"label_agreement":null},{"id":"W1978406346","doi":"10.3758/bf03192769","title":"Anagram software for cognitive research that enables specification of psycholinguistic variables","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","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":"McGill University","funders":"","keywords":"Anagram; Anagrams; Computer science; Task (project management); Software; Cognition; Natural language processing; Artificial intelligence; Programming language; Psychology","score_opus":0.46341037151236264,"score_gpt":0.6295342610735168,"score_spread":0.1661238895611542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978406346","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":[0.0044763708,0.00041181175,0.9913002,0.00006957409,0.000085671505,0.0016075938,0.000024881607,0.00022629916,0.0017975902],"genre_scores_gemma":[0.15379846,0.000041381896,0.8442465,0.0000056672297,0.00013982403,0.0008988001,0.000034522087,0.000032546108,0.00080231635],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99360484,0.0022799922,0.00055362674,0.0009086851,0.0016322499,0.0010206262],"domain_scores_gemma":[0.9851628,0.008107356,0.00018048474,0.0011840253,0.0052194726,0.00014586317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02460257,0.00018947509,0.00038095718,0.0016489251,0.00048975326,0.00022491552,0.0017074965,0.00018684324,0.000020933761],"category_scores_gemma":[0.0068289055,0.00018082578,0.0001453061,0.003752361,0.0006454664,0.00028718635,0.0004902678,0.0006617593,0.0000070577917],"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":[0.000085284046,0.0008725308,0.004839277,0.000109803834,0.000027109792,0.000022381297,0.00028068337,0.000008447486,0.060662087,0.11304372,0.0013664918,0.8186822],"study_design_scores_gemma":[0.00062507595,0.00050488324,0.022315005,0.00016973449,0.00004463153,0.000009022475,0.00044576457,0.0012486696,0.628731,0.3318826,0.01360737,0.00041622767],"about_ca_topic_score_codex":0.0005146527,"about_ca_topic_score_gemma":0.00006442081,"teacher_disagreement_score":0.818266,"about_ca_system_score_codex":0.00020234908,"about_ca_system_score_gemma":0.00021964885,"threshold_uncertainty_score":0.8526809},"labels":[],"label_agreement":null},{"id":"W1979311362","doi":"10.3758/s13428-012-0302-1","title":"ELIA: A software application for integrating spoken language and eye movements","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","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":"University of Calgary","funders":"","keywords":"Computer science; Software; Eye tracking; Eye movement; Process (computing); Gaze; Raw data; Artificial intelligence; Natural language processing; Human–computer interaction; Programming language","score_opus":0.19167298798216587,"score_gpt":0.5646022571054135,"score_spread":0.3729292691232476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979311362","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":[0.98454326,0.00011140244,0.012785008,0.0001865282,0.0000748065,0.0020231125,0.000026385043,0.00009432877,0.00015515264],"genre_scores_gemma":[0.6647966,0.00003708961,0.32470238,0.0007883705,0.00022469477,0.004813776,0.000028061757,0.000067430425,0.0045416085],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99762535,0.000882448,0.00021604341,0.00055600697,0.00023999008,0.00048018259],"domain_scores_gemma":[0.99789613,0.0014230948,0.000059121827,0.0003543327,0.00014199027,0.00012534614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020316155,0.00012978233,0.00016933553,0.00016703876,0.00030463576,0.000101264224,0.00033339116,0.00010269736,0.000089639696],"category_scores_gemma":[0.003863023,0.000103295846,0.00005143018,0.00025740388,0.00024203572,0.0001614396,0.00021734231,0.0003731956,0.000034936405],"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":[0.0000070725937,0.000047950576,0.0010835966,0.000015581085,0.0000010209993,0.000017809716,0.00073565304,3.7502794e-8,0.7197653,0.000058555037,0.0000792442,0.2781882],"study_design_scores_gemma":[0.0004771992,0.00023826119,0.0038187795,0.000020522672,0.00000969136,0.000036179757,0.0021832276,0.00018583193,0.98903507,0.0012953272,0.002504479,0.00019543178],"about_ca_topic_score_codex":0.00032501388,"about_ca_topic_score_gemma":0.00001171647,"teacher_disagreement_score":0.3197467,"about_ca_system_score_codex":0.000030969255,"about_ca_system_score_gemma":0.0000365737,"threshold_uncertainty_score":0.46246785},"labels":[],"label_agreement":null},{"id":"W1979532929","doi":"10.3758/s13428-012-0210-4","title":"Age-of-acquisition ratings for 30,000 English words","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":1250,"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":"Economic and Social Research Council","keywords":"Age of Acquisition; Vocabulary; Lexicon; Noun; Crowdsourcing; Computer science; Psychology; Natural language processing; Word (group theory); Variance (accounting); Similarity (geometry); Correlation; Artificial intelligence; Linguistics; Statistics; Mathematics; Cognition; World Wide Web","score_opus":0.2541210475944673,"score_gpt":0.5307494941877987,"score_spread":0.2766284465933314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979532929","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":[0.0827001,0.0005184028,0.91046715,0.00005324344,0.0017575618,0.0012610772,0.000017719625,0.00015381236,0.0030709517],"genre_scores_gemma":[0.30293447,0.000005438841,0.6951634,0.000020741336,0.0007005343,0.0007215098,0.000015402027,0.000019283321,0.00041919824],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99609864,0.0016503975,0.00036271536,0.00034043455,0.00068692875,0.0008608827],"domain_scores_gemma":[0.9969537,0.0012642053,0.000093071794,0.0007416297,0.00063235825,0.00031503703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014133419,0.00013041814,0.0002696727,0.00030935262,0.00019874748,0.00016045793,0.0008893985,0.0001304831,0.00008156376],"category_scores_gemma":[0.00155909,0.000119000026,0.000125085,0.00073902006,0.00013271485,0.0005955466,0.0003122021,0.00025634034,0.000023037865],"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":[0.000071045055,0.00069944386,0.01490031,0.000179611,0.000023632354,0.000018597715,0.013143584,0.0000016283636,0.27609736,0.039018556,0.004838569,0.65100765],"study_design_scores_gemma":[0.0027724353,0.0016505404,0.10500528,0.00020314241,0.00005272554,0.00003938533,0.002244906,0.0011530857,0.73009115,0.007887963,0.14780919,0.0010901855],"about_ca_topic_score_codex":0.00012868796,"about_ca_topic_score_gemma":0.000001803433,"teacher_disagreement_score":0.6499175,"about_ca_system_score_codex":0.00008382766,"about_ca_system_score_gemma":0.000102528065,"threshold_uncertainty_score":0.48983893},"labels":[],"label_agreement":null},{"id":"W1979886455","doi":"10.3758/brm.41.2.452","title":"Corroborating biased indicators: Global and local agreement among objective and subjective estimates of printed word frequency","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":24,"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 Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; University of Ottawa","keywords":"Word lists by frequency; Variance (accounting); Selection (genetic algorithm); Frequency; Word (group theory); Age of Acquisition; Psychology; Variable (mathematics); Statistics; Computer science; Cognitive psychology; Variation (astronomy); Econometrics; Mathematics; Natural language processing; Artificial intelligence; Cognition","score_opus":0.1119647348854283,"score_gpt":0.5289141928556063,"score_spread":0.41694945797017796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979886455","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":[0.9754545,0.00053399295,0.019276045,0.00005166503,0.00010716268,0.00080918195,0.000020055239,0.000042073545,0.0037052967],"genre_scores_gemma":[0.8711616,0.000011433267,0.1285173,0.000013186622,0.0000194379,0.00015211714,0.000008971643,0.000011554739,0.00010443218],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99630564,0.0016570196,0.00044852437,0.0005889506,0.00044199664,0.00055788027],"domain_scores_gemma":[0.9981682,0.00082484854,0.00015365225,0.00031964152,0.00028524414,0.0002484327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040063886,0.00020775858,0.00037117876,0.0004153086,0.00019114104,0.00007145197,0.00019124795,0.00015926971,0.000120459204],"category_scores_gemma":[0.0007093102,0.00018380128,0.000042516258,0.0010059738,0.00067894394,0.00012223083,0.000117600575,0.00048456775,0.0000048126667],"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":[0.00009491798,0.00024409412,0.48109066,0.000014453926,0.00003874632,0.00005351375,0.005630791,4.029346e-7,0.0032244865,0.0010946239,0.000031057065,0.5084823],"study_design_scores_gemma":[0.00064686936,0.0005483983,0.9853525,0.00013336784,0.000029276613,0.000026936736,0.0041355467,0.000049888145,0.00700091,0.0018719648,0.000027634514,0.00017668912],"about_ca_topic_score_codex":0.0012336319,"about_ca_topic_score_gemma":0.000032644963,"teacher_disagreement_score":0.50830555,"about_ca_system_score_codex":0.00022446369,"about_ca_system_score_gemma":0.00012569556,"threshold_uncertainty_score":0.7495199},"labels":[],"label_agreement":null},{"id":"W1984681595","doi":"10.3758/s13428-014-0544-1","title":"A simple algorithm for the offline recalibration of eye-tracking data through best-fitting linear transformation","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","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 British Columbia","funders":"Economic and Social Research Council","keywords":"Computer science; Eye tracking; MATLAB; Artificial intelligence; Transformation (genetics); Computer vision; Algorithm; Eye movement; Tracking (education)","score_opus":0.4242559375345631,"score_gpt":0.5898099072666028,"score_spread":0.16555396973203967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984681595","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":[0.0050679194,0.00010503104,0.9923224,0.0014248017,0.0001334842,0.00070269,0.000030414316,0.0001274653,0.00008583406],"genre_scores_gemma":[0.08858836,0.000032062246,0.9109723,0.000026102016,0.00011508204,0.00015641643,0.000052762156,0.000016686845,0.000040260853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996904,0.0012041719,0.00046645408,0.00046909956,0.00050752907,0.00044870167],"domain_scores_gemma":[0.9951755,0.0026732667,0.00014922518,0.0014526678,0.0005026356,0.000046741538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013211007,0.00012593878,0.00023252965,0.00016333461,0.0004557476,0.00012417954,0.002204257,0.0001320051,0.000005751126],"category_scores_gemma":[0.0017137476,0.00009312831,0.000070973576,0.0007792538,0.00022249276,0.0008974133,0.00046354643,0.0004721422,0.0000036087981],"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":[0.00000446297,0.00009420087,0.00018312149,0.000022699025,0.000008401713,5.0228357e-7,0.00044605552,0.000023475508,0.01160359,0.0067888666,0.00007195725,0.98075265],"study_design_scores_gemma":[0.00039447763,0.0003002211,0.002038889,0.000037587244,0.00002772214,0.0000047519993,0.00029340154,0.8938765,0.08092231,0.005091466,0.016884161,0.00012852754],"about_ca_topic_score_codex":0.00015288193,"about_ca_topic_score_gemma":0.000012718522,"teacher_disagreement_score":0.98062414,"about_ca_system_score_codex":0.000029922008,"about_ca_system_score_gemma":0.00008554702,"threshold_uncertainty_score":0.4578698},"labels":[],"label_agreement":null},{"id":"W1985548644","doi":"10.3758/brm.40.3.858","title":"Recovering data from scanned graphs: Performance of Frantz’s g3data software","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":18,"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":"Natural Sciences and Engineering Research Council of Canada; Trent University","keywords":"Computer science; Software; Computer graphics (images); Programming language","score_opus":0.5383671611823693,"score_gpt":0.5695334473161054,"score_spread":0.031166286133736176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985548644","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":[0.2581378,0.00026689615,0.7402887,0.000062151565,0.00023720955,0.00023614077,0.0005060102,0.00012305379,0.00014204864],"genre_scores_gemma":[0.058614057,0.00091551425,0.9393123,0.000043329816,0.000048480582,0.00002274262,0.00057423045,0.000023642333,0.0004456953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966233,0.0008840977,0.00040117934,0.0006863535,0.0009625881,0.0004425033],"domain_scores_gemma":[0.9956142,0.0005708561,0.00010336364,0.0031954302,0.00033397635,0.00018222697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039749295,0.0001346462,0.00026641967,0.0003737711,0.0003222853,0.00011078694,0.0046678213,0.00007989619,0.00015062767],"category_scores_gemma":[0.0011325293,0.00012741581,0.000049355716,0.0014725887,0.00026141354,0.0014446492,0.0030262058,0.00035540195,0.000044884007],"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":[0.000054763077,0.00081132713,0.15311454,0.000117453725,0.00007041169,0.00014005786,0.0011738928,0.000029253426,0.028736617,0.001477609,0.021001657,0.79327244],"study_design_scores_gemma":[0.002079111,0.0007601271,0.29762134,0.00045285875,0.00007256311,0.000092250455,0.0003352228,0.49684373,0.12504567,0.0015888774,0.07375501,0.0013532613],"about_ca_topic_score_codex":0.0004261503,"about_ca_topic_score_gemma":0.000017258331,"teacher_disagreement_score":0.7919192,"about_ca_system_score_codex":0.00003138557,"about_ca_system_score_gemma":0.00025354634,"threshold_uncertainty_score":0.86740506},"labels":[],"label_agreement":null},{"id":"W1986294108","doi":"10.3758/brm.41.3.833","title":"Using Noldus Observer XT for research on deaf signers learning to read: An innovative methodology","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","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":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Speech recognition; Psychology","score_opus":0.9560280300315404,"score_gpt":0.7934256045912061,"score_spread":0.1626024254403342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986294108","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":[0.9411017,0.00007676983,0.04927581,0.0016963927,0.00025269034,0.0024949152,0.0000063224716,0.00014569613,0.0049497257],"genre_scores_gemma":[0.3695243,0.0000062125496,0.6247605,0.00022166237,0.00020412533,0.0009653924,0.000033824883,0.000071437236,0.004212545],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9598912,0.0359767,0.0005636867,0.0009460358,0.0009094429,0.0017129187],"domain_scores_gemma":[0.9886458,0.0073680556,0.00009494728,0.0015744014,0.0018947974,0.00042202484],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.06747407,0.00024904832,0.0004531834,0.001707034,0.0010536823,0.00015754695,0.0012024804,0.0004228134,0.00044318385],"category_scores_gemma":[0.0063282154,0.00024754155,0.000097262135,0.0034501797,0.00038555902,0.000205954,0.00031457073,0.0025487698,0.00012253715],"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":[0.0013123887,0.0010873091,0.002883595,0.000011825583,0.000034749195,0.000027850208,0.01483632,0.00008579135,0.19968848,0.023670757,0.0009084092,0.7554525],"study_design_scores_gemma":[0.0054447013,0.046854522,0.6144824,0.000340097,0.000107848806,0.000080484366,0.08931092,0.0016846177,0.07906203,0.015504519,0.14507633,0.0020515285],"about_ca_topic_score_codex":0.0015811088,"about_ca_topic_score_gemma":0.00003634383,"teacher_disagreement_score":0.753401,"about_ca_system_score_codex":0.0005184249,"about_ca_system_score_gemma":0.0002785005,"threshold_uncertainty_score":0.9999977},"labels":[],"label_agreement":null},{"id":"W1989587788","doi":"10.3758/brm.41.3.699","title":"Web-based image norming: How do object familiarity and visual complexity ratings compare when collected in-lab versus online?","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"University of Toronto Scarborough; University of Toronto","keywords":"Psychology; Web application; Artificial intelligence; Computer science; Cognitive psychology; Statistics; Information retrieval; World Wide Web; Mathematics","score_opus":0.4874111073272016,"score_gpt":0.5725089247469776,"score_spread":0.08509781741977596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989587788","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":[0.9957209,0.000022918912,0.0009867151,0.0010335381,0.000137444,0.001030363,0.00013608523,0.00013489144,0.00079714076],"genre_scores_gemma":[0.90953755,0.000046146306,0.08978447,0.00017444459,0.00004781107,0.00008594253,0.000059024962,0.000023110986,0.00024147125],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9923133,0.0050830725,0.0003125697,0.00073916087,0.00084921625,0.0007026829],"domain_scores_gemma":[0.9972568,0.0017674773,0.00007836435,0.0002769033,0.00032978962,0.0002906618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029912973,0.00023879627,0.00037682845,0.0005956036,0.0005142984,0.00038676607,0.00029620627,0.00013973397,0.00038402263],"category_scores_gemma":[0.0038432046,0.00023755514,0.000080309204,0.0013850266,0.0006593856,0.00030530762,0.0001230449,0.001090465,0.000022155054],"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":[0.00057641027,0.00088624493,0.0049130213,0.00002807233,0.0000011490918,0.000057297064,0.00044642246,4.2247626e-7,0.9165933,0.000031338997,0.00042700334,0.0760393],"study_design_scores_gemma":[0.010782146,0.0019276225,0.6582109,0.00013947698,0.000031010648,0.000029942688,0.0021993073,0.03400148,0.28832665,0.0005283184,0.0030538028,0.00076933333],"about_ca_topic_score_codex":0.00027593324,"about_ca_topic_score_gemma":0.0007517748,"teacher_disagreement_score":0.6532979,"about_ca_system_score_codex":0.00024228383,"about_ca_system_score_gemma":0.00029068525,"threshold_uncertainty_score":0.96872175},"labels":[],"label_agreement":null},{"id":"W1990092159","doi":"10.3758/bf03192808","title":"BatMon II: Children’s category norms for 33 categories","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Categorization; Cognitive psychology; Developmental psychology; Linguistics; Computer science; Artificial intelligence","score_opus":0.16915305304255768,"score_gpt":0.545034962112387,"score_spread":0.3758819090698293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990092159","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":[0.96556157,0.001150121,0.006170488,0.00073132967,0.0008928555,0.001982227,0.00007222772,0.0002655648,0.023173641],"genre_scores_gemma":[0.8309465,0.000017890394,0.08732497,0.00006602521,0.00096184004,0.0021896048,0.00026085746,0.00012312569,0.07810916],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961742,0.0010265572,0.00042477614,0.00076159136,0.00050802284,0.0011048471],"domain_scores_gemma":[0.998284,0.00060090673,0.00008137308,0.00056306954,0.00029389476,0.00017674672],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0050916607,0.0002537095,0.00034862116,0.00032384228,0.0009317661,0.00010456948,0.00048238112,0.00022412027,0.0011763416],"category_scores_gemma":[0.00025614136,0.00021726728,0.00018001955,0.0004743104,0.00030320016,0.00008910657,0.00023936096,0.00076503586,0.00020613208],"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":[0.00045479744,0.0020729115,0.26335788,0.000044726883,0.0001112031,0.00007407899,0.0038012639,0.0000048623315,0.02532972,0.085551,0.06208649,0.5571111],"study_design_scores_gemma":[0.0008033921,0.00046321482,0.84437764,0.000010049868,0.000026941012,0.000034289347,0.0003941363,0.0000032539212,0.0050568604,0.002409224,0.146115,0.00030599535],"about_ca_topic_score_codex":0.0028307599,"about_ca_topic_score_gemma":0.00009556698,"teacher_disagreement_score":0.58101976,"about_ca_system_score_codex":0.00015637661,"about_ca_system_score_gemma":0.00016157732,"threshold_uncertainty_score":0.9997367},"labels":[],"label_agreement":null},{"id":"W1991251969","doi":"10.3758/s13428-012-0219-8","title":"Design of a noninvasive face mask for ocular occlusion in rats and assessment in a visual discrimination paradigm","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","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":"Queen's University","funders":"","keywords":"Monocular; Visual cortex; Neuroscience; Computer science; Monocular deprivation; Computer vision; Artificial intelligence; Psychology; Ocular dominance","score_opus":0.4670633180786287,"score_gpt":0.6305032203990433,"score_spread":0.16343990232041455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991251969","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":[0.9692292,0.00009319436,0.02742853,0.0002814591,0.00012577104,0.0027865206,0.0000074594213,0.000011276051,0.00003654009],"genre_scores_gemma":[0.9849221,0.00031281053,0.013830437,0.000050632934,0.000018941195,0.0007489828,7.2568724e-7,0.000023009661,0.00009235742],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.989879,0.0074469605,0.00035480512,0.00057718065,0.0007891336,0.00095293],"domain_scores_gemma":[0.99507505,0.0043653715,0.00007222187,0.00021187517,0.0000696772,0.00020581094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011182705,0.00014667255,0.00027817127,0.00091043575,0.00020227142,0.000049980394,0.0003719078,0.0000950348,0.000016913302],"category_scores_gemma":[0.0021641739,0.00013143214,0.000041066214,0.0012482173,0.0005321965,0.00050034514,0.00039840039,0.0007454608,0.0000023078633],"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":[0.00016667502,0.0008562197,0.010531286,0.000044751134,5.4112786e-7,0.00010995476,0.0009191259,0.000015271757,0.9705557,0.00033683263,0.000008528396,0.016455067],"study_design_scores_gemma":[0.0008367211,0.000682216,0.047562025,0.000027508351,0.000006244422,0.00003308571,0.00029294344,0.0046747564,0.9454422,0.00027195067,0.00005455556,0.00011576278],"about_ca_topic_score_codex":0.000034422475,"about_ca_topic_score_gemma":0.0000040946816,"teacher_disagreement_score":0.03703074,"about_ca_system_score_codex":0.00013607112,"about_ca_system_score_gemma":0.00027019932,"threshold_uncertainty_score":0.53596467},"labels":[],"label_agreement":null},{"id":"W1993000953","doi":"10.3758/s13428-013-0373-7","title":"The effective number of parameters in post hoc models","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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 Alberta","funders":"","keywords":"Post hoc; Simple (philosophy); Computer science; Set (abstract data type); Context (archaeology); Monte Carlo method; Statistics; Mathematics","score_opus":0.34766603907049415,"score_gpt":0.6206011347065685,"score_spread":0.2729350956360744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993000953","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":[0.44163048,0.00006256395,0.55258185,0.00017343755,0.00008736123,0.0019559753,0.00001649165,0.00002247202,0.0034693726],"genre_scores_gemma":[0.069400005,0.000030731637,0.9288191,0.000009122594,0.000012402557,0.0015482744,7.223442e-7,0.000026192874,0.00015343251],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915985,0.0064325915,0.0004562743,0.0002942855,0.00060695823,0.0006114257],"domain_scores_gemma":[0.96677566,0.03180181,0.00008465715,0.00057831686,0.0006148164,0.00014472472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010489044,0.00014590708,0.00035516577,0.00012986574,0.00014722277,0.000091589805,0.00047229693,0.000119204204,0.00024047178],"category_scores_gemma":[0.010377032,0.00009247549,0.0000929687,0.00056317955,0.00058169145,0.00014414816,0.00020964687,0.0006779306,0.000041570445],"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":[0.000045092158,0.00020120172,0.0009925881,0.000039598137,0.000012589645,0.000007899517,0.0004144563,3.6598092e-7,0.0035267964,0.26662013,0.00017570314,0.72796357],"study_design_scores_gemma":[0.0002623248,0.00020340654,0.016804744,0.000053915188,0.00001452229,0.0000068938875,0.0005706375,0.0011424222,0.0072702235,0.97351736,0.000033150558,0.00012038347],"about_ca_topic_score_codex":0.0009117645,"about_ca_topic_score_gemma":0.000030589992,"teacher_disagreement_score":0.7278432,"about_ca_system_score_codex":0.000088384586,"about_ca_system_score_gemma":0.000083229184,"threshold_uncertainty_score":0.99795896},"labels":[],"label_agreement":null},{"id":"W1993078811","doi":"10.3758/brm.42.3.809","title":"Automatic detection and quantification of growth spurts","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Infant Health and Development","field":"Health Professions","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":"McGill University","funders":"","keywords":"Growth spurt; Computer science; Statistics; Mathematics; Medicine","score_opus":0.41912270103037413,"score_gpt":0.6821904125655601,"score_spread":0.263067711535186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993078811","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":[0.98780304,0.000042750344,0.007902667,0.00028647794,0.00075091666,0.0014830001,0.000005252657,0.000064775995,0.0016611109],"genre_scores_gemma":[0.8276562,0.000045111825,0.17104997,0.00003462087,0.00008374422,0.0007197376,0.0000050632716,0.000017968265,0.0003875935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954316,0.0027732893,0.00056047353,0.0002508578,0.0004453285,0.0005384704],"domain_scores_gemma":[0.99687576,0.001674081,0.00014964833,0.00034381682,0.00071847654,0.000238242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015603453,0.00008647108,0.00020406084,0.0003834232,0.0007941279,0.000009404919,0.00013763111,0.00023894038,0.00043911845],"category_scores_gemma":[0.0026780874,0.00007410431,0.000024900684,0.00043890424,0.00017248836,0.00009427094,0.00011703786,0.0013585425,0.00006334705],"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":[0.00003496725,0.000077557066,0.051975086,0.00052171893,0.0000033775868,0.0000021543815,0.001898512,1.0878704e-8,0.46652514,0.0026426727,0.00019994943,0.47611883],"study_design_scores_gemma":[0.00040834863,0.00010309261,0.9289102,0.00007104387,0.000010322202,0.000006184964,0.00096025097,0.00040091283,0.062005777,0.0015660517,0.005448612,0.000109217675],"about_ca_topic_score_codex":0.00075608946,"about_ca_topic_score_gemma":0.0002157404,"teacher_disagreement_score":0.8769351,"about_ca_system_score_codex":0.00006254522,"about_ca_system_score_gemma":0.0004874217,"threshold_uncertainty_score":0.610787},"labels":[],"label_agreement":null},{"id":"W1995383499","doi":"10.3758/s13428-011-0078-8","title":"Exploiting human sensitivity to gaze for tracking the eyes","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":16,"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; Killam Trusts","keywords":"Gaze; Eye movement; Eye tracking; Saccade; Fixation (population genetics); Computer vision; Covert; Computer science; Artificial intelligence; Eye–hand coordination; Visual search; Psychology; Optometry; Cognitive psychology; Medicine; Population","score_opus":0.6849314061675018,"score_gpt":0.6082399704273977,"score_spread":0.07669143574010406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995383499","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":[0.2597966,0.000023534416,0.7379359,0.0005707902,0.00012737076,0.00062236213,0.0000027703445,0.00027695496,0.00064373703],"genre_scores_gemma":[0.55605596,8.343115e-7,0.44332558,0.000037040274,0.00004524456,0.00038752696,4.538601e-7,0.000013789453,0.00013359624],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960656,0.0018848359,0.0002430158,0.0005897505,0.00040130122,0.00081550534],"domain_scores_gemma":[0.9967578,0.0016129843,0.00005874071,0.00096175954,0.00046642876,0.0001422595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014782162,0.00014830352,0.00021232489,0.00032102413,0.0009508668,0.00018573066,0.0012420306,0.000101110505,0.000012551117],"category_scores_gemma":[0.0015158969,0.00011093326,0.000111174886,0.00076674164,0.0002527097,0.00022102088,0.0006675229,0.00059399544,0.000020974121],"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":[0.0000068892173,0.00014187602,0.003253894,0.000009622111,0.000007839385,0.000044000855,0.002096463,6.1370787e-7,0.20182475,0.050344735,0.00020545062,0.7420639],"study_design_scores_gemma":[0.0003541244,0.0006328621,0.29585555,0.00007662028,0.000020023817,0.00006195468,0.001417751,0.00079797336,0.6781983,0.01777416,0.0043821186,0.00042857954],"about_ca_topic_score_codex":0.00021525547,"about_ca_topic_score_gemma":0.00005099591,"teacher_disagreement_score":0.74163526,"about_ca_system_score_codex":0.00006788393,"about_ca_system_score_gemma":0.000055447348,"threshold_uncertainty_score":0.73133945},"labels":[],"label_agreement":null},{"id":"W1998133270","doi":"10.3758/brm.40.4.1075","title":"Body—object interaction ratings for 1,618 monosyllabic nouns","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":117,"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; University of Northern British Columbia","funders":"","keywords":"Noun; Referent; Set (abstract data type); Generalizability theory; Object (grammar); Word (group theory); Computer science; Psychology; Concreteness; Natural language processing; Artificial intelligence; Cognitive psychology; Mathematics; Linguistics; Developmental psychology","score_opus":0.5842658790059307,"score_gpt":0.6586748091934802,"score_spread":0.07440893018754946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998133270","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":[0.6953915,0.000100421326,0.29004747,0.00066407275,0.0019384543,0.0019264185,0.000018941426,0.0002442136,0.009668554],"genre_scores_gemma":[0.7770761,0.0000694359,0.16078065,0.00024842197,0.00078128313,0.0034192952,0.00017153409,0.000118431875,0.0573348],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962744,0.0018768922,0.00043134083,0.00048180355,0.00042422093,0.00051135867],"domain_scores_gemma":[0.99725604,0.0011798877,0.00012945912,0.00047133057,0.0008120282,0.00015123225],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037496542,0.00015191709,0.00022129246,0.00041403953,0.0006856381,0.00006135405,0.00024393435,0.00020809428,0.0033002815],"category_scores_gemma":[0.0012441745,0.0001512054,0.0001277341,0.00072732155,0.00016551396,0.00029050288,0.00005408024,0.00053565257,0.0003266608],"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":[0.0008232461,0.0019230015,0.076633655,0.000069771726,0.00012489942,0.00007549641,0.015276446,0.000024530651,0.24990103,0.00779699,0.1293712,0.51797974],"study_design_scores_gemma":[0.0033470602,0.0014002752,0.36504012,0.000039005416,0.0000651117,0.00028709313,0.0065718866,0.0031383352,0.053220145,0.0006937164,0.56548184,0.00071538595],"about_ca_topic_score_codex":0.00026407346,"about_ca_topic_score_gemma":0.000015308633,"teacher_disagreement_score":0.51726437,"about_ca_system_score_codex":0.00023988898,"about_ca_system_score_gemma":0.00013838518,"threshold_uncertainty_score":0.9976108},"labels":[],"label_agreement":null},{"id":"W1998804905","doi":"10.3758/s13428-013-0315-4","title":"Internal consistency: Reports of its death are premature","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personality Traits and Psychology","field":"Psychology","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":"Queen's University","funders":"","keywords":"Consistency (knowledge bases); Internal consistency; Reliability (semiconductor); Psychology; Personality; Stability (learning theory); Social psychology; Cognitive psychology; Clinical psychology; Computer science; Psychometrics; Artificial intelligence","score_opus":0.4210199386381068,"score_gpt":0.6174052493332904,"score_spread":0.1963853106951836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998804905","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":[0.92428106,0.0027187504,0.0006612038,0.0010127664,0.001220664,0.0012243387,0.000040938234,0.00006645047,0.06877384],"genre_scores_gemma":[0.94400865,0.000030022897,0.035190303,0.00021779042,0.00019535131,0.00093272194,0.000011901785,0.00005110764,0.01936217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99419457,0.003221139,0.0006303277,0.0006409461,0.0005734814,0.0007395523],"domain_scores_gemma":[0.99704224,0.0006905223,0.00025071495,0.00093068177,0.0008002613,0.00028560543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055275136,0.00019003471,0.00045999384,0.0003258627,0.00013261351,0.00004899973,0.0004524162,0.00036042635,0.015328627],"category_scores_gemma":[0.0006740502,0.0001586117,0.00018815987,0.00038742338,0.0004158575,0.000109915745,0.00014788953,0.0010572502,0.0002521167],"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":[0.00029142876,0.00301731,0.42640507,0.00026635974,0.00035984817,0.0023207695,0.009118342,2.8094792e-7,0.13023666,0.014752282,0.10572362,0.30750802],"study_design_scores_gemma":[0.00037838638,0.00028108197,0.96916234,0.0000849921,0.000031524803,0.00082641485,0.0013420017,0.0000025616569,0.0028354174,0.0018947388,0.02297291,0.0001876065],"about_ca_topic_score_codex":0.00082159333,"about_ca_topic_score_gemma":0.000023507064,"teacher_disagreement_score":0.5427573,"about_ca_system_score_codex":0.000044722667,"about_ca_system_score_gemma":0.00008596646,"threshold_uncertainty_score":0.9855715},"labels":[],"label_agreement":null},{"id":"W1998828876","doi":"10.3758/s13428-013-0441-z","title":"Error bars in within-subject designs: a comment on Baguley (2012)","year":2014,"lang":"en","type":"letter","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":129,"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":"Plot (graphics); Computer science; Standard error; Set (abstract data type); Subject (documents); Confidence interval; Factor (programming language); Statistics; Data set; Error bar; Algorithm; Artificial intelligence; Mathematics","score_opus":0.8313740192000905,"score_gpt":0.6323470359685018,"score_spread":0.19902698323158863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998828876","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":[0.013209691,0.002867739,0.0015928335,0.914748,0.0072306315,0.008271839,0.00027335272,0.0005177722,0.051288158],"genre_scores_gemma":[0.0021991523,0.00018715294,0.040870313,0.8891234,0.0043358468,0.016477047,0.000439632,0.0005269493,0.045840528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96871537,0.023608174,0.001231693,0.002106619,0.0017490694,0.0025890898],"domain_scores_gemma":[0.99243474,0.004540807,0.00030851204,0.0020905894,0.00028823738,0.0003371314],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.017489763,0.00096636557,0.00158439,0.0012194904,0.00045412543,0.00016337044,0.0018665089,0.002879915,0.009969467],"category_scores_gemma":[0.0004919665,0.0007412399,0.00042397174,0.0011490929,0.0009840648,0.00008164076,0.00046946315,0.013992212,0.00255783],"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":[0.00030086332,0.0011405224,0.0018913546,0.000048747956,0.00006282963,0.0026604414,0.0008637261,4.2503896e-7,0.0001811614,0.00026163764,0.9161835,0.07640484],"study_design_scores_gemma":[0.0011996201,0.0022979835,0.026648277,0.00020696364,0.000090000234,0.000059971033,0.0003341938,0.0000010236635,0.00010573047,0.0007700484,0.9674231,0.0008631029],"about_ca_topic_score_codex":0.0020229092,"about_ca_topic_score_gemma":0.000066579305,"teacher_disagreement_score":0.075541735,"about_ca_system_score_codex":0.000501864,"about_ca_system_score_gemma":0.00008629739,"threshold_uncertainty_score":0.99950385},"labels":[],"label_agreement":null},{"id":"W2000645851","doi":"10.3758/s13428-013-0395-1","title":"Statistical power of latent growth curve models to detect quadratic growth","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":71,"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 Sherbrooke","funders":"","keywords":"Latent growth modeling; Growth curve (statistics); Statistics; Statistical model; Growth model; Quadratic equation; Statistical power; Computer science; Power (physics); Econometrics; Quadratic model; Mathematics; Mathematical economics","score_opus":0.38843895614225343,"score_gpt":0.555385129510922,"score_spread":0.16694617336866857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000645851","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":[0.071789704,0.000038831295,0.9251871,0.00030439947,0.000101286896,0.0014596488,0.00011232906,0.00007244165,0.0009342721],"genre_scores_gemma":[0.20482498,0.000009020585,0.7939335,0.00003401789,0.000030423185,0.0007218253,0.00000478899,0.000053281252,0.00038814242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939854,0.0023862007,0.0007561349,0.00054372597,0.0013720492,0.0009564644],"domain_scores_gemma":[0.98943627,0.007910431,0.00008062033,0.0005213849,0.001298275,0.0007530009],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037767866,0.0002649481,0.00067807926,0.0003100034,0.00013902306,0.000085187894,0.00053857215,0.00014904421,0.002320022],"category_scores_gemma":[0.007226448,0.00020100438,0.00012623607,0.0008863974,0.00038387006,0.000173794,0.00038148137,0.00066859904,0.00028233542],"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":[0.00021918726,0.0022579087,0.0019174952,0.0006193525,0.00013443612,0.000175961,0.0023526049,0.000003230074,0.033222303,0.6707295,0.017584564,0.27078345],"study_design_scores_gemma":[0.0003730319,0.0010712817,0.015733201,0.000053468877,0.000051227613,0.00001215287,0.00017351321,0.0023661808,0.015874103,0.9639201,0.000038101014,0.00033361872],"about_ca_topic_score_codex":0.0014207134,"about_ca_topic_score_gemma":0.000007801286,"teacher_disagreement_score":0.29319063,"about_ca_system_score_codex":0.000109270324,"about_ca_system_score_gemma":0.000101281374,"threshold_uncertainty_score":0.998592},"labels":[],"label_agreement":null},{"id":"W2002429320","doi":"10.3758/s13428-013-0327-0","title":"Pupil diameter measurement errors as a function of gaze direction in corneal reflection eyetrackers","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":155,"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":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pupillometry; Gaze; Pupillary response; Pupil; Eye tracking; Psychology; Nonverbal communication; Cognitive psychology; Computer vision; Reflection (computer programming); Task (project management); Artificial intelligence; Computer science; Communication","score_opus":0.3221110839369203,"score_gpt":0.5182101067454136,"score_spread":0.19609902280849328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002429320","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":[0.660297,0.00011992235,0.33635226,0.00048985187,0.0005671523,0.00077677687,5.3487673e-7,0.00035749725,0.0010390169],"genre_scores_gemma":[0.861295,0.00001677989,0.13792023,0.000013402832,0.000022132494,0.00055131665,8.615917e-7,0.000018797855,0.00016151981],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953907,0.0021517528,0.00039542763,0.00055708934,0.00096913474,0.0005358558],"domain_scores_gemma":[0.9981115,0.0002733346,0.00011240446,0.00060641667,0.0007878356,0.00010849615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00830446,0.00014689949,0.00024658008,0.0010445924,0.00011199655,0.0000876354,0.00051979464,0.00018969511,0.000050816063],"category_scores_gemma":[0.0010129103,0.00013655877,0.000086509106,0.0018282802,0.0002137367,0.00042975627,0.00018238762,0.00074023183,0.000056178473],"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":[0.000021263793,0.00030371675,0.012971772,0.000014099432,0.000009449155,0.0000060703846,0.00014977137,0.0000046027835,0.31209075,0.00084127253,0.00025537904,0.67333186],"study_design_scores_gemma":[0.00043440948,0.00085769984,0.9106695,0.00006344055,0.000011206637,0.000014152655,0.00020468642,0.0010022268,0.08098774,0.0045094956,0.0010655288,0.00017988915],"about_ca_topic_score_codex":0.0018669221,"about_ca_topic_score_gemma":0.0001561983,"teacher_disagreement_score":0.89769775,"about_ca_system_score_codex":0.0004220768,"about_ca_system_score_gemma":0.00013225502,"threshold_uncertainty_score":0.55687046},"labels":[],"label_agreement":null},{"id":"W2002467630","doi":"10.3758/s13428-014-0502-y","title":"Semantic properties, aptness, familiarity, conventionality, and interpretive diversity scores for 84 metaphors and similes","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":45,"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; McGill University","funders":"","keywords":"Simile; Salient; Metaphor; Interpretation (philosophy); Psychology; Literal and figurative language; Cognitive psychology; Meaning (existential); Cognition; Diversity (politics); Linguistics; Expression (computer science); Computer science; Artificial intelligence; Sociology; Philosophy","score_opus":0.2521318354855341,"score_gpt":0.5103424258964011,"score_spread":0.258210590410867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002467630","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":[0.9769268,0.0018325653,0.018327026,0.00014910943,0.00031940828,0.0013104832,0.00008276918,0.00005641344,0.0009954287],"genre_scores_gemma":[0.99104416,0.00008789251,0.006900125,0.00007225847,0.00008872956,0.0005494773,0.00002576098,0.000026384247,0.0012052018],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948602,0.0033716324,0.00025583888,0.0006152491,0.000419024,0.00047807532],"domain_scores_gemma":[0.99770546,0.0012956478,0.00006903977,0.00033086864,0.00041127883,0.00018767832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007398142,0.00018741992,0.0003525927,0.0002649237,0.00060757174,0.00010580347,0.00026469352,0.0001705202,0.00029142346],"category_scores_gemma":[0.0012473759,0.0001545244,0.000108345055,0.00022479192,0.0008667881,0.00015156038,0.0006360695,0.00037899494,0.000014477845],"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":[0.0015423215,0.0013703146,0.42574537,0.0007967566,0.00048040503,0.000050416642,0.028504146,1.5222379e-7,0.035834856,0.03942308,0.0017172196,0.46453497],"study_design_scores_gemma":[0.002913757,0.0013367964,0.9162977,0.00030817967,0.0007251347,0.00007557527,0.015156161,0.0005443481,0.014372466,0.04403945,0.0034364047,0.0007940669],"about_ca_topic_score_codex":0.0021552742,"about_ca_topic_score_gemma":0.00019370655,"teacher_disagreement_score":0.4905523,"about_ca_system_score_codex":0.000042300002,"about_ca_system_score_gemma":0.000036437283,"threshold_uncertainty_score":0.63013226},"labels":[],"label_agreement":null},{"id":"W2003491767","doi":"10.3758/s13428-011-0158-9","title":"Wayfinding: The effects of large displays and 3-D perception","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":22,"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; McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Simulator sickness; Perception; Computer science; Landmark; Depth perception; Human–computer interaction; Stereoscopy; Virtual reality; Virtual machine; Stereopsis; Psychology; Computer vision","score_opus":0.19493293637273648,"score_gpt":0.5042521348622732,"score_spread":0.3093191984895367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003491767","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":[0.9800974,0.00014872158,0.017785478,0.000009792643,0.0001368322,0.00038599025,0.0000042882853,0.000050414183,0.0013810829],"genre_scores_gemma":[0.98855525,0.00010667111,0.011093033,0.0000041386256,0.00002559681,0.00013469976,0.0000050334183,0.000015200249,0.00006038976],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989457,0.00046528035,0.0001086597,0.00009229111,0.00019818684,0.00018984839],"domain_scores_gemma":[0.9993632,0.00035227643,0.0000123570435,0.00014043623,0.0000755583,0.000056188124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018728732,0.000059619088,0.00008182324,0.00010801144,0.00010280773,0.000013267716,0.00009005621,0.000057849884,0.0001444733],"category_scores_gemma":[0.00025380487,0.00004389109,0.0000282537,0.00021577247,0.000085682645,0.00007012873,0.000042840955,0.00024566986,0.000010676971],"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":[0.00001712492,0.000082103514,0.007761095,0.00017641525,0.000010481881,0.0000056774225,0.004351302,3.230647e-7,0.74064034,0.0011559473,0.00017724736,0.24562193],"study_design_scores_gemma":[0.00039006196,0.00017203942,0.6815888,0.00006104758,0.000031561158,0.000005650448,0.0006737914,0.0010883876,0.3146573,0.0007891172,0.00043760668,0.00010457784],"about_ca_topic_score_codex":0.00004648935,"about_ca_topic_score_gemma":0.000005719396,"teacher_disagreement_score":0.67382777,"about_ca_system_score_codex":0.000022238899,"about_ca_system_score_gemma":0.0000061202713,"threshold_uncertainty_score":0.17898268},"labels":[],"label_agreement":null},{"id":"W2005020967","doi":"10.3758/brm.42.1.109","title":"Subjective frequency norms for 330 Spanish simple and compound words","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","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 Ottawa","funders":"","keywords":"Noun; Normative; Psychology; Verb; Consistency (knowledge bases); Reliability (semiconductor); Linguistics; Dependency (UML); Test (biology); Cognitive psychology; Mathematics; Statistics; Social psychology; Natural language processing; Artificial intelligence; Computer science","score_opus":0.22443089424841303,"score_gpt":0.5912289163641797,"score_spread":0.36679802211576673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005020967","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":[0.97962373,0.00014308722,0.0071524554,0.00016635505,0.0010214463,0.0012464065,0.000052927746,0.00007404802,0.010519522],"genre_scores_gemma":[0.66485804,0.000008939391,0.3263459,0.000044341683,0.00027057235,0.0017330844,0.000043604567,0.000059249167,0.006636292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968649,0.000974317,0.0003338833,0.0006265123,0.00036359765,0.0008368039],"domain_scores_gemma":[0.9966706,0.0020127532,0.0000633608,0.0005820104,0.00037473335,0.0002965291],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074346014,0.00019003055,0.00030374763,0.00032021492,0.00042559372,0.00017991703,0.00035851018,0.00022100443,0.0009638294],"category_scores_gemma":[0.00072092994,0.00016403683,0.000080287435,0.00038770871,0.00036297023,0.0001272644,0.00013390722,0.0010255964,0.000056276433],"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":[0.0001835971,0.00053607026,0.23480822,0.000042232783,0.00007464724,0.00008753281,0.01165502,3.687924e-8,0.109649695,0.019601883,0.0037350864,0.619626],"study_design_scores_gemma":[0.0012966275,0.00045644835,0.83682376,0.000017895356,0.00003158015,0.00013049922,0.0020511537,0.000011684353,0.0077329776,0.017025374,0.13400792,0.00041410912],"about_ca_topic_score_codex":0.0011298665,"about_ca_topic_score_gemma":0.000176413,"teacher_disagreement_score":0.61921185,"about_ca_system_score_codex":0.00006986959,"about_ca_system_score_gemma":0.00013251453,"threshold_uncertainty_score":0.9999494},"labels":[],"label_agreement":null},{"id":"W2006342589","doi":"10.3758/brm.40.1.263","title":"Rebus puzzles as insight problems","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":88,"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","funders":"","keywords":"Computer science; Psychology","score_opus":0.47439013244181594,"score_gpt":0.5834460447021849,"score_spread":0.10905591226036893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006342589","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":[0.017916856,0.00047058403,0.95733285,0.0029760385,0.00013564738,0.0013254636,0.000004210096,0.00039553846,0.01944283],"genre_scores_gemma":[0.064700596,0.00042645476,0.92205024,0.00012347924,0.00010469543,0.0023111082,0.000011062025,0.000039692066,0.010232684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952083,0.0019601092,0.00033833532,0.00068596425,0.0011131456,0.00069413794],"domain_scores_gemma":[0.99682426,0.0006506666,0.000065848806,0.0016668173,0.0004625135,0.00032991453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045518493,0.00015184544,0.00020448059,0.00040507622,0.0008068583,0.00014845612,0.0020564906,0.0001313159,0.0000845077],"category_scores_gemma":[0.0004909442,0.00013710556,0.000089181005,0.0019287391,0.00047076785,0.00045232286,0.0009729812,0.000723174,0.000466364],"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":[0.000009580212,0.0012931636,0.0017432522,0.00003753549,0.000029423443,0.00030348348,0.0056922925,0.000049145696,0.11103437,0.14397855,0.009982412,0.72584677],"study_design_scores_gemma":[0.0009644667,0.00050310587,0.046988584,0.00006422809,0.00002086726,0.0010621299,0.00023788105,0.0061198794,0.1556134,0.031273812,0.7562715,0.0008801506],"about_ca_topic_score_codex":0.00050141546,"about_ca_topic_score_gemma":0.000023511691,"teacher_disagreement_score":0.7462891,"about_ca_system_score_codex":0.00017656977,"about_ca_system_score_gemma":0.00046692253,"threshold_uncertainty_score":0.62057835},"labels":[],"label_agreement":null},{"id":"W2007579756","doi":"10.3758/brm.41.3.736","title":"An improved screw-free method for electrode implantation and intracranial electroencephalographic recordings in mice","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","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":"University of Toronto; Toronto Western Hospital","funders":"","keywords":"GLUE; Cyanoacrylate; Electrode; Isoflurane; Biomedical engineering; Hippocampal formation; Electroencephalography; Skull; Materials science; Medicine; Surgery; Anesthesia; Chemistry; Layer (electronics); Composite material","score_opus":0.15867781067207018,"score_gpt":0.5680586405988695,"score_spread":0.40938082992679925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007579756","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":[0.9767483,0.000049112354,0.01952847,0.0011118181,0.00015128501,0.002229637,0.000025529942,0.00009670203,0.000059148748],"genre_scores_gemma":[0.85258365,0.0006285428,0.1445397,0.0010002899,0.00015701908,0.0009172326,0.0000033143901,0.000052514617,0.00011777066],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9897436,0.0059998333,0.0004459699,0.001435617,0.0006422656,0.0017327466],"domain_scores_gemma":[0.9957339,0.003065464,0.000089505236,0.000501953,0.0002108313,0.00039835056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010416409,0.00024772747,0.00036742652,0.0013721624,0.00064385525,0.00027137628,0.0012717718,0.00016997372,0.000018882656],"category_scores_gemma":[0.0042124917,0.00024686303,0.000085230684,0.0024310823,0.00045411361,0.00076922885,0.00013930014,0.001427648,0.0000023599528],"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":[0.00064383354,0.00028783886,0.0003196399,0.000009426772,7.476815e-7,0.00009050532,0.0000978171,5.248969e-7,0.76735675,0.0003611108,0.000035427325,0.23079638],"study_design_scores_gemma":[0.0015856939,0.004091462,0.015658796,0.0000075651233,0.000014211669,0.0003289961,0.000045970257,0.0061624153,0.96522814,0.0064631775,0.00017620885,0.00023738292],"about_ca_topic_score_codex":0.00010751405,"about_ca_topic_score_gemma":0.000053690597,"teacher_disagreement_score":0.230559,"about_ca_system_score_codex":0.000086975015,"about_ca_system_score_gemma":0.0002165194,"threshold_uncertainty_score":0.9999984},"labels":[],"label_agreement":null},{"id":"W2010248328","doi":"10.3758/brm.42.1.82","title":"Norms for two types of manipulability (graspability and functional usage), familiarity, and age of acquisition for 320 photographs of objects","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":58,"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":"Object (grammar); Set (abstract data type); Psychology; Cognitive psychology; Point (geometry); Contrast (vision); Social psychology; Computer science; Artificial intelligence; Mathematics","score_opus":0.2881918808271415,"score_gpt":0.5612557759404353,"score_spread":0.2730638951132938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010248328","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":[0.9013166,0.000045745535,0.09667958,0.000032541793,0.00024112263,0.001350921,0.000114054026,0.000011802063,0.00020766599],"genre_scores_gemma":[0.93016857,0.0000071127974,0.06918266,0.000007979238,0.000035258818,0.00035700577,0.00008313902,0.000012919907,0.00014537203],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9981948,0.0006040931,0.000422161,0.00032389731,0.00026457355,0.00019048013],"domain_scores_gemma":[0.99698085,0.0014771672,0.00015775955,0.00033481524,0.0009738116,0.00007559699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005889684,0.00009435162,0.00028230227,0.00022570057,0.00010707683,0.000011556396,0.000088736786,0.00016369509,0.00033302393],"category_scores_gemma":[0.000944479,0.00008681008,0.0000869139,0.0003539895,0.0006165436,0.00010368523,0.000057294943,0.00020570504,2.8344306e-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":[0.00046838392,0.0005311749,0.41425964,0.0002925092,0.00002758753,2.081193e-7,0.00069136143,0.0000012981858,0.5439815,0.0047636623,0.00004571323,0.034936976],"study_design_scores_gemma":[0.0012096553,0.00042687866,0.9314773,0.000008841209,0.00003977397,0.0000025960517,0.00051201205,0.00038734177,0.059955668,0.005721725,0.00018222716,0.00007599684],"about_ca_topic_score_codex":0.00048447787,"about_ca_topic_score_gemma":0.0002834994,"teacher_disagreement_score":0.51721764,"about_ca_system_score_codex":0.000018877854,"about_ca_system_score_gemma":0.00005832559,"threshold_uncertainty_score":0.36463782},"labels":[],"label_agreement":null},{"id":"W2010891396","doi":"10.3758/s13428-010-0030-3","title":"Can computer mice be used as low-cost devices for the acquisition of planar human movement velocity signals?","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":13,"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; Context (archaeology); Movement (music); Data acquisition; Tracking (education); Computer vision; Artificial intelligence; Work (physics); Motion (physics); Human–computer interaction; Planar; Simulation; Acoustics; Computer graphics (images); Psychology; Engineering","score_opus":0.3409888756271376,"score_gpt":0.5554284158859369,"score_spread":0.21443954025879935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010891396","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":[0.99042755,0.0000026115113,0.00571559,0.0015122038,0.0004409988,0.0014968694,0.0001754751,0.000034584104,0.00019413044],"genre_scores_gemma":[0.983129,0.000004660287,0.014804337,0.0007217608,0.00020289197,0.0005808839,0.000015061996,0.000026461548,0.0005149248],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99708164,0.0010938679,0.00030524613,0.00040174992,0.0006764057,0.00044111392],"domain_scores_gemma":[0.99432003,0.004639175,0.00012332591,0.00048749193,0.0002959114,0.00013408686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017735946,0.00013556865,0.0001892214,0.00019679885,0.00086418126,0.00014189833,0.00058624137,0.000097015,0.00037327976],"category_scores_gemma":[0.00052850397,0.00010227111,0.00012966084,0.00030696305,0.00033879705,0.00016999712,0.000101081685,0.0007065994,0.00001188806],"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":[0.00004797653,0.00026789305,0.00037401507,0.000018661935,0.0000068930713,0.000007584726,0.0006258057,0.0000059180843,0.9823442,0.001776186,0.00045106717,0.014073762],"study_design_scores_gemma":[0.0003053987,0.00020069919,0.012643999,0.000015804535,0.000024702278,0.000008530448,0.00046785452,0.000507617,0.9787184,0.00045671628,0.0065389816,0.000111276844],"about_ca_topic_score_codex":0.0013083707,"about_ca_topic_score_gemma":0.0012018677,"teacher_disagreement_score":0.013962486,"about_ca_system_score_codex":0.000056934867,"about_ca_system_score_gemma":0.00009154244,"threshold_uncertainty_score":0.66466707},"labels":[],"label_agreement":null},{"id":"W2012306139","doi":"10.3758/bf03193896","title":"Measuring online volitional response control with a continuous tracking task","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":22,"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":"Task (project management); Computer science; Reliability (semiconductor); Context (archaeology); Response time; TRACE (psycholinguistics); Control (management); Tracking (education); Measure (data warehouse); Association (psychology); Human–computer interaction; Simulation; Artificial intelligence; Data mining; Psychology; Engineering; Power (physics)","score_opus":0.6035913841167487,"score_gpt":0.5851437254619571,"score_spread":0.018447658654791588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012306139","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":[0.9958124,0.000115594055,0.0010355655,0.001291236,0.00015898266,0.0008213873,0.00017659283,0.00016343126,0.00042480533],"genre_scores_gemma":[0.9851809,0.0000064720143,0.011552479,0.00019555683,0.00019458783,0.00036707218,0.0000067855312,0.0000446288,0.0024514971],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9914129,0.0052524954,0.00039252723,0.0008516443,0.0010909901,0.0009994549],"domain_scores_gemma":[0.9964944,0.002424685,0.00009491494,0.0004212523,0.00039647022,0.00016825747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004377349,0.00025870375,0.00039336082,0.0003761164,0.0007116294,0.0001290584,0.00045847532,0.000113035865,0.00009584338],"category_scores_gemma":[0.0012867259,0.00019162154,0.00011646847,0.00066660246,0.0010435509,0.00023030776,0.000121659694,0.00095924916,0.00005228716],"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":[0.0017191737,0.0008662304,0.014714691,0.000005649193,0.0000036889369,0.0007472993,0.000051598203,0.000002960955,0.9613341,0.00014255162,0.00031782416,0.020094251],"study_design_scores_gemma":[0.0026183247,0.0010048926,0.50586265,0.000054188928,0.000052757947,0.00043875002,0.00018720138,0.000017939903,0.4825074,0.00073954114,0.006119445,0.00039687345],"about_ca_topic_score_codex":0.0001872809,"about_ca_topic_score_gemma":0.00004526041,"teacher_disagreement_score":0.49114797,"about_ca_system_score_codex":0.000113478585,"about_ca_system_score_gemma":0.00009557262,"threshold_uncertainty_score":0.7814099},"labels":[],"label_agreement":null},{"id":"W2013137720","doi":"10.3758/brm.42.3.671","title":"Controlling low-level image properties: The SHINE toolbox","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":1232,"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; Université de Montréal","funders":"Université de Montréal","keywords":"Toolbox; Computer science; Image (mathematics); Artificial intelligence; Programming language","score_opus":0.36229890259229897,"score_gpt":0.5548363531033043,"score_spread":0.1925374505110053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013137720","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":[0.2888849,0.00006303125,0.70625734,0.0018120622,0.0010202458,0.0007606089,0.000002614024,0.00018607899,0.0010131344],"genre_scores_gemma":[0.70192015,0.000010268489,0.2950708,0.000121823636,0.00019466435,0.00045645982,0.0000010147529,0.000020137017,0.0022046757],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99610674,0.0016921436,0.00030283918,0.00045993726,0.0008657763,0.00057255867],"domain_scores_gemma":[0.99783903,0.00041472696,0.000055887955,0.00096858136,0.00055431924,0.00016742144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011358384,0.00013721673,0.00016961721,0.00020402414,0.000739239,0.00071066624,0.0015363661,0.000100850106,0.00013681673],"category_scores_gemma":[0.0013086371,0.000083241015,0.00012353752,0.00083752564,0.00031570267,0.0005878976,0.00035931956,0.0012298381,0.0001532107],"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":[0.00001052214,0.00011019232,0.00009152148,0.0000068987883,0.0000036318206,0.0000089076575,0.00038967864,9.0613037e-7,0.7066262,0.002631,0.00013372657,0.28998682],"study_design_scores_gemma":[0.0018440342,0.0006112485,0.04446325,0.000063964864,0.000027369519,0.00015689271,0.00086549204,0.08585244,0.8295188,0.0044323467,0.031424817,0.0007393275],"about_ca_topic_score_codex":0.00016317218,"about_ca_topic_score_gemma":0.000046894445,"teacher_disagreement_score":0.41303527,"about_ca_system_score_codex":0.000039478833,"about_ca_system_score_gemma":0.00012997769,"threshold_uncertainty_score":0.68529713},"labels":[],"label_agreement":null},{"id":"W2014721111","doi":"10.3758/brm.42.2.366","title":"Applying the permutation test to factorial designs","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":22,"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":"Permutation (music); Factorial; Fractional factorial design; Parametric statistics; Factorial experiment; Resampling; Mathematics; Computation; Limit (mathematics); Computer science; Test (biology); Algorithm; Statistics","score_opus":0.773946312954811,"score_gpt":0.7301019632369032,"score_spread":0.04384434971790774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014721111","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":[0.27137265,0.000059036167,0.7065371,0.00086721306,0.004397093,0.0077433586,0.00003478499,0.00015419169,0.00883458],"genre_scores_gemma":[0.22307844,0.0000013566142,0.76867574,0.0000882955,0.0005779443,0.005193413,0.0000019616377,0.00004228043,0.0023405731],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98392695,0.008940059,0.0007818003,0.0009818561,0.004453657,0.0009156653],"domain_scores_gemma":[0.96042836,0.035858408,0.00013177702,0.0017355456,0.001277749,0.0005681377],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.083144024,0.00023555632,0.00034890446,0.00072152563,0.0010510096,0.0012881161,0.0026493943,0.00020687553,0.0019380576],"category_scores_gemma":[0.08366858,0.00014447318,0.0001807228,0.003008227,0.00051262253,0.00042561203,0.0007507112,0.0015902177,0.001065831],"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":[0.00002846074,0.00008799047,0.002206996,5.861946e-7,0.0000017174015,0.0000073642263,0.0006991784,0.000004281858,0.62276196,0.00072649436,0.0011738605,0.3723011],"study_design_scores_gemma":[0.00046170017,0.00064292573,0.039532736,0.0000081743065,0.000017854998,0.000042099633,0.0041803312,0.0008135224,0.75725925,0.015219862,0.18138157,0.00043997492],"about_ca_topic_score_codex":0.00018863173,"about_ca_topic_score_gemma":0.000031660038,"teacher_disagreement_score":0.37186113,"about_ca_system_score_codex":0.00012025523,"about_ca_system_score_gemma":0.00027476472,"threshold_uncertainty_score":0.99974865},"labels":[],"label_agreement":null},{"id":"W2016329964","doi":"10.3758/s13428-012-0273-2","title":"Communicative and noncommunicative point-light actions featuring high-resolution representation of the hands and fingers","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":19,"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":"Gesture; Computer science; Motion (physics); Representation (politics); Point (geometry); Biological motion; Computer vision; Consistency (knowledge bases); Set (abstract data type); Perception; Artificial intelligence; Motion capture; Action (physics); Position (finance); Frame of reference; Sight; Human–computer interaction; Psychology; Mathematics","score_opus":0.44170687730108377,"score_gpt":0.6120041218654197,"score_spread":0.17029724456433598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016329964","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":[0.9865838,0.001820667,0.0006451783,0.0023775166,0.0001288929,0.0007434463,0.000005590805,0.00003377127,0.007661102],"genre_scores_gemma":[0.972303,0.00035503512,0.026013145,0.000014211917,0.00003052288,0.00036998332,0.000008949731,0.00001881337,0.00088636606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99133694,0.007537866,0.00027597405,0.00019296742,0.00027206464,0.00038415706],"domain_scores_gemma":[0.9960147,0.001841878,0.00015230557,0.001651057,0.00021563772,0.00012440846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005274372,0.000114043214,0.00020026675,0.00019448563,0.0007343226,0.000040364102,0.00055428635,0.00013101223,0.0000752647],"category_scores_gemma":[0.000577272,0.00009071172,0.00004901637,0.0006665476,0.00067306706,0.0002861139,0.0010016038,0.0008534124,0.0000056506206],"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":[0.00030286,0.0015447346,0.45516005,0.000047106223,0.0001890777,8.273656e-7,0.08618002,0.0000013739023,0.111902565,0.029273842,0.0017325311,0.313665],"study_design_scores_gemma":[0.0005742471,0.00012537149,0.971651,0.00005338168,0.00004882966,0.000014861906,0.0073680766,0.000027571914,0.0176163,0.00037115585,0.0020484221,0.00010076164],"about_ca_topic_score_codex":0.001507624,"about_ca_topic_score_gemma":0.000049654,"teacher_disagreement_score":0.51649094,"about_ca_system_score_codex":0.00009863223,"about_ca_system_score_gemma":0.000031519416,"threshold_uncertainty_score":0.564789},"labels":[],"label_agreement":null},{"id":"W2017115354","doi":"10.3758/brm.41.3.615","title":"A hybrid approach to experimental control","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Control Systems Optimization","field":"Engineering","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 Alberta","funders":"","keywords":"Computer science; Control (management); XML; Set (abstract data type); Programming language; Range (aeronautics); Object (grammar); Operating system; Artificial intelligence","score_opus":0.12827365322053494,"score_gpt":0.5035860982041628,"score_spread":0.3753124449836278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017115354","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":[0.026305264,0.0006393374,0.96160835,0.000041243573,0.00014772062,0.0015643365,0.000008871355,0.0004014992,0.009283392],"genre_scores_gemma":[0.6655609,0.0000029230866,0.3333866,0.0000282917,0.00009501046,0.0006913788,0.0000038188186,0.000033836586,0.00019723938],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977501,0.00060104305,0.00026478816,0.00030815354,0.00046602555,0.00060986815],"domain_scores_gemma":[0.99900657,0.00013469822,0.000014983596,0.0004351607,0.00012853532,0.00028004794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001873214,0.00016606868,0.00026839078,0.00029709536,0.000112890826,0.00007796048,0.00030140075,0.000061816856,0.000026192904],"category_scores_gemma":[0.00016900741,0.00016827299,0.000065148066,0.00036387306,0.00003227073,0.00017221156,0.000028811215,0.0003361943,0.00004688457],"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":[0.00006248876,0.00029851688,0.000054213466,0.000013363483,0.000017044944,0.000023561506,0.00039448758,0.08569439,0.73633146,0.00090765266,0.001107589,0.17509523],"study_design_scores_gemma":[0.0052847816,0.0011439788,0.0053590946,0.00006778868,0.000047025835,0.00014971833,0.001008842,0.5486223,0.416772,0.00056064315,0.019590326,0.001393508],"about_ca_topic_score_codex":0.000009202513,"about_ca_topic_score_gemma":1.6075784e-7,"teacher_disagreement_score":0.63925564,"about_ca_system_score_codex":0.00027170326,"about_ca_system_score_gemma":0.000019306954,"threshold_uncertainty_score":0.68619734},"labels":[],"label_agreement":null},{"id":"W2019158162","doi":"10.3758/brm.40.3.744","title":"SayWhen: An automated method for high-accuracy speech onset detection","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Computer science; Latency (audio); Speech recognition; Voice activity detection; Coding (social sciences); Key (lock); Software; Speech processing","score_opus":0.2683079724846872,"score_gpt":0.5790835721226062,"score_spread":0.310775599637919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019158162","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":[0.19673738,0.00009204677,0.8007649,0.00022910278,0.00032988068,0.00076024345,0.000008875599,0.0010013911,0.00007616423],"genre_scores_gemma":[0.0688486,0.000020615997,0.92990696,0.000073154966,0.00015684978,0.0005468991,0.0000115685325,0.000040402756,0.00039492254],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99369377,0.0029882768,0.00042472413,0.0009423107,0.0009114759,0.0010394228],"domain_scores_gemma":[0.9956493,0.0018849405,0.00012975791,0.0011167817,0.0008126944,0.00040655988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010512236,0.00024139383,0.00035328438,0.0006204788,0.001239315,0.00038368464,0.0015058875,0.00020501507,0.000037880392],"category_scores_gemma":[0.0022843718,0.00022599543,0.00012021229,0.0017015478,0.00017428942,0.0012670463,0.00036613984,0.00060691143,0.000033124288],"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":[0.000028145132,0.00015885783,0.00021678339,0.00001643681,0.000006370423,0.00007542011,0.00027500556,0.0000039404113,0.2802708,0.000069101254,0.0003849984,0.7184941],"study_design_scores_gemma":[0.0005692564,0.0005359841,0.0115327835,0.00001685014,0.000010860585,0.0004961943,0.00006433192,0.023000881,0.95803565,0.0025555813,0.002880903,0.00030072036],"about_ca_topic_score_codex":0.00038091015,"about_ca_topic_score_gemma":0.0000354619,"teacher_disagreement_score":0.7181934,"about_ca_system_score_codex":0.00018737785,"about_ca_system_score_gemma":0.00043886196,"threshold_uncertainty_score":0.9531934},"labels":[],"label_agreement":null},{"id":"W2019929444","doi":"10.3758/s13428-012-0204-2","title":"SPSS macros to compare any two fitted values from a regression model","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Applications","field":"Mathematics","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":"NOSM University; Lakehead University","funders":"","keywords":"Statistics; Mathematics; Polynomial regression; Regression analysis; Linear regression; Regression; Standard error; Macro; Confidence interval; Design matrix; Segmented regression; Computer science","score_opus":0.7862703712146977,"score_gpt":0.74524494245617,"score_spread":0.04102542875852766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019929444","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":[0.27485278,0.00011016321,0.72240996,0.00027272952,0.000091532376,0.0010028932,0.00027904255,0.00011324159,0.00086765457],"genre_scores_gemma":[0.12158646,0.0000069205107,0.8758675,0.00005331773,0.00021149944,0.0011299562,0.000022902539,0.0000613329,0.001060132],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942941,0.0028812883,0.00046279514,0.0004824547,0.0008862224,0.0009931575],"domain_scores_gemma":[0.991141,0.0065666893,0.0000785634,0.0010344612,0.00037855687,0.00080072513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072851833,0.00023353785,0.00045654486,0.00020434684,0.00042145766,0.00010083103,0.000549754,0.000086670516,0.00060316804],"category_scores_gemma":[0.0048350883,0.00018530407,0.00010792408,0.00067239715,0.00018611857,0.00012667077,0.0004775677,0.0006595823,0.00014465138],"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":[0.0001484885,0.0019895572,0.011356913,0.00008359051,0.000043217166,0.000015199196,0.004123973,0.000011326821,0.35428515,0.1501251,0.028615784,0.4492017],"study_design_scores_gemma":[0.0010817562,0.00010599346,0.038445845,0.0002662308,0.00018195444,0.000010318792,0.0013911114,0.018442804,0.12556244,0.80782133,0.0059244204,0.0007657805],"about_ca_topic_score_codex":0.0003452472,"about_ca_topic_score_gemma":0.000013528406,"teacher_disagreement_score":0.65769625,"about_ca_system_score_codex":0.00013663885,"about_ca_system_score_gemma":0.00006814358,"threshold_uncertainty_score":0.7556481},"labels":[],"label_agreement":null},{"id":"W2020571594","doi":"10.3758/s13428-014-0495-6","title":"Manipulability agreement as a predictor of action initiation latency","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","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":"McGill University; Douglas Mental Health University Institute; Université de Moncton","funders":"","keywords":"Agreement; Latency (audio); Computer science; Psychology; Action (physics); Physics; Telecommunications; Linguistics","score_opus":0.5568847796030505,"score_gpt":0.6374625389479308,"score_spread":0.08057775934488032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020571594","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":[0.84484863,0.000022434751,0.13861756,0.0002497578,0.0006783651,0.00071768183,0.00000585199,0.00006623414,0.014793476],"genre_scores_gemma":[0.9797771,0.0000118248345,0.01508768,0.000040681563,0.00013677451,0.0003497533,0.000052780146,0.000019244237,0.004524171],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99433464,0.0040309085,0.0004334664,0.00032769638,0.0005997672,0.0002735486],"domain_scores_gemma":[0.9980611,0.0004766146,0.00015256197,0.0005095411,0.00069282844,0.000107314634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0068351724,0.000097083655,0.0001683283,0.00027821457,0.00014822217,0.000023601699,0.00017467704,0.00016725661,0.008204522],"category_scores_gemma":[0.0013159505,0.00009454248,0.00006390452,0.00057326147,0.00012325306,0.00017976185,0.000055161974,0.00031415976,0.00026107416],"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":[0.00021190746,0.0013197759,0.26690158,0.00009763017,0.0000379633,0.0000028704808,0.0024370854,0.000011408171,0.07894564,0.02912403,0.001726078,0.619184],"study_design_scores_gemma":[0.0007608709,0.00050489075,0.9679729,0.000015802494,0.000022689888,0.000005497563,0.00091399753,0.00070644147,0.016324408,0.0024204776,0.010231023,0.00012105306],"about_ca_topic_score_codex":0.00033330283,"about_ca_topic_score_gemma":0.000021770422,"teacher_disagreement_score":0.70107126,"about_ca_system_score_codex":0.00017005905,"about_ca_system_score_gemma":0.000069975555,"threshold_uncertainty_score":0.9927021},"labels":[],"label_agreement":null},{"id":"W2021096528","doi":"10.3758/s13428-015-0576-1","title":"Is the cognitive reflection test a measure of both reflection and intuition?","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Learning Styles and Cognitive Differences","field":"Psychology","cited_by":254,"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":"Intuition; Cognition; Cognitive psychology; Psychology; Measure (data warehouse); Cognitive style; Computer science; Cognitive science; Data mining","score_opus":0.5571369298902951,"score_gpt":0.6457370586835582,"score_spread":0.08860012879326318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021096528","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":[0.9456202,0.0009845685,0.010237828,0.0007275888,0.0003465371,0.00097646745,0.000039143175,0.00006108811,0.04100659],"genre_scores_gemma":[0.99439526,0.000034275527,0.0019105689,0.00006613873,0.00011063066,0.00042641693,0.0000069389175,0.000020115875,0.0030296368],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943638,0.0041918973,0.00021758523,0.00036202354,0.0005426099,0.00032209296],"domain_scores_gemma":[0.99653137,0.0018853146,0.00009763047,0.0002148562,0.0011479392,0.00012289028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006927297,0.000117654046,0.00018195767,0.00022680244,0.00027729184,0.000062885396,0.00014613487,0.00013831537,0.0003484532],"category_scores_gemma":[0.0025887405,0.00008184575,0.000057323556,0.0006843635,0.00051759684,0.00008168406,0.000087420565,0.000704834,0.000036935373],"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":[0.00049513654,0.00065291027,0.14554308,0.00002048943,0.00008446428,0.000013133617,0.020658074,4.4489717e-8,0.01852267,0.0017599915,0.002473538,0.8097765],"study_design_scores_gemma":[0.0018008841,0.003423934,0.9223767,0.00016187553,0.00017606256,0.00009963363,0.043372124,0.000022206354,0.015168859,0.007961626,0.0051602134,0.00027591575],"about_ca_topic_score_codex":0.0010025585,"about_ca_topic_score_gemma":0.00006252261,"teacher_disagreement_score":0.8095006,"about_ca_system_score_codex":0.000054926426,"about_ca_system_score_gemma":0.000101731115,"threshold_uncertainty_score":0.3815318},"labels":[],"label_agreement":null},{"id":"W2022055962","doi":"10.3758/s13428-011-0069-9","title":"Response time accuracy in Apple Macintosh computers","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":61,"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","funders":"","keywords":"USB; Computer science; Computer hardware; Significant difference; Response time; Computer graphics (images); Operating system; Statistics; Mathematics; Software","score_opus":0.5416860349608625,"score_gpt":0.5790788147780557,"score_spread":0.037392779817193134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022055962","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":[0.992735,0.0000025124914,0.0039194156,0.00014154763,0.00027954855,0.0007719838,0.00000837689,0.000095654155,0.0020459434],"genre_scores_gemma":[0.94989157,0.000026790196,0.04633762,0.00044626172,0.000045822417,0.0003572707,0.0000016160158,0.000034964454,0.0028581005],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9909729,0.0063710376,0.00030620216,0.00078062614,0.0007532592,0.00081597007],"domain_scores_gemma":[0.99678886,0.0022302014,0.000051795905,0.0006306499,0.00006806383,0.00023044112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009710811,0.00014932296,0.00020207325,0.00072104554,0.00025846544,0.0000939629,0.0008571783,0.000090076464,0.0007874692],"category_scores_gemma":[0.0038888582,0.00013876146,0.00006951457,0.0015457127,0.0005772293,0.0004567758,0.0004094526,0.0006402782,0.0005363888],"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":[0.0003801209,0.00024988534,0.00017928345,0.000002640494,1.749769e-7,0.00019511027,0.0017205625,4.4044916e-7,0.9228041,0.00009359861,0.00074345985,0.07363059],"study_design_scores_gemma":[0.0006465577,0.00037557643,0.05533055,0.00002408852,0.000003275877,0.00008189449,0.00030354678,0.00067191373,0.9309809,0.00032597897,0.0110115055,0.00024418457],"about_ca_topic_score_codex":0.00021142121,"about_ca_topic_score_gemma":0.0000065074646,"teacher_disagreement_score":0.07338641,"about_ca_system_score_codex":0.00012591251,"about_ca_system_score_gemma":0.00015366706,"threshold_uncertainty_score":0.86222357},"labels":[],"label_agreement":null},{"id":"W2022075199","doi":"10.3758/brm.42.4.957","title":"Estimating the probability and fidelity of memory","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":20,"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; Fidelity; Variance (accounting); Probability distribution; Algorithm; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.444713486248623,"score_gpt":0.6297663182607204,"score_spread":0.18505283201209738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022075199","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":[0.4101766,0.000016114183,0.58790797,0.00015019432,0.00012329585,0.0005951888,0.0000135798255,0.000022946719,0.0009941066],"genre_scores_gemma":[0.07263844,0.0000010979584,0.92706364,0.0000059268705,0.000055916124,0.00017342402,3.8904955e-7,0.000013037273,0.000048139627],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99514323,0.0032524676,0.00043117692,0.00030530212,0.0005134206,0.00035442348],"domain_scores_gemma":[0.9830978,0.01540629,0.000098983444,0.0007773715,0.0004792468,0.00014030414],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027800307,0.00011025217,0.0002813722,0.00006413769,0.00024623456,0.000053835545,0.0003620678,0.00010516446,0.0002977112],"category_scores_gemma":[0.04467904,0.00006795126,0.00005263167,0.0002947333,0.0011722699,0.00005856246,0.0002978497,0.0010620687,0.0000017715101],"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":[0.000012394132,0.00014270685,0.0027095145,0.00016317802,0.0000050602534,0.00000294906,0.00038861908,4.8232533e-8,0.050925035,0.20458037,0.000079886515,0.7409902],"study_design_scores_gemma":[0.000111656685,0.00006820148,0.040133726,0.00002351797,0.00002348763,0.000013140503,0.00010967595,0.0013286802,0.015414609,0.94263136,0.000058894755,0.00008301709],"about_ca_topic_score_codex":0.00017267563,"about_ca_topic_score_gemma":0.000030472549,"teacher_disagreement_score":0.74090725,"about_ca_system_score_codex":0.000015525451,"about_ca_system_score_gemma":0.0001057321,"threshold_uncertainty_score":0.9635087},"labels":[],"label_agreement":null},{"id":"W2023736093","doi":"10.3758/s13428-012-0314-x","title":"Norms of valence, arousal, and dominance for 13,915 English lemmas","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1978,"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":"Psychology; Valence (chemistry); Stimulus (psychology); Taboo; Cognitive psychology; Arousal; Linguistics; Social psychology; Sociology","score_opus":0.22356297190789665,"score_gpt":0.5275938138999604,"score_spread":0.30403084199206376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023736093","genre_codex":"empirical","genre_gemma":"methods","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":[0.513875,0.00070979143,0.48321468,0.00021708784,0.00030432528,0.0009971914,0.0000052513597,0.00005063127,0.0006260438],"genre_scores_gemma":[0.16509892,0.00014161422,0.83266133,0.000017188962,0.00009993105,0.000503104,0.0000034702948,0.000013936962,0.0014605128],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99765575,0.0005294,0.0003477538,0.00047277624,0.0005222512,0.00047204533],"domain_scores_gemma":[0.99730086,0.0010401106,0.00010545917,0.00059879315,0.0008045727,0.00015020266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004983515,0.00011920707,0.0002919669,0.0003323755,0.00018964859,0.00023252063,0.00080587016,0.00007358289,0.00007024999],"category_scores_gemma":[0.00062597456,0.000098240096,0.00011024135,0.00071991514,0.00020459463,0.00055377814,0.00042518898,0.00020552438,0.000009594309],"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":[0.0000155234,0.00027807723,0.03933546,0.000094445495,0.000035814584,0.0000047136914,0.002668955,0.0000061072583,0.07092092,0.0083208345,0.0056250137,0.87269413],"study_design_scores_gemma":[0.004558884,0.0023601383,0.44114363,0.0003949822,0.0001444108,0.00002339056,0.0039620274,0.094942175,0.371912,0.016203396,0.06269742,0.0016575347],"about_ca_topic_score_codex":0.00017679256,"about_ca_topic_score_gemma":0.000004605906,"teacher_disagreement_score":0.8710366,"about_ca_system_score_codex":0.00002307694,"about_ca_system_score_gemma":0.00006227638,"threshold_uncertainty_score":0.4006115},"labels":[],"label_agreement":null},{"id":"W2025651983","doi":"10.3758/s13428-013-0399-x","title":"Subcutaneous dye injection for marking and identification of individual adult zebrafish (Danio rerio) in behavioral studies","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"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":"Zebrafish; Danio; Agonistic behaviour; Simplicity; Fish <Actinopterygii>; Animal behavior; Social behaviour; Psychology; Computer science; Biology; Neuroscience; Aggression; Zoology; Developmental psychology; Fishery; Physics","score_opus":0.16960624862176968,"score_gpt":0.5433258792030013,"score_spread":0.3737196305812317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025651983","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":[0.9941301,0.0006118437,0.002834817,0.00025596024,0.00006370258,0.0020008879,0.000061756255,0.000012103621,0.000028881763],"genre_scores_gemma":[0.9664203,0.00032363372,0.028856067,0.00002043998,0.00008503774,0.0038174023,0.00014540917,0.00003351587,0.00029819453],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99708813,0.0007799051,0.0005209685,0.0005361989,0.00056971196,0.0005050947],"domain_scores_gemma":[0.9978451,0.00034480606,0.000115967094,0.0004350801,0.001088266,0.00017075696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044907187,0.00013914905,0.00023086208,0.00035664393,0.00016442481,0.00008706542,0.0003810871,0.00021668785,0.000019229503],"category_scores_gemma":[0.0027786558,0.00013671996,0.000066245,0.0005057218,0.00061318075,0.000020715805,0.00040646282,0.00030675542,0.000003390379],"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":[0.000064049316,0.00022576455,0.004685153,0.000059457918,0.000021223274,0.0000019922074,0.00020454201,3.5918578e-7,0.8055475,0.00008146476,0.0008127733,0.18829572],"study_design_scores_gemma":[0.0015400401,0.0031752351,0.19187185,0.00008640072,0.00006433607,0.0000731233,0.0058567757,0.00017169064,0.79205376,0.0025073115,0.0021719986,0.000427506],"about_ca_topic_score_codex":0.00031345244,"about_ca_topic_score_gemma":0.0001802627,"teacher_disagreement_score":0.18786821,"about_ca_system_score_codex":0.0000726693,"about_ca_system_score_gemma":0.00012970199,"threshold_uncertainty_score":0.5575278},"labels":[],"label_agreement":null},{"id":"W2026427809","doi":"10.3758/s13428-012-0241-x","title":"Bayesian combination of two-dimensional location estimates","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimension (graph theory); Variable (mathematics); Task (project management); Bayesian probability; Computer science; Motion (physics); Artificial intelligence; Value (mathematics); Mathematics; Pattern recognition (psychology); Statistics; Algorithm","score_opus":0.44191674458838565,"score_gpt":0.6149044304039545,"score_spread":0.17298768581556884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026427809","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":[0.8477352,0.00009497235,0.14922687,0.00016837947,0.0004527299,0.00054082624,0.0000055454957,0.00010568071,0.0016697705],"genre_scores_gemma":[0.8848472,0.0000026379648,0.11462108,0.000050667135,0.000040865394,0.000075220836,0.000005232954,0.00001681279,0.00034025367],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99677,0.0016466641,0.00022661284,0.00022771883,0.000738543,0.0003904134],"domain_scores_gemma":[0.9985081,0.00073831086,0.000070093316,0.00021880964,0.0002941715,0.00017050022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005116518,0.00009098088,0.00013120449,0.0002840082,0.00025279884,0.0000413007,0.00020320743,0.00006784051,0.0006494455],"category_scores_gemma":[0.0020032672,0.00008261315,0.0000363221,0.0007650161,0.00021850126,0.00034074427,0.000096336444,0.00026955243,0.00008292493],"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":[0.000014059852,0.00055210385,0.0009448335,0.00002394632,5.240029e-7,7.4831775e-7,0.00028804105,0.000014434752,0.9234686,0.005884559,0.00005672867,0.06875143],"study_design_scores_gemma":[0.0002832399,0.00016332061,0.007642093,0.000026716483,0.00000743101,0.0000152739,0.00006423059,0.004349435,0.98311436,0.0041417712,0.000100690064,0.00009143224],"about_ca_topic_score_codex":0.000030670188,"about_ca_topic_score_gemma":5.914353e-7,"teacher_disagreement_score":0.068660006,"about_ca_system_score_codex":0.00005737641,"about_ca_system_score_gemma":0.00007629776,"threshold_uncertainty_score":0.7110973},"labels":[],"label_agreement":null},{"id":"W2026942731","doi":"10.3758/s13428-011-0090-z","title":"Redefining membership in animal groups","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Animal Behavior and Reproduction","field":"Agricultural and Biological Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SGS (Canada); University of Toronto","funders":"","keywords":"Shoal; Shoaling and schooling; Danio; Group cohesiveness; Herding; Flock; Group (periodic table); Collective motion; Computer science; Geography; Ecology; Zebrafish; Fishery; Artificial intelligence; Psychology; Biology; Social psychology; Geology; Physics; Oceanography","score_opus":0.589806443472049,"score_gpt":0.5161282013694632,"score_spread":0.07367824210258578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026942731","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":[0.9918409,0.00014384388,0.000005407541,0.00012271301,0.00011354942,0.00033011692,0.0000036431607,0.000069760856,0.0073700785],"genre_scores_gemma":[0.9868614,0.000023758399,0.012301745,0.000009147652,0.0001605156,0.00015843273,0.000009134577,0.0000022327172,0.00047364135],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9967967,0.0013840026,0.00026410318,0.00053629116,0.00041307596,0.00060578267],"domain_scores_gemma":[0.9993322,0.00023197556,0.000040565443,0.00011808914,0.00012556686,0.00015162812],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060971254,0.00012656987,0.0001820462,0.00007085881,0.0002390943,0.000042490014,0.00034546247,0.00015814025,0.0021898458],"category_scores_gemma":[0.00028813223,0.000051933926,0.000086535474,0.0009873324,0.0001880183,0.00017011572,0.00017048826,0.0005983787,0.00006579668],"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":[0.00009934796,0.00024617824,0.15346248,0.0000025305064,0.0000012584601,0.000042637937,0.00045742423,1.596817e-8,0.61652744,0.0007583096,0.000050640512,0.22835171],"study_design_scores_gemma":[0.00008044989,0.00053678337,0.949871,0.000012361149,0.000006251366,0.000021592346,0.0018614585,0.0000022836418,0.04577436,0.0005470728,0.0011426193,0.00014374981],"about_ca_topic_score_codex":0.0018871126,"about_ca_topic_score_gemma":0.0002960393,"teacher_disagreement_score":0.79640853,"about_ca_system_score_codex":0.00006452481,"about_ca_system_score_gemma":0.000013278682,"threshold_uncertainty_score":0.9987223},"labels":[],"label_agreement":null},{"id":"W2027900864","doi":"10.3758/s13428-012-0289-7","title":"SPSS and SAS programs for comparing Pearson correlations and OLS regression coefficients","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":287,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Rounding; Raw data; Computer science; Statistics; Pearson product-moment correlation coefficient; Regression analysis; Regression; Software; Data mining; Mathematics; Programming language","score_opus":0.6740604188140626,"score_gpt":0.6686980108350041,"score_spread":0.005362407979058514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027900864","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":[0.28674096,0.00012246087,0.7095298,0.00019588294,0.000044288558,0.0028837316,0.000015059019,0.000056378594,0.00041139804],"genre_scores_gemma":[0.09402148,0.000016248981,0.9024734,0.000004979472,0.00003557146,0.002634512,0.000011581373,0.000029296005,0.000772919],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99779224,0.00081344007,0.00028757274,0.00036477027,0.00032204468,0.0004199276],"domain_scores_gemma":[0.99380666,0.0052124527,0.00006657445,0.00031248532,0.00034396615,0.0002578449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035491218,0.00012874318,0.0002680264,0.00012452329,0.0004954975,0.00019862967,0.00013992091,0.00009780937,0.00005262835],"category_scores_gemma":[0.0029754739,0.000101340505,0.00003708845,0.00028421095,0.0003219618,0.00008562274,0.00018183168,0.00032409927,0.000007752385],"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":[0.0000124880935,0.00032341745,0.009413209,0.00010669993,0.000007793775,8.925254e-7,0.00040759493,1.21561e-7,0.007381381,0.062206637,0.0012385955,0.91890115],"study_design_scores_gemma":[0.0026242612,0.0007580825,0.24986131,0.0005783324,0.00023051433,0.000051162147,0.0033449682,0.03937764,0.0048076115,0.68319863,0.0143777765,0.0007896851],"about_ca_topic_score_codex":0.000093138755,"about_ca_topic_score_gemma":0.0000060088873,"teacher_disagreement_score":0.9181115,"about_ca_system_score_codex":0.000032640117,"about_ca_system_score_gemma":0.00002541254,"threshold_uncertainty_score":0.4132546},"labels":[],"label_agreement":null},{"id":"W2030751416","doi":"10.3758/brm.41.2.546","title":"Subjective frequency and imageability ratings for 3,600 French nouns","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":98,"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":"Noun; Reliability (semiconductor); Psychology; Audiology; Consistency (knowledge bases); Rating scale; Cognitive psychology; Computer science; Statistics; Natural language processing; Artificial intelligence; Developmental psychology; Mathematics; Medicine","score_opus":0.2242416127247494,"score_gpt":0.6053365934815501,"score_spread":0.3810949807568007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030751416","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":[0.961116,0.0005584164,0.020540783,0.0006375969,0.00037041635,0.0017996919,0.00003855497,0.000098147735,0.014840392],"genre_scores_gemma":[0.53265554,0.000008590246,0.45975417,0.00008385901,0.00012522755,0.0010463495,0.000018456638,0.000023978548,0.006283817],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99568963,0.0020568352,0.0003963248,0.0007307147,0.00035239873,0.00077409577],"domain_scores_gemma":[0.9968026,0.0018330776,0.00006743176,0.0005525704,0.00051113666,0.00023317641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0103765745,0.00018643161,0.00030842223,0.0002740973,0.0003756742,0.00013451933,0.00028401928,0.00016232222,0.00045560126],"category_scores_gemma":[0.001468236,0.00016520685,0.000090478796,0.00043615606,0.00026193375,0.00014752452,0.000057305264,0.0005930584,0.000029367518],"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":[0.00009410157,0.0006599697,0.10820231,0.00002924263,0.00002554232,0.0000400492,0.017506838,4.482363e-8,0.044787165,0.004765504,0.003073318,0.8208159],"study_design_scores_gemma":[0.00069973036,0.00069912506,0.9705245,0.000019085177,0.000018670493,0.000031257496,0.0008267036,0.000008428894,0.004248984,0.015175505,0.0075155343,0.0002324857],"about_ca_topic_score_codex":0.0007220718,"about_ca_topic_score_gemma":0.000011932101,"teacher_disagreement_score":0.8623222,"about_ca_system_score_codex":0.00014883654,"about_ca_system_score_gemma":0.00012780463,"threshold_uncertainty_score":0.67369395},"labels":[],"label_agreement":null},{"id":"W2034196084","doi":"10.3758/s13428-010-0029-9","title":"A computer-generated face database with ratings on realism, masculinity, race, and stereotypy","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":22,"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":"Masculinity; Psychology; Perception; Race (biology); Ethnic group; Set (abstract data type); Face perception; Face (sociological concept); Social psychology; Cognitive psychology; Computer science; Gender studies; Sociology","score_opus":0.358130814821676,"score_gpt":0.5455536191535534,"score_spread":0.18742280433187736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034196084","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":[0.9882775,0.0000042687175,0.009192457,0.0005843152,0.0002009865,0.0007870697,0.000101176876,0.000111695605,0.0007405297],"genre_scores_gemma":[0.643367,0.00022684733,0.352524,0.00066188787,0.0002884001,0.00041114248,0.00011254016,0.000086492146,0.0023216668],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9950956,0.0028791549,0.00020698576,0.00067677454,0.000686405,0.0004550636],"domain_scores_gemma":[0.9979304,0.0009946825,0.000056882684,0.0005045336,0.00019538355,0.00031809235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038609335,0.00017919026,0.00020937821,0.00028746677,0.00045221296,0.00028306802,0.0002661521,0.00012060921,0.0005041566],"category_scores_gemma":[0.0007719066,0.00013946721,0.000034121436,0.00060090184,0.0004595661,0.00024603354,0.00020414226,0.0013169376,0.000128462],"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":[0.000117308475,0.00019201558,0.00046060805,0.000016164358,0.0000014967565,0.00004781587,0.00038781122,0.0000017574586,0.84888947,0.00021693214,0.00058646605,0.14908214],"study_design_scores_gemma":[0.0019534263,0.0011401186,0.018386316,0.00008799836,0.000023235974,0.000259008,0.0003512191,0.004621176,0.9561323,0.00007799434,0.016480727,0.00048649206],"about_ca_topic_score_codex":0.0001499061,"about_ca_topic_score_gemma":0.000117435324,"teacher_disagreement_score":0.3449105,"about_ca_system_score_codex":0.000023344695,"about_ca_system_score_gemma":0.00008367707,"threshold_uncertainty_score":0.5721512},"labels":[],"label_agreement":null},{"id":"W2035770374","doi":"10.3758/s13428-014-0488-5","title":"Four types of manipulability ratings and naming latencies for a set of 560 photographs of objects","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":31,"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; Université de Moncton","funders":"","keywords":"Affordance; Comparability; USable; Set (abstract data type); Popularity; Computer science; Cognitive psychology; Psychology; Cognition; Human–computer interaction; Social psychology; Multimedia; Mathematics","score_opus":0.48768210256630884,"score_gpt":0.6016371807737658,"score_spread":0.11395507820745698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035770374","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":[0.94147086,0.00006040366,0.057034336,0.000034706976,0.000091660535,0.00058156525,0.000019089528,0.000012403272,0.0006949878],"genre_scores_gemma":[0.9099761,0.0000070528245,0.089533545,0.0000059970344,0.00001714032,0.000109255896,0.000008436776,0.000011700167,0.0003307512],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9977696,0.0012571187,0.0003675785,0.00019681526,0.00023899673,0.00016987881],"domain_scores_gemma":[0.9974927,0.0012702902,0.00018379891,0.00026763917,0.00074054435,0.000045030498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005766123,0.00006863305,0.00024683974,0.00022607371,0.00006571667,0.0000070036917,0.00011316844,0.00010054853,0.00020773085],"category_scores_gemma":[0.0017469123,0.000062860425,0.00006094353,0.0004088434,0.00026029337,0.000060821072,0.0000453836,0.00011907234,6.044626e-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":[0.00022571809,0.00025662078,0.31623712,0.00053741765,0.00004756134,4.862291e-7,0.008566368,0.0000057453676,0.4758696,0.0058285403,0.00014247367,0.19228236],"study_design_scores_gemma":[0.0014772768,0.0011096754,0.75951874,0.000074619726,0.00006435293,0.0000058406613,0.0061883624,0.002359688,0.22521392,0.0024908222,0.0013280732,0.00016860473],"about_ca_topic_score_codex":0.00038158853,"about_ca_topic_score_gemma":0.000033887954,"teacher_disagreement_score":0.44328165,"about_ca_system_score_codex":0.000015300115,"about_ca_system_score_gemma":0.000038099657,"threshold_uncertainty_score":0.25633737},"labels":[],"label_agreement":null},{"id":"W2037416776","doi":"10.3758/brm.42.3.847","title":"A general framework and an R package for the detection of dichotomous differential item functioning","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":288,"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":"Differential item functioning; R package; Set (abstract data type); Differential (mechanical device); Psychometrics; Item response theory; Computer science; Psychology; Cognitive psychology; Artificial intelligence; Developmental psychology; Programming language","score_opus":0.7240286491433732,"score_gpt":0.6707538589519908,"score_spread":0.05327479019138237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037416776","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":[0.5136876,0.00010002043,0.4848782,0.000043572338,0.00084157684,0.00037792922,0.0000066217603,0.000018839837,0.00004565116],"genre_scores_gemma":[0.6185635,0.000012934645,0.38063976,0.000006831375,0.00033666458,0.00021481661,7.2473847e-7,0.000013181761,0.00021159738],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936786,0.003488145,0.0005347093,0.00056838995,0.0012640557,0.00046606566],"domain_scores_gemma":[0.86268574,0.134658,0.0002576457,0.0012177534,0.00095415435,0.00022673643],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041738793,0.00012762654,0.00030229948,0.0006411377,0.00080209365,0.00040973406,0.00080990925,0.00020886371,0.00020636377],"category_scores_gemma":[0.20133327,0.000074320655,0.00012552261,0.0018749585,0.00045167486,0.00018832265,0.00027658237,0.0010347101,0.0000017504],"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":[0.00005341176,0.00004020192,0.017356362,0.0000030908695,0.000004898132,6.9185495e-7,0.00015712183,5.581072e-7,0.35986242,0.00041274072,0.000017669145,0.6220908],"study_design_scores_gemma":[0.00047067506,0.00080425304,0.8548586,0.000012217964,0.00004442828,0.000029331595,0.0015738779,0.007421458,0.08832646,0.04297403,0.003298538,0.00018613189],"about_ca_topic_score_codex":0.00018595847,"about_ca_topic_score_gemma":0.000052446885,"teacher_disagreement_score":0.83750224,"about_ca_system_score_codex":0.000015362084,"about_ca_system_score_gemma":0.000045698092,"threshold_uncertainty_score":0.9867316},"labels":[],"label_agreement":null},{"id":"W2037493627","doi":"10.3758/s13428-011-0182-9","title":"SOS! An algorithm and software for the stochastic optimization of stimuli","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":36,"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":"National Institute of Neurological Disorders and Stroke; University of Pittsburgh; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Carnegie Mellon University; University of Pennsylvania","keywords":"Computer science; Generality; Software; Python (programming language); Maximization; Machine learning; Usability; MATLAB; Toolbox; Artificial intelligence; Algorithm; Mathematical optimization; Human–computer interaction; Programming language; Mathematics","score_opus":0.6979840277782209,"score_gpt":0.6476718274083718,"score_spread":0.05031220036984907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037493627","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":[0.1996023,0.0005464985,0.7974934,0.00028367795,0.0004452045,0.0014855365,0.000074994714,0.00005510875,0.000013269861],"genre_scores_gemma":[0.282801,0.00009381323,0.7152261,0.00010553301,0.0002081248,0.0009928674,0.000005185074,0.00004399128,0.0005233358],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976657,0.0009934417,0.0001934677,0.0003141783,0.0003326797,0.00050052674],"domain_scores_gemma":[0.996768,0.0025179682,0.00005742644,0.00030373962,0.00021419018,0.00013867213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026842712,0.00011769682,0.00017692323,0.000113682516,0.00052678975,0.000032788306,0.00028974027,0.00007020079,0.00003891878],"category_scores_gemma":[0.0017655796,0.00007456891,0.000043494005,0.00039266076,0.00078333763,0.00025647343,0.00018869451,0.00027413503,0.0000020248985],"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":[0.000065231456,0.00049392716,0.0019144521,0.000014988291,0.0000038468843,0.0000019561621,0.0005416709,0.00019311762,0.1630609,0.000077664205,0.00016538164,0.8334668],"study_design_scores_gemma":[0.0039057194,0.0050563575,0.11938526,0.00008068826,0.0005680543,0.00023651942,0.0037634203,0.031377055,0.82932585,0.0017219511,0.0033211529,0.0012579836],"about_ca_topic_score_codex":0.000027790536,"about_ca_topic_score_gemma":0.0000011254209,"teacher_disagreement_score":0.8322089,"about_ca_system_score_codex":0.00001635917,"about_ca_system_score_gemma":0.000020502976,"threshold_uncertainty_score":0.40516943},"labels":[],"label_agreement":null},{"id":"W2038349824","doi":"10.3758/s13428-015-0585-0","title":"Disparity in organizational research: How should we measure it?","year":2015,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Gender Diversity and Inequality","field":"Social Sciences","cited_by":19,"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":"Program for New Century Excellent Talents in University; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Gini coefficient; Theil index; Statistics; Standard deviation; Econometrics; Inequality; Mathematics; Index (typography); Measure (data warehouse); Sample size determination; Economics; Computer science; Economic inequality","score_opus":0.9601976785276772,"score_gpt":0.72143815920155,"score_spread":0.23875951932612727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038349824","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":[0.000006465369,0.9742393,0.00024346956,0.0045169136,0.0004628732,0.0028928341,0.00015686842,0.000072473995,0.017408831],"genre_scores_gemma":[0.000031210093,0.9824255,0.007930765,0.000013410184,0.00050241314,0.0003554352,0.00012470412,0.000056817713,0.008559734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9149158,0.07537649,0.0005526145,0.0010259124,0.006395749,0.0017334492],"domain_scores_gemma":[0.9904394,0.0040104534,0.00015887959,0.00092999125,0.00353685,0.0009244318],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.16072904,0.00036364738,0.0014717525,0.0015330645,0.0016432486,0.0006600849,0.00253872,0.00133016,0.0013141031],"category_scores_gemma":[0.023061568,0.00033059774,0.00032646427,0.007069001,0.0018066106,0.0004442349,0.0013914461,0.0052231182,0.00027778393],"study_design_candidate":"not_applicable","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":[0.000008240766,0.00041095744,0.0005129691,0.0016830472,0.000026554017,0.000072407514,0.00682494,5.3686954e-8,0.0000010535267,0.007009178,0.035156913,0.9482937],"study_design_scores_gemma":[0.00014403486,0.000046811547,0.00011810619,0.0013780758,0.00007280357,0.000002287068,0.009569135,5.101619e-7,0.000001120191,0.0020189702,0.986322,0.00032617047],"about_ca_topic_score_codex":0.0051658484,"about_ca_topic_score_gemma":0.0039977063,"teacher_disagreement_score":0.9511651,"about_ca_system_score_codex":0.002594055,"about_ca_system_score_gemma":0.008024721,"threshold_uncertainty_score":0.9999663},"labels":[],"label_agreement":null},{"id":"W2039891070","doi":"10.3758/bf03192810","title":"SPSS and SAS programs for generalizability theory analyses","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":166,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Generalizability theory; Computer science; Psychology; Developmental psychology","score_opus":0.9596454361401149,"score_gpt":0.7860996307771648,"score_spread":0.17354580536295006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039891070","genre_codex":"empirical","genre_gemma":"methods","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":[0.53096986,0.0018392132,0.46192923,0.00016409303,0.00026971044,0.00120033,0.000017377333,0.00008295241,0.0035272632],"genre_scores_gemma":[0.08487267,0.000017585404,0.90919673,0.00001970989,0.00020056318,0.0005560144,0.000006884723,0.00002165477,0.0051081814],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98177874,0.0137589285,0.0008415174,0.0010433798,0.0017319266,0.0008454998],"domain_scores_gemma":[0.89558405,0.10147211,0.00019917676,0.0012035792,0.0013022721,0.00023882955],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14207996,0.00018254081,0.0005040048,0.000957665,0.0005476671,0.0006173577,0.00096600346,0.00015012221,0.00019782264],"category_scores_gemma":[0.15501313,0.00012058576,0.00021610637,0.0036897727,0.0007379934,0.0001900689,0.0004272142,0.00034880606,0.000007480075],"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":[0.00005243669,0.00016504627,0.11431914,0.0000089318455,0.0000065314525,0.0000046802165,0.000048626345,0.0000032703786,0.010093153,0.0034071368,0.0017797992,0.8701112],"study_design_scores_gemma":[0.00044884215,0.0002892646,0.38407546,0.000007947978,0.000030188243,0.000015343232,0.0008686789,0.00052961643,0.007087787,0.57022524,0.036201548,0.0002200477],"about_ca_topic_score_codex":0.0004167868,"about_ca_topic_score_gemma":0.00002452196,"teacher_disagreement_score":0.8698912,"about_ca_system_score_codex":0.000057628815,"about_ca_system_score_gemma":0.00009150364,"threshold_uncertainty_score":0.8834092},"labels":[],"label_agreement":null},{"id":"W2043356813","doi":"10.3758/s13428-012-0299-5","title":"Recurrence quantification analysis of eye movements","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":148,"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; University of British Columbia","funders":"","keywords":"Recurrence quantification analysis; Gaze; Eye movement; Fixation (population genetics); Computer science; Artificial intelligence; Context (archaeology); Nonlinear system; Geography; Medicine","score_opus":0.6078203590008676,"score_gpt":0.6485880780666875,"score_spread":0.040767719065819885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043356813","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":[0.9347575,0.000018919454,0.06318994,0.00010603459,0.00013650981,0.00052885694,0.000014896237,0.000044227912,0.0012031202],"genre_scores_gemma":[0.96077,0.000044191143,0.036254026,0.00005885561,0.000012591932,0.00030718057,0.000008748062,0.000012484738,0.0025319057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957912,0.0023016324,0.00032510576,0.0004448449,0.0008059668,0.00033127988],"domain_scores_gemma":[0.9984849,0.00043265257,0.000104885075,0.00046428916,0.00037930295,0.0001339341],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003726198,0.00009111444,0.00020938717,0.0008265675,0.00020623713,0.00011596278,0.00045836685,0.00007209662,0.002858568],"category_scores_gemma":[0.0018094344,0.00008054548,0.00010002673,0.0033050007,0.00021537395,0.0002465075,0.000111077185,0.00027408716,0.0002150097],"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":[0.0000045854085,0.00016236221,0.0016419484,0.000009432312,0.0000051117645,4.8968894e-7,0.00024864596,0.0000032674745,0.81730163,0.00058892585,0.000051841907,0.17998172],"study_design_scores_gemma":[0.000093050716,0.00009820579,0.10774595,0.000012009896,0.00004533155,2.9380908e-7,0.00026396083,0.004884387,0.8852714,0.0009988279,0.00048399644,0.00010260393],"about_ca_topic_score_codex":0.00017561816,"about_ca_topic_score_gemma":0.0000030723374,"teacher_disagreement_score":0.17987913,"about_ca_system_score_codex":0.000040764924,"about_ca_system_score_gemma":0.000049810456,"threshold_uncertainty_score":0.99805295},"labels":[],"label_agreement":null},{"id":"W2045164651","doi":"10.3758/s13428-013-0370-x","title":"Subjective frequency ratings for 432 ASL signs","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":62,"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":"National Institute on Deafness and Other Communication Disorders","keywords":"American Sign Language; Sign (mathematics); Psychology; Age of Acquisition; Sign language; Audiology; Word lists by frequency; Linguistics; Mathematics; Cognition; Medicine","score_opus":0.5161361651891855,"score_gpt":0.6621774302998505,"score_spread":0.14604126511066506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045164651","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":[0.9173585,0.00031613326,0.037806265,0.0013347317,0.00038198222,0.004310344,0.000010701721,0.00018308712,0.038298238],"genre_scores_gemma":[0.64922374,0.000009511892,0.32529268,0.000075811935,0.00015694297,0.011851741,0.00002397414,0.000058347705,0.013307277],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99468213,0.003565848,0.00030644445,0.00038219322,0.00032493664,0.0007384193],"domain_scores_gemma":[0.9960847,0.0021314644,0.00006381071,0.0009537774,0.00057712826,0.00018911621],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073465444,0.00013514902,0.0002027164,0.00025012516,0.0003949825,0.00012739582,0.0006179775,0.00018071261,0.0030957512],"category_scores_gemma":[0.0010027882,0.0001258398,0.00010903504,0.00043707126,0.00019867177,0.00019797416,0.00015781977,0.0006392899,0.0006535223],"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":[0.000051271745,0.00082576496,0.04551589,0.000021759866,0.000043457207,0.0000048423235,0.006185567,1.1854031e-7,0.337211,0.015519683,0.008412295,0.58620834],"study_design_scores_gemma":[0.001641486,0.0025624023,0.9186757,0.000043160508,0.00004677822,0.000018138162,0.00652748,0.00008948299,0.021813348,0.029857755,0.018184358,0.0005399014],"about_ca_topic_score_codex":0.002751239,"about_ca_topic_score_gemma":0.000021627204,"teacher_disagreement_score":0.8731598,"about_ca_system_score_codex":0.00013522859,"about_ca_system_score_gemma":0.00010416129,"threshold_uncertainty_score":0.99781555},"labels":[],"label_agreement":null},{"id":"W2046087187","doi":"10.3758/bf03192781","title":"Picture-naming norms for Canadian French: Name agreement, familiarity, visual complexity, and age of acquisition","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Normative; Age of Acquisition; Agreement; Psychology; Age groups; Nomination; Interpretation (philosophy); Age discrimination; Linguistics; Audiology; Demography; Medicine; Cognition; Sociology; Political science; Law","score_opus":0.29682124807064453,"score_gpt":0.535764501236298,"score_spread":0.2389432531656535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046087187","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":[0.995868,0.00010745506,0.0017230901,0.00015971402,0.00015708996,0.0009261994,0.00017847953,0.000027320262,0.00085260265],"genre_scores_gemma":[0.977103,0.0000130513645,0.021700809,0.00017321251,0.00013111837,0.00010554636,0.00007515254,0.000020845166,0.0006772439],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968858,0.0012004081,0.00032247053,0.00054014305,0.00035516714,0.0006960436],"domain_scores_gemma":[0.9982886,0.0010008991,0.00007433447,0.000282231,0.00015711544,0.00019685194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027275942,0.00016024076,0.00028219065,0.0004330952,0.00046351383,0.00007524916,0.00034687665,0.000151449,0.00010051923],"category_scores_gemma":[0.0006654624,0.00014102146,0.00008211006,0.00035647638,0.00086378655,0.00010509603,0.00020033655,0.00036730996,0.0000039888196],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016647533,0.00013473185,0.0073264376,0.000043039545,0.000002162017,0.00029926843,0.0003135048,4.989216e-7,0.9768193,0.0007360262,0.0001461086,0.014162319],"study_design_scores_gemma":[0.0010759637,0.000860699,0.16075456,0.000044587083,0.000037511083,0.00020204186,0.000341508,0.00024130836,0.82198703,0.010263966,0.0038000825,0.00039073368],"about_ca_topic_score_codex":0.06793102,"about_ca_topic_score_gemma":0.037940774,"teacher_disagreement_score":0.15483221,"about_ca_system_score_codex":0.00007987108,"about_ca_system_score_gemma":0.00013584508,"threshold_uncertainty_score":0.9796143},"labels":[],"label_agreement":null},{"id":"W2046573508","doi":"10.3758/brm.40.3.705","title":"WINDSOR: Windsor improved norms of distance and similarity of representations of semantics","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","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 Windsor","funders":"","keywords":"Windsor; Computer science; Similarity (geometry); Word (group theory); Semantic similarity; Semantics (computer science); Meaning (existential); Natural language processing; Lexical semantics; Cognition; Artificial intelligence; Lexical item; Linguistics; Psychology","score_opus":0.27716463127891805,"score_gpt":0.5285698993187112,"score_spread":0.2514052680397932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046573508","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":[0.42548692,0.00012604665,0.57383054,0.00010363717,0.000043810032,0.00025414905,0.000008776542,0.000012405186,0.00013367433],"genre_scores_gemma":[0.5483707,0.000049264872,0.45143154,0.000002168846,0.000009047908,0.000016225833,7.822016e-7,0.0000055594182,0.000114703944],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974415,0.00070494914,0.0005260808,0.00038022918,0.00064984575,0.00029744973],"domain_scores_gemma":[0.9973283,0.00071419834,0.0001799392,0.0010520123,0.00061603106,0.00010953099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003074482,0.000097542084,0.00033319276,0.00023908616,0.00012358667,0.000015112348,0.0007540128,0.00008373548,0.000007934919],"category_scores_gemma":[0.0007805201,0.00008939218,0.00007642639,0.00069441646,0.0005382302,0.0002582938,0.0005538431,0.00030732935,2.4857613e-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":[0.00005398123,0.0007908455,0.29932797,0.00038211714,0.000038865088,0.000029604977,0.007485661,0.00013443505,0.55437046,0.014533018,0.00006328651,0.12278972],"study_design_scores_gemma":[0.00094662514,0.00036374523,0.35813013,0.00008976018,0.000028761922,0.00003802686,0.0004983808,0.09217617,0.5433983,0.0038925044,0.00018233106,0.00025527377],"about_ca_topic_score_codex":0.000424564,"about_ca_topic_score_gemma":0.00001864886,"teacher_disagreement_score":0.12288378,"about_ca_system_score_codex":0.00002364415,"about_ca_system_score_gemma":0.00017993052,"threshold_uncertainty_score":0.36453074},"labels":[],"label_agreement":null},{"id":"W2047223150","doi":"10.3758/s13428-013-0378-2","title":"The transitional impact scale: Assessing the material and psychological impact of life transitions","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Hospital Edmonton; University of Alberta","funders":"","keywords":"Varimax rotation; Cronbach's alpha; Psychology; Scale (ratio); Event (particle physics); Statistics; Internal consistency; Factor analysis; Clinical psychology; Psychometrics; Mathematics; Cartography; Physics; Geography","score_opus":0.3562437201120754,"score_gpt":0.6613279935070518,"score_spread":0.30508427339497646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047223150","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":[0.9939708,0.00034610395,0.0016551573,0.0011750137,0.00043247145,0.0008906144,0.000087244814,0.000027987358,0.0014145967],"genre_scores_gemma":[0.996412,0.000061754785,0.0024870664,0.000032376945,0.00028230977,0.00044605543,0.000014030029,0.000027899267,0.00023652561],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9923452,0.0057937102,0.00038258807,0.00032804662,0.00050474744,0.00064566644],"domain_scores_gemma":[0.9976188,0.0012040276,0.000070257454,0.0005599142,0.00031052608,0.00023646439],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061639305,0.00017677322,0.00027181112,0.00015361395,0.00086006656,0.00042242467,0.0004452079,0.0001849275,0.0067744306],"category_scores_gemma":[0.00013651079,0.00008855687,0.00029788897,0.00039000058,0.0012151999,0.0002098015,0.000035375626,0.00072759663,0.000044219745],"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":[0.0009776539,0.0030892568,0.06387479,0.000027043388,0.00047680835,0.000035927107,0.007947192,0.0000046021955,0.4468289,0.002566256,0.011548448,0.46262312],"study_design_scores_gemma":[0.0006809886,0.0005195974,0.99366033,0.000009007463,0.000030213998,0.0000852586,0.0012710211,0.000018451938,0.00044847635,0.0030551862,0.0001104028,0.000111060726],"about_ca_topic_score_codex":0.0017045033,"about_ca_topic_score_gemma":0.00002617866,"teacher_disagreement_score":0.92978555,"about_ca_system_score_codex":0.000066476285,"about_ca_system_score_gemma":0.00012300487,"threshold_uncertainty_score":0.99413353},"labels":[],"label_agreement":null},{"id":"W2047902775","doi":"10.3758/s13428-012-0186-0","title":"MorePower 6.0 for ANOVA with relational confidence intervals and Bayesian analysis","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":645,"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":"Statistics; Analysis of variance; Confidence interval; Bayesian probability; Statistical power; Computer science; Mixed-design analysis of variance; One-way analysis of variance; Calculator; Interpretation (philosophy); Sample size determination; Repeated measures design; Factorial; Mathematics","score_opus":0.5923435475429615,"score_gpt":0.5003782614832487,"score_spread":0.09196528605971277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047902775","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":[0.55625474,0.0007796054,0.43976954,0.0001682202,0.000066344466,0.0004445122,0.00005945637,0.000010386774,0.0024471798],"genre_scores_gemma":[0.8398661,0.00004053183,0.15860227,0.000030361596,0.000047218884,0.00028889978,0.00003333528,0.000016391677,0.0010748834],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987342,0.00013591055,0.0003708248,0.00033309177,0.00006478443,0.00036120304],"domain_scores_gemma":[0.999046,0.00037346824,0.00013482157,0.00026183014,0.000035595145,0.00014828052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070586773,0.0000970536,0.0002799753,0.00039222036,0.00015525817,0.000051275223,0.00010652227,0.000077611556,0.001050009],"category_scores_gemma":[0.00021737273,0.00009804245,0.00008592045,0.00031374767,0.00018353549,0.0003839789,0.000067143315,0.00015542147,0.000051666175],"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":[0.000018494362,0.00008043282,0.9192701,0.000007571068,0.00009760082,3.5819846e-7,0.00041515968,0.000018140554,0.0001331264,0.07629962,0.00007352663,0.0035858452],"study_design_scores_gemma":[0.00031705544,0.00010102019,0.9888505,0.00000449428,0.000060952905,0.000004624929,0.00024252085,0.0015748215,0.00037351405,0.0046645263,0.0036540146,0.00015197655],"about_ca_topic_score_codex":0.00012202102,"about_ca_topic_score_gemma":0.0000112615735,"teacher_disagreement_score":0.28361136,"about_ca_system_score_codex":0.00013327587,"about_ca_system_score_gemma":0.000012084505,"threshold_uncertainty_score":0.99986315},"labels":[],"label_agreement":null},{"id":"W2049257061","doi":"10.3758/bf03192854","title":"Word lists for testing cognitive biases toward body shape among men and women","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Eating Disorders and Behaviors","field":"Psychology","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 Calgary","funders":"","keywords":"Categorization; Normative; Cognition; Word (group theory); Psychology; Word list; Word lists by frequency; Valence (chemistry); Cognitive psychology; Natural language processing; Computer science; Linguistics; Index (typography); Artificial intelligence","score_opus":0.46739107672332725,"score_gpt":0.6153644590337722,"score_spread":0.147973382310445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049257061","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":[0.98769206,0.00034465347,0.0026302857,0.00003217863,0.00018045085,0.0017403133,0.000043198823,0.00012471738,0.007212135],"genre_scores_gemma":[0.93560076,0.000009898004,0.057614602,0.000036042074,0.00017888131,0.002056138,0.00002893468,0.00008895394,0.0043857857],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956436,0.0011653309,0.0004602827,0.0007624417,0.00047494483,0.00149341],"domain_scores_gemma":[0.9875968,0.010917516,0.00011907302,0.00032645187,0.0006007669,0.00043936263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012985355,0.00025476175,0.00038246592,0.0005043785,0.000458705,0.00014282101,0.00030312434,0.00025031684,0.00072660006],"category_scores_gemma":[0.0066885944,0.00023956079,0.000084170366,0.00082208624,0.00062803715,0.00013101884,0.000222207,0.0006785153,0.000018604176],"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":[0.0002371861,0.00056279515,0.35787067,0.000025308647,0.000026760357,0.0000932016,0.0060583893,3.337972e-8,0.008654687,0.00006504749,0.00037351582,0.6260324],"study_design_scores_gemma":[0.001408041,0.0012136034,0.9651374,0.0001380506,0.00006604035,0.000020996948,0.029378518,0.000043871194,0.0014463721,0.00030004358,0.00050279376,0.00034424703],"about_ca_topic_score_codex":0.0009170311,"about_ca_topic_score_gemma":0.000034954246,"teacher_disagreement_score":0.62568814,"about_ca_system_score_codex":0.00011489636,"about_ca_system_score_gemma":0.00007514616,"threshold_uncertainty_score":0.9769006},"labels":[],"label_agreement":null},{"id":"W2049304476","doi":"10.3758/s13428-011-0184-7","title":"The bank of standardized stimuli (BOSS): comparison between French and English norms","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","cited_by":33,"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 Montréal; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation; Jewish Rehabilitation Hospital; McGill University; Douglas Mental Health University Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boss; Categorization; Linguistics; Psychology; Concordance; Set (abstract data type); Affect (linguistics); Agreement; Social psychology; Object (grammar); Communication; Computer science","score_opus":0.28537434359636293,"score_gpt":0.6022035280019665,"score_spread":0.3168291844056036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049304476","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":[0.97871137,0.0027874121,0.012013855,0.000046694182,0.0006534289,0.00070130674,0.000086552514,0.000055989305,0.0049433825],"genre_scores_gemma":[0.9865047,0.00008904492,0.009974383,0.000004745534,0.0006345892,0.00017451723,0.000053390333,0.000033716038,0.002530924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99487454,0.003047168,0.000458242,0.0002809402,0.0006326366,0.0007064857],"domain_scores_gemma":[0.99636245,0.002109355,0.000103562255,0.00062239537,0.00054840196,0.00025382475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011249344,0.000148842,0.00035622276,0.00019240654,0.0004553594,0.000079320904,0.000334108,0.00018262114,0.001645848],"category_scores_gemma":[0.00081235444,0.00010462386,0.000081291364,0.000503101,0.00064588664,0.00014438789,0.00013987579,0.00055484485,0.000023014962],"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":[0.000057669768,0.00020271567,0.7074117,0.00001656661,0.000040682706,0.0000011693559,0.032058697,1.9128088e-7,0.0025192336,0.0012671198,0.003333612,0.25309062],"study_design_scores_gemma":[0.0007289766,0.00015640439,0.9366052,0.000007137165,0.00005798605,0.0000025215586,0.007359626,0.000003725551,0.001545565,0.00012128238,0.05328202,0.00012953728],"about_ca_topic_score_codex":0.0011328515,"about_ca_topic_score_gemma":0.000086407854,"teacher_disagreement_score":0.25296107,"about_ca_system_score_codex":0.00006756995,"about_ca_system_score_gemma":0.000062130915,"threshold_uncertainty_score":0.9992668},"labels":[],"label_agreement":null},{"id":"W2052221032","doi":"10.3758/brm.40.3.735","title":"The noisy-bit method for digital displays: Converting a 256 luminance resolution into a continuous resolution","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":75,"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":"Luminance; Computer science; Computer vision; Artificial intelligence; Pixel; Contrast (vision); Dither; Noise (video); Psychophysics; Display device; Flicker; Computer graphics (images); Image (mathematics); Noise shaping; Perception","score_opus":0.3448104394742743,"score_gpt":0.5649020745438365,"score_spread":0.22009163506956214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052221032","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":[0.19305979,0.000247426,0.80247945,0.00086457276,0.0005034639,0.0018075001,0.000037232214,0.0002167579,0.00078384904],"genre_scores_gemma":[0.60440195,0.00023457859,0.3804852,0.00023905747,0.00032926194,0.0021199987,0.00001739086,0.00010794028,0.012064654],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99337226,0.0030631118,0.00057580747,0.00088547973,0.0010280902,0.0010752622],"domain_scores_gemma":[0.9946937,0.0037901273,0.00019210024,0.00059044285,0.0004890865,0.00024457075],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0093078865,0.00024317521,0.00031311388,0.0002246773,0.003647121,0.00040613016,0.0007344093,0.00019601763,0.000029451221],"category_scores_gemma":[0.013541165,0.0001885731,0.00019097031,0.0009548022,0.00083925494,0.0005515614,0.00029609445,0.000740849,0.000067724526],"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":[0.00034038763,0.00016390363,0.00014921927,0.000037153706,0.0000025248999,0.000024384131,0.0016989161,0.000005123777,0.75678325,0.0024744207,0.000970972,0.23734978],"study_design_scores_gemma":[0.002194875,0.0016779798,0.00358966,0.00020229653,0.00004220091,0.0005004428,0.0022696585,0.061927956,0.787727,0.010178719,0.1288232,0.00086603226],"about_ca_topic_score_codex":0.0001340184,"about_ca_topic_score_gemma":0.000019766589,"teacher_disagreement_score":0.4219942,"about_ca_system_score_codex":0.00024152847,"about_ca_system_score_gemma":0.00024645086,"threshold_uncertainty_score":0.99764997},"labels":[],"label_agreement":null},{"id":"W2052698354","doi":"10.3758/s13428-013-0442-y","title":"A behavioral database for masked form priming","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":74,"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":"Priming (agriculture); Lexical decision task; Computer science; Spelling; Vocabulary; Natural language processing; Word recognition; Task (project management); Reading (process); Orthography; Prime (order theory); Cognitive psychology; Psychology; Artificial intelligence; Cognition; Linguistics; Mathematics","score_opus":0.5022630634511727,"score_gpt":0.6631078933795438,"score_spread":0.16084482992837112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052698354","genre_codex":"empirical","genre_gemma":"methods","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":[0.7986727,0.00016105594,0.18560486,0.00027908152,0.0016155199,0.0026502332,0.00008648712,0.00022875899,0.01070135],"genre_scores_gemma":[0.16948864,0.0000053442895,0.8006011,0.00007994269,0.00035684687,0.0051990566,0.00018827972,0.000103827806,0.02397694],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953509,0.0018000993,0.00046149368,0.00070392253,0.00054371275,0.0011398984],"domain_scores_gemma":[0.99670404,0.0015649087,0.00008069056,0.0009943078,0.00033120313,0.00032486775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014125971,0.00021366595,0.0003269658,0.00047783565,0.00041225235,0.00013438157,0.0005721995,0.00016881105,0.00083144824],"category_scores_gemma":[0.0006547224,0.0001935704,0.00014333152,0.00040984602,0.00016884593,0.00016401557,0.00021927283,0.00059302396,0.00017042778],"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":[0.00017322034,0.00061874674,0.005236983,0.00004278093,0.000019756422,0.000024740066,0.0052365926,1.0831689e-7,0.018014671,0.0069047804,0.0068191965,0.9569084],"study_design_scores_gemma":[0.002691287,0.0010511517,0.057064287,0.00010565411,0.00009871743,0.0000758479,0.0018661435,0.00019150547,0.014835097,0.0016063553,0.9197421,0.00067183736],"about_ca_topic_score_codex":0.0003269022,"about_ca_topic_score_gemma":0.000009952259,"teacher_disagreement_score":0.9562366,"about_ca_system_score_codex":0.00014512957,"about_ca_system_score_gemma":0.000095463205,"threshold_uncertainty_score":0.91037756},"labels":[],"label_agreement":null},{"id":"W2054762775","doi":"10.3758/s13428-012-0201-5","title":"Examining the convergent validity of shared mental model measures","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Team Dynamics and Performance","field":"Psychology","cited_by":23,"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":"Convergent validity; Mental model; Psychology; Computer science; Cognitive psychology; Psychometrics; Developmental psychology; Cognitive science; Internal consistency","score_opus":0.7335922008773689,"score_gpt":0.6234797288686424,"score_spread":0.11011247200872643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054762775","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":[0.9848577,0.00053219544,0.008901899,0.00008427814,0.00082242466,0.00053783465,0.00007991414,0.000026104122,0.004157649],"genre_scores_gemma":[0.97502166,0.000043139557,0.022269798,0.0000197872,0.00011150644,0.0003277956,0.000012804268,0.000027132184,0.0021664028],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99565977,0.002467376,0.0002970536,0.00022848281,0.00065405824,0.0006932621],"domain_scores_gemma":[0.9983932,0.0005189816,0.00007930838,0.00066664687,0.00016966942,0.00017221975],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014367253,0.00012327578,0.00019841427,0.0001318725,0.00023916035,0.000024044388,0.00051117386,0.00011143634,0.00136246],"category_scores_gemma":[0.00017894582,0.000087166336,0.00008384291,0.00028072018,0.00027521825,0.00012352523,0.00023730294,0.0005525326,0.000055203676],"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":[0.00019930706,0.0012382444,0.58864224,0.000038600716,0.00009198414,0.0000050641543,0.04051119,0.000018961127,0.093131535,0.0052695842,0.008680163,0.26217315],"study_design_scores_gemma":[0.0007520599,0.0002973587,0.9621287,0.000025325955,0.00006128169,0.000026457412,0.004026199,0.009406949,0.00838598,0.00026168014,0.014327531,0.0003004569],"about_ca_topic_score_codex":0.00026464643,"about_ca_topic_score_gemma":0.000008696705,"teacher_disagreement_score":0.3734865,"about_ca_system_score_codex":0.000074273856,"about_ca_system_score_gemma":0.00005798998,"threshold_uncertainty_score":0.9995504},"labels":[],"label_agreement":null},{"id":"W2055350558","doi":"10.3758/s13428-014-0550-3","title":"A comparison of scanpath comparison methods","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":164,"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; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Measure (data warehouse); Encoding (memory); Eye movement; Natural language processing; Machine learning; Pattern recognition (psychology); Data mining","score_opus":0.46569732647646395,"score_gpt":0.6720252201736696,"score_spread":0.20632789369720567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055350558","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":[0.0633009,0.00029786857,0.9327527,0.0003428309,0.00029063743,0.00031848132,0.0000017749304,0.00030557154,0.0023891826],"genre_scores_gemma":[0.45052275,0.0000026833309,0.54923487,0.000007739843,0.000022676893,0.00008177718,0.0000011552377,0.00001284963,0.000113486],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9886192,0.0082335435,0.0007221451,0.00074664166,0.0008381904,0.0008402775],"domain_scores_gemma":[0.994393,0.0029155873,0.00024164097,0.0016217462,0.0006045227,0.00022351477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019739265,0.00021882427,0.00080601516,0.00077016366,0.000287107,0.00011851504,0.0025485083,0.00023557436,0.000034870463],"category_scores_gemma":[0.0022085216,0.00019693833,0.0001563843,0.0016963386,0.00062776817,0.0001769781,0.0010044898,0.0011560638,0.00003413675],"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":[0.000006948761,0.0004805375,0.04514718,0.000022271759,0.000009789221,0.0000023875627,0.0004398563,0.000007774563,0.08356711,0.038513493,0.00046643056,0.8313362],"study_design_scores_gemma":[0.0006301427,0.0012588652,0.18168785,0.000073804586,0.00003186066,0.000016732096,0.0004337027,0.0684175,0.7066609,0.009318478,0.031025333,0.00044478907],"about_ca_topic_score_codex":0.00014719587,"about_ca_topic_score_gemma":0.0000104956325,"teacher_disagreement_score":0.83089143,"about_ca_system_score_codex":0.00008931543,"about_ca_system_score_gemma":0.00012346856,"threshold_uncertainty_score":0.80309117},"labels":[],"label_agreement":null},{"id":"W2055627930","doi":"10.3758/s13428-012-0253-6","title":"Recoding and representation in artificial grammar learning","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":19,"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; Encoding (memory); Natural language processing; Representation (politics); Artificial intelligence; Task (project management); Episodic memory; Grammar; Memory model; External Data Representation; Semantic memory; Machine learning; Cognition; Psychology; Linguistics; Shared memory","score_opus":0.5400207676779264,"score_gpt":0.6517631461762786,"score_spread":0.11174237849835222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055627930","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":[0.9867337,0.00047548223,0.0012014782,0.00019111848,0.00035159328,0.00032468795,4.1722345e-7,0.000050708055,0.010670839],"genre_scores_gemma":[0.9581315,0.00003302945,0.037384227,0.000011716601,0.00024011743,0.00017923316,0.0000076268966,0.00002580664,0.003986762],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941777,0.004271991,0.00026207074,0.00033727748,0.0002794736,0.00067147834],"domain_scores_gemma":[0.9988016,0.00076909934,0.000043478078,0.00016919435,0.000054881082,0.00016177988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01264507,0.000095859956,0.0001657489,0.00036826514,0.00022238796,0.00005913542,0.00009922986,0.000105097926,0.00084011845],"category_scores_gemma":[0.0010572125,0.00009424765,0.00003341938,0.0005038421,0.000103133636,0.00012620805,0.00012671297,0.00094718137,0.00010317237],"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":[0.000032046773,0.00011942391,0.44294247,0.000003975867,0.0000041112135,0.000014245506,0.0046270974,4.6461355e-7,0.013886094,0.0031843635,0.00008258246,0.53510314],"study_design_scores_gemma":[0.0002006694,0.00007285273,0.9777828,0.000018607441,0.000005151185,0.00001992774,0.0034462758,0.000012836667,0.0017183913,0.00019599103,0.016407741,0.0001187773],"about_ca_topic_score_codex":0.00026167472,"about_ca_topic_score_gemma":0.000013860178,"teacher_disagreement_score":0.53498435,"about_ca_system_score_codex":0.00007413626,"about_ca_system_score_gemma":0.000022728145,"threshold_uncertainty_score":0.9198708},"labels":[],"label_agreement":null},{"id":"W2056379117","doi":"10.3758/s13428-015-0564-5","title":"Assessing perceptual change with an ambiguous figures task: Normative data for 40 standard picture sets","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":41,"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 Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Perception; Normative; Ambiguity; Morphing; Computer science; Cognitive psychology; Object (grammar); Psychology; Artificial intelligence","score_opus":0.8104658419495807,"score_gpt":0.6598050748479091,"score_spread":0.15066076710167164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056379117","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":[0.80791974,0.00008782924,0.18639445,0.0005114827,0.00043501527,0.0024393061,0.0010875998,0.00033265265,0.0007919235],"genre_scores_gemma":[0.6145626,0.000020218162,0.38261575,0.0006586516,0.00036049122,0.000766436,0.00031583788,0.000112709095,0.0005873437],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99234396,0.0039281584,0.00028642593,0.0010233283,0.0015623181,0.000855835],"domain_scores_gemma":[0.9970795,0.000373596,0.000110781584,0.0011378147,0.00067940867,0.0006189076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008728701,0.00027756506,0.00034806205,0.00031396514,0.00082337775,0.0010293131,0.0013112217,0.00018997255,0.0002001892],"category_scores_gemma":[0.002811759,0.00020995588,0.000044790962,0.0006918007,0.00046554522,0.0025593517,0.0004680377,0.0008001834,0.000028183484],"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":[0.0010022492,0.00040459365,0.00008067018,0.00010355181,0.0000051087277,0.00007072438,0.015733441,0.0000035402431,0.31314436,0.000118831595,0.0017582286,0.6675747],"study_design_scores_gemma":[0.012635657,0.027739916,0.019757837,0.00091645843,0.00035083859,0.0008132391,0.15057285,0.031438988,0.6264345,0.0081219645,0.11706869,0.004149067],"about_ca_topic_score_codex":0.00014580436,"about_ca_topic_score_gemma":0.000054546268,"teacher_disagreement_score":0.6634256,"about_ca_system_score_codex":0.0001702553,"about_ca_system_score_gemma":0.0005087729,"threshold_uncertainty_score":0.99256897},"labels":[],"label_agreement":null},{"id":"W2058117779","doi":"10.3758/bf03192965","title":"Comparing derived and acquired acceleration profiles: 3-D optical electronic data analyses","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":15,"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":"Acceleration; Trajectory; Accelerometer; Position (finance); Computer science; Root mean square; Mean squared error; Movement (music); Geodesy; Simulation; Mathematics; Statistics; Acoustics; Physics; Geology","score_opus":0.7508497431548431,"score_gpt":0.6347631879419575,"score_spread":0.11608655521288558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058117779","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":[0.83220494,0.00015484844,0.16606985,0.000092810675,0.000053405867,0.0006550035,0.0000051095312,0.00006230801,0.00070169824],"genre_scores_gemma":[0.9502789,0.00005698207,0.04919767,0.000032577092,0.000094750176,0.00006896133,0.000023739763,0.000017852672,0.00022860049],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99628043,0.0013480389,0.0003052365,0.00066787715,0.0006550686,0.00074336195],"domain_scores_gemma":[0.9975643,0.0014687707,0.000056187768,0.00059767265,0.00012051877,0.00019255046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073072636,0.0001244922,0.00020851681,0.00027600618,0.00038824155,0.0002465451,0.0005492092,0.000076745906,0.00005086675],"category_scores_gemma":[0.0030037079,0.000109007706,0.000029185412,0.00054427155,0.0002610567,0.0005205361,0.000408736,0.0003452107,0.000011075029],"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":[0.0000818252,0.000082668455,0.000846067,0.0000075244398,0.0000028805744,0.000018032315,0.00008408869,0.000002188391,0.9034961,0.0013406115,0.000010178742,0.09402783],"study_design_scores_gemma":[0.0006339142,0.00016974447,0.12792756,0.000012881675,0.000031452735,0.000022846223,0.0002275378,0.018915169,0.8505572,0.00037474724,0.0009535793,0.00017337746],"about_ca_topic_score_codex":0.000066349894,"about_ca_topic_score_gemma":0.00005158045,"teacher_disagreement_score":0.12708148,"about_ca_system_score_codex":0.000083435625,"about_ca_system_score_gemma":0.0001234569,"threshold_uncertainty_score":0.4445205},"labels":[],"label_agreement":null},{"id":"W2058821124","doi":"10.3758/brm.40.2.428","title":"Comparing online and lab methods in a problem-solving experiment","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":216,"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":"Computer science; Artificial intelligence; Psychology; Mathematics education","score_opus":0.4997630286426059,"score_gpt":0.6502886072233989,"score_spread":0.15052557858079296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058821124","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":[0.9835528,0.0017547818,0.005228939,0.0007579337,0.00009796155,0.0007521693,0.0000016371652,0.00009346843,0.00776027],"genre_scores_gemma":[0.11221239,0.0005771697,0.885247,0.000013091452,0.00015630423,0.00012764044,0.0000036645333,0.000022845343,0.0016399295],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9876562,0.009925307,0.00036562842,0.0004568877,0.0007230553,0.0008729575],"domain_scores_gemma":[0.99780756,0.0014142591,0.00006170811,0.00024520126,0.0001979978,0.0002732745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019385086,0.00013897386,0.0003410794,0.00045766943,0.0009581465,0.00009627462,0.00034988072,0.0001410852,0.0001603713],"category_scores_gemma":[0.0015332001,0.00013336165,0.000055643526,0.0010427933,0.0006367282,0.0002575383,0.00034888528,0.001033688,0.000005261613],"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":[0.000031890868,0.00068026985,0.14552121,0.000026722668,0.000010089421,0.00014330605,0.03344533,0.0000098383425,0.051521007,0.0017342669,0.0001378747,0.7667382],"study_design_scores_gemma":[0.0027551525,0.00061257224,0.33570072,0.00039213436,0.00004264766,0.000074439675,0.14223136,0.0018884526,0.026322955,0.0020812252,0.48665205,0.0012462891],"about_ca_topic_score_codex":0.005012541,"about_ca_topic_score_gemma":0.0014820341,"teacher_disagreement_score":0.88001806,"about_ca_system_score_codex":0.00023414414,"about_ca_system_score_gemma":0.0005587364,"threshold_uncertainty_score":0.75774956},"labels":[],"label_agreement":null},{"id":"W2062564842","doi":"10.3758/s13428-012-0283-0","title":"Norms for grip agreement for 296 photographs of objects","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","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 de Moncton","funders":"","keywords":"Affordance; Object (grammar); Set (abstract data type); Cognition; Computer science; Artificial intelligence; Psychology; Cognitive psychology","score_opus":0.5991373342195433,"score_gpt":0.6734610464504677,"score_spread":0.07432371223092438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062564842","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":[0.20565727,0.00043767446,0.7815096,0.00016887141,0.0019359646,0.0048038843,0.000098238415,0.00006229542,0.005326233],"genre_scores_gemma":[0.62032014,0.000024132554,0.3624232,0.00009931749,0.0004026795,0.0064664474,0.00015135514,0.000056586072,0.010056153],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997719,0.0007513866,0.00036191614,0.00023827034,0.0003479571,0.0005814747],"domain_scores_gemma":[0.997681,0.00095598,0.00012147128,0.0003875316,0.0006927923,0.0001611907],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0069319396,0.000106840635,0.00020479625,0.00034600557,0.00018859752,0.000018158817,0.00019865876,0.0001503223,0.0018206463],"category_scores_gemma":[0.00062892516,0.00009516721,0.00015438003,0.0005307565,0.00011116971,0.00014490087,0.00004027236,0.00016301147,0.000022586017],"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":[0.0005974224,0.0025441386,0.16425382,0.00023646689,0.0001408934,7.6646944e-7,0.011363445,0.000002166381,0.1457769,0.019075701,0.023295624,0.63271266],"study_design_scores_gemma":[0.0054224413,0.0019100645,0.41141358,0.000043820095,0.00016388399,0.000010368479,0.012275117,0.00033462836,0.21298087,0.0014124109,0.35345197,0.00058086624],"about_ca_topic_score_codex":0.000113349575,"about_ca_topic_score_gemma":0.000013195089,"teacher_disagreement_score":0.6321318,"about_ca_system_score_codex":0.00007805295,"about_ca_system_score_gemma":0.000054420314,"threshold_uncertainty_score":0.9990918},"labels":[],"label_agreement":null},{"id":"W2064017523","doi":"10.3758/s13428-012-0266-1","title":"A methodological note on evaluating performance in a sustained-attention-to-response task","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","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 Waterloo","funders":"","keywords":"Response time; Stimulus (psychology); Computer science; Task (project management); Cognitive psychology; Response inhibition; Psychology; Audiology; Cognition; Neuroscience; Medicine","score_opus":0.8800142472997852,"score_gpt":0.7255989051982621,"score_spread":0.15441534210152308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064017523","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":[0.99555343,0.00004089183,0.00052976346,0.001487421,0.00046055793,0.0013056702,0.000010659722,0.00008630932,0.0005252881],"genre_scores_gemma":[0.93778396,0.000017183716,0.058735386,0.00048052156,0.000110769484,0.0010989638,0.0000010178807,0.00003120642,0.0017409758],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9736365,0.022364553,0.00047222228,0.00084274414,0.0010772079,0.0016067798],"domain_scores_gemma":[0.9905427,0.008290625,0.00007315967,0.0005513811,0.00016992727,0.0003722242],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036458846,0.00027074566,0.00041855063,0.0008110956,0.00053715834,0.000060329145,0.000600576,0.00016740401,0.00014613442],"category_scores_gemma":[0.019517172,0.00020387597,0.00012448902,0.0016544021,0.00043732143,0.00028269118,0.000529438,0.001344117,0.00046957695],"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":[0.0014432828,0.0006335182,0.033984493,0.000008861502,9.342612e-7,0.000060759856,0.0004711757,0.0000028048232,0.81839395,0.00006885951,0.00008784594,0.14484355],"study_design_scores_gemma":[0.0006723655,0.0019648115,0.72327805,0.00004407968,0.000013905097,0.000049625414,0.00037634754,0.000049699862,0.27136868,0.00010942016,0.0017818002,0.00029124838],"about_ca_topic_score_codex":0.000022448849,"about_ca_topic_score_gemma":0.0000021613685,"teacher_disagreement_score":0.6892935,"about_ca_system_score_codex":0.0002481488,"about_ca_system_score_gemma":0.00006201141,"threshold_uncertainty_score":0.99216837},"labels":[],"label_agreement":null},{"id":"W2064232423","doi":"10.3758/bf03192703","title":"Generating complex three-dimensional stimuli (Greebles) for haptic expertise training","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":8,"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 Institutes of Health Research; James S. McDonnell Foundation; National Science Foundation","keywords":"Haptic technology; Computer science; Set (abstract data type); Perception; Object (grammar); Training (meteorology); Artificial intelligence; Human–computer interaction; Psychology","score_opus":0.7364569336206933,"score_gpt":0.6112126661609603,"score_spread":0.12524426745973305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064232423","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":[0.8924058,0.00004073044,0.10245319,0.0013898383,0.00047377168,0.001535328,0.00006980357,0.00020787136,0.001423669],"genre_scores_gemma":[0.6135893,0.0000037376951,0.38354158,0.00034111258,0.00043225693,0.00065284746,0.0000073240567,0.00004821844,0.0013836198],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961605,0.0011761009,0.00041170712,0.0006680916,0.0007139068,0.000869687],"domain_scores_gemma":[0.99531627,0.0036486103,0.0000740564,0.00044232688,0.00023735667,0.00028138043],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001329136,0.00019518672,0.0002658595,0.00030740688,0.0011311902,0.00018661126,0.00038107537,0.00010104367,0.00093029387],"category_scores_gemma":[0.003285314,0.0001826284,0.00016870954,0.00036317031,0.00025868588,0.00035779428,0.00013775883,0.0006226477,0.00010162484],"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":[0.00004082798,0.00013961246,0.000030695996,0.00000426398,0.0000021718972,0.000017312865,0.00048776896,0.00044188322,0.68640494,0.0003082066,0.0005778402,0.3115445],"study_design_scores_gemma":[0.00085390644,0.000305525,0.0005791667,0.000034175868,0.000021344094,0.00016372476,0.000467916,0.4169594,0.546354,0.00026005533,0.033655472,0.00034532335],"about_ca_topic_score_codex":0.00007451027,"about_ca_topic_score_gemma":0.00011840012,"teacher_disagreement_score":0.41651753,"about_ca_system_score_codex":0.00017760429,"about_ca_system_score_gemma":0.00015008988,"threshold_uncertainty_score":0.999983},"labels":[],"label_agreement":null},{"id":"W2067456760","doi":"10.3758/brm.41.2.337","title":"Combined eyetracking and keystroke-logging methods for studying cognitive processes in text production","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":127,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SR Research (Canada)","funders":"","keywords":"Timeline; Keystroke logging; Computer science; Parsing; Keystroke dynamics; Cognition; Reading (process); Human–computer interaction; Matching (statistics); Identification (biology); Artificial intelligence; Natural language processing; Psychology; Password; Computer security","score_opus":0.4066462785331903,"score_gpt":0.6576008177856255,"score_spread":0.2509545392524352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067456760","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":[0.97578126,0.0007827566,0.015795955,0.0026298095,0.000278733,0.0023682064,0.0000028151549,0.00013127406,0.002229204],"genre_scores_gemma":[0.7519357,0.0001267329,0.24654949,0.000021268981,0.0002920706,0.0004975033,0.000005070067,0.000014468536,0.00055770954],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9940004,0.004120094,0.00029624213,0.0005072505,0.0004037014,0.00067232514],"domain_scores_gemma":[0.9945515,0.0042037913,0.00008916188,0.00012501897,0.0008927106,0.00013783757],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03303052,0.0001185557,0.00023608077,0.00050536287,0.001325759,0.00030241036,0.0001792025,0.00011844275,0.000011859679],"category_scores_gemma":[0.024456363,0.00012541194,0.000034753688,0.0010979667,0.00031944542,0.00034951727,0.000038587114,0.00046865203,0.000001027505],"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":[0.00005560343,0.00032300205,0.021163076,0.00008987486,0.0000036535887,0.0000016354135,0.026936254,5.370619e-7,0.012773679,0.0006432729,0.000034908167,0.9379745],"study_design_scores_gemma":[0.0026432876,0.0013967009,0.48994145,0.001911051,0.00014153442,0.000011614921,0.40460017,0.00017191372,0.07160008,0.019766442,0.0068094707,0.0010063018],"about_ca_topic_score_codex":0.00048633522,"about_ca_topic_score_gemma":0.0001607453,"teacher_disagreement_score":0.9369682,"about_ca_system_score_codex":0.0001750845,"about_ca_system_score_gemma":0.00041733505,"threshold_uncertainty_score":0.99997437},"labels":[],"label_agreement":null},{"id":"W2067667602","doi":"10.3758/bf03192772","title":"NUANCE 3.0: Using genetic programming to model variable relationships","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","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 Toronto; University of Alberta","funders":"Government of Canada","keywords":"Computer science; Genetic programming; Set (abstract data type); Artificial intelligence; Machine learning; Human–computer interaction; Cognitive science; Programming language; Psychology","score_opus":0.37795273108280475,"score_gpt":0.5393659313395897,"score_spread":0.1614132002567849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067667602","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":[0.015145172,0.0001541248,0.9828353,0.00031690364,0.000051524843,0.0007449378,0.0000035515893,0.00013559664,0.00061291707],"genre_scores_gemma":[0.016993066,0.0000022347672,0.9809486,0.000014247317,0.00009268836,0.00073354604,0.000003399779,0.000017078319,0.0011951326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972024,0.00080321287,0.0002874548,0.00054167135,0.00056256494,0.00060268247],"domain_scores_gemma":[0.9982089,0.00036198474,0.000042448184,0.00080375414,0.0003947498,0.0001881559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038930415,0.00011317578,0.0001245808,0.000279072,0.00092885847,0.00023915853,0.00087665796,0.00008123996,0.000008980934],"category_scores_gemma":[0.00014450497,0.00011815763,0.00004406043,0.002109257,0.00008164969,0.00032691055,0.00042179239,0.00044865557,0.000033807035],"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":[0.0000053660174,0.0009061234,0.0069606635,0.000023370834,0.00000754489,0.00001946536,0.00041193413,0.13141628,0.11123176,0.51498216,0.0010226271,0.23301274],"study_design_scores_gemma":[0.00010431953,0.000035491776,0.020386806,0.000016488893,0.0000068167783,0.000024501294,0.000027592456,0.93416154,0.0013244922,0.037221603,0.006491153,0.00019920536],"about_ca_topic_score_codex":0.0003586187,"about_ca_topic_score_gemma":0.00000635833,"teacher_disagreement_score":0.8027453,"about_ca_system_score_codex":0.00018245722,"about_ca_system_score_gemma":0.00027815413,"threshold_uncertainty_score":0.7144122},"labels":[],"label_agreement":null},{"id":"W2070372221","doi":"10.3758/s13428-014-0524-5","title":"Response latencies are alive and well for identifying fakers on a self-report personality inventory: A reconsideration of van Hooft and Born (2012)","year":2014,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":24,"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":"Congruence (geometry); Correctness; Personality; Psychology; Personality theory; Personality Assessment Inventory; Test (biology); Personality test; Social psychology; Psychometrics; Computer science; Test validity; Developmental psychology; Algorithm","score_opus":0.41778008388408583,"score_gpt":0.5838089755094042,"score_spread":0.16602889162531842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070372221","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":[0.993863,0.00033551146,0.0024817758,0.0011242984,0.00026727698,0.0008804862,0.00008519459,0.000043999917,0.00091847975],"genre_scores_gemma":[0.93424845,0.00006136799,0.061271112,0.00033073564,0.0001513281,0.0007350081,0.00003085964,0.00006217732,0.0031089545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894681,0.008460532,0.0004431592,0.0007316957,0.0003722197,0.00052428234],"domain_scores_gemma":[0.9951155,0.0035186808,0.00027242248,0.00049499184,0.0003663316,0.00023206594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02626737,0.00019327634,0.0004144211,0.00035497552,0.0003508332,0.000068351765,0.00014763117,0.00026044904,0.0003053361],"category_scores_gemma":[0.0021655816,0.0001814756,0.00010683476,0.00019685457,0.0004939564,0.00012480067,0.000066632994,0.0005025867,0.000007964368],"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":[0.011898846,0.0021888772,0.7063883,0.000556827,0.0006798658,0.0002977746,0.06145858,0.0000010757053,0.039981443,0.0058690724,0.026562598,0.14411676],"study_design_scores_gemma":[0.0015954793,0.001085577,0.9537857,0.00006202541,0.00010552716,0.00020908302,0.0041674776,0.00005762952,0.00065431494,0.0025930244,0.035444003,0.0002401642],"about_ca_topic_score_codex":0.0004148526,"about_ca_topic_score_gemma":0.00025865677,"teacher_disagreement_score":0.24739741,"about_ca_system_score_codex":0.0000612985,"about_ca_system_score_gemma":0.00007696503,"threshold_uncertainty_score":0.9103799},"labels":[],"label_agreement":null},{"id":"W2073248762","doi":"10.3758/brm.41.4.1210","title":"Grounding co-occurrence: Identifying features in a lexical co-occurrence model of semantic memory","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":32,"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 Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Computer science; Co-occurrence; Feature vector; Word (group theory); Natural language processing; Artificial intelligence; Feature (linguistics); Semantics (computer science); Distributional semantics; Memory model; Vector space model; Space (punctuation); Semantic network; Vector space; Artificial neural network; Semantic similarity; Linguistics; Mathematics; Programming language","score_opus":0.46308618363239945,"score_gpt":0.6144912133150822,"score_spread":0.1514050296826827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073248762","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":[0.99606067,0.00017853113,0.0016008123,0.00016791088,0.00021344879,0.00066780666,0.00021274232,0.00007332027,0.00082476035],"genre_scores_gemma":[0.9910287,0.00010677066,0.008267716,0.00019561026,0.000056238277,0.0000597033,0.000032386168,0.000013011574,0.00023986222],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9930741,0.0034641505,0.00059380743,0.0009267775,0.0009411581,0.0009999664],"domain_scores_gemma":[0.9971043,0.0018054954,0.0001430489,0.0006182689,0.00011867443,0.00021020374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064826855,0.00025668897,0.00050105696,0.00082855043,0.00029747133,0.00011101073,0.0010199086,0.00022787553,0.000052439947],"category_scores_gemma":[0.0038215828,0.00022898763,0.00015609535,0.00097435864,0.00080232456,0.00030961432,0.0001654814,0.0016245142,0.000015019181],"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":[0.00007518262,0.00038687885,0.001082554,0.000052744537,0.0000013605141,0.0007024737,0.0016359276,0.00001899546,0.9550716,0.00038723566,0.00031414418,0.040270872],"study_design_scores_gemma":[0.0006718032,0.00030088105,0.0058614323,0.00015023489,0.000017389182,0.00031385617,0.000604742,0.00069925806,0.9890368,0.0019203225,0.00007424034,0.00034901948],"about_ca_topic_score_codex":0.000062055275,"about_ca_topic_score_gemma":0.000008406423,"teacher_disagreement_score":0.039921854,"about_ca_system_score_codex":0.000083495244,"about_ca_system_score_gemma":0.00023393582,"threshold_uncertainty_score":0.9337844},"labels":[],"label_agreement":null},{"id":"W2074008056","doi":"10.3758/s13428-010-0053-9","title":"Examining workgroup diversity effects: does playing by the (group-retention) rules help or hinder?","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gender Diversity and Inequality","field":"Social Sciences","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":"Western University; University of Guelph","funders":"","keywords":"Workgroup; Diversity (politics); Group (periodic table); Outcome (game theory); Psychology; Social psychology; Retention rate; Computer science; Statistics; Mathematics; Computer security; Political science","score_opus":0.7036334484509716,"score_gpt":0.5292031031139763,"score_spread":0.1744303453369953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074008056","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":[0.9735329,0.00020601448,0.011455314,0.00024168188,0.0006775001,0.0010285195,0.000028762235,0.00015109968,0.012678193],"genre_scores_gemma":[0.95567787,0.00014007206,0.039909262,0.000073597526,0.00015070748,0.00009932593,0.000010644202,0.000016246007,0.0039222683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98613787,0.010796376,0.00022994862,0.0005050077,0.001407243,0.0009235793],"domain_scores_gemma":[0.9963535,0.0025449817,0.00009712077,0.00045818125,0.00023936304,0.00030684957],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024113677,0.00016607913,0.00024036443,0.00015423971,0.006493481,0.00022868456,0.001329112,0.00022127441,0.0012886451],"category_scores_gemma":[0.0018093127,0.00010530483,0.00012709913,0.0006638094,0.001127375,0.00057777896,0.0014652767,0.00079440547,0.00007630054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024932553,0.00064274116,0.60067755,0.00008224451,0.00008711204,0.000090814174,0.11952576,6.106005e-8,0.003581998,0.008856214,0.003330998,0.26287517],"study_design_scores_gemma":[0.0008794739,0.00039767058,0.7758549,0.00008674202,0.00015608338,0.0000029058403,0.20282601,0.000009156077,0.0032487954,0.0051912325,0.010810174,0.0005368898],"about_ca_topic_score_codex":0.018237881,"about_ca_topic_score_gemma":0.0010648482,"teacher_disagreement_score":0.26233828,"about_ca_system_score_codex":0.00025297463,"about_ca_system_score_gemma":0.000113145215,"threshold_uncertainty_score":0.9996243},"labels":[],"label_agreement":null},{"id":"W2074995870","doi":"10.3758/s13428-012-0294-x","title":"Capturing and evaluating blinks from video-based eyetrackers","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":24,"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; Simon Fraser University","funders":"","keywords":"Computer science; Sensitivity (control systems); Computer vision; Artificial intelligence; Pupil; Workload; Contrast (vision); Plot (graphics); Psychology; Mathematics; Statistics","score_opus":0.4686376173035349,"score_gpt":0.6115095745346915,"score_spread":0.14287195723115653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074995870","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":[0.6356411,0.00073139713,0.36221796,0.00055779406,0.00020865335,0.00021733159,0.0000032099351,0.0002412994,0.00018123395],"genre_scores_gemma":[0.5175104,0.0000032662656,0.4822763,0.000024870478,0.00005266449,0.0000822211,0.0000015552774,0.000010534906,0.00003819212],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99546766,0.002225669,0.00024434007,0.0005187496,0.0006726329,0.0008709218],"domain_scores_gemma":[0.9967314,0.0019597292,0.00006526714,0.0007569233,0.00021430678,0.00027238642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012050364,0.00015575695,0.00021917568,0.00041790673,0.00035130224,0.00019228499,0.00082542474,0.00018779044,0.000035228255],"category_scores_gemma":[0.001435305,0.00014254228,0.00005698402,0.00064633705,0.00029568627,0.00036612168,0.00051121996,0.00096994574,0.000034295266],"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":[0.0000067695596,0.00014039855,0.07564526,0.000009066084,0.000008682816,0.000015318268,0.00048522349,0.0000026661648,0.08279234,0.0018847873,0.00007600883,0.83893347],"study_design_scores_gemma":[0.0008844443,0.0002654829,0.8027774,0.00008021138,0.000033904074,0.000017233142,0.00033750958,0.015074816,0.17460808,0.0034612,0.0020116721,0.00044804538],"about_ca_topic_score_codex":0.00033749867,"about_ca_topic_score_gemma":0.0000073279693,"teacher_disagreement_score":0.8384854,"about_ca_system_score_codex":0.00009656904,"about_ca_system_score_gemma":0.000100455996,"threshold_uncertainty_score":0.5812706},"labels":[],"label_agreement":null},{"id":"W2077834585","doi":"10.3758/brm.40.4.961","title":"Random without replacement is not random: Caveat emptor","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":7,"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":"Natural Sciences and Engineering Research Council of Canada; UC Berkeley College of Chemistry","keywords":"Caveat emptor; Computer science; Selection (genetic algorithm); Simple random sample; Artificial intelligence; Medicine","score_opus":0.7589440560245428,"score_gpt":0.6292991638743772,"score_spread":0.1296448921501656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077834585","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":[0.9607194,0.0018280208,0.0027670881,0.0014425535,0.0016092308,0.0025790299,0.000064048705,0.00024544436,0.028745182],"genre_scores_gemma":[0.79260445,0.0006981484,0.047361366,0.0011103225,0.0007023005,0.006082542,0.000026138447,0.00013097534,0.15128379],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98985946,0.005428199,0.000767563,0.0012300449,0.0012401261,0.0014746201],"domain_scores_gemma":[0.9963397,0.0013548473,0.00012974115,0.0012492201,0.00043548614,0.0004910049],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008379546,0.00042534212,0.0009078446,0.00030709888,0.0010986353,0.00006271974,0.00073683425,0.00038138308,0.020878915],"category_scores_gemma":[0.00043019664,0.00030931152,0.00039263058,0.00077828206,0.0010973214,0.00009963893,0.00036136562,0.0013648289,0.0017240618],"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":[0.020819904,0.0038258894,0.34042817,0.00002910956,0.00029981078,0.0010910856,0.013234454,2.7383598e-7,0.027947664,0.000364573,0.21117795,0.3807811],"study_design_scores_gemma":[0.024596721,0.0019995016,0.5649546,0.00004028886,0.00017152459,0.00036571862,0.0014922663,0.000003678054,0.009351772,0.00020471687,0.3959253,0.00089394464],"about_ca_topic_score_codex":0.0010184118,"about_ca_topic_score_gemma":0.000014262503,"teacher_disagreement_score":0.37988716,"about_ca_system_score_codex":0.00013963593,"about_ca_system_score_gemma":0.000056125617,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W2078894097","doi":"10.3758/bf03192726","title":"Semantic feature production norms for a large set of living and nonliving things","year":2005,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":1102,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto; Western University","funders":"National Institute on Deafness and Other Communication Disorders; National Institute of Mental Health; U.S. Public Health Service; National Institutes of Health","keywords":"Categorization; Set (abstract data type); Feature (linguistics); Computer science; Cognitive psychology; Semantic memory; Semantic feature; Psychology; Neuropsychology; Semantics (computer science); Cognitive science; Natural language processing; Artificial intelligence; Cognition; Linguistics","score_opus":0.1772768251816343,"score_gpt":0.5544826933288824,"score_spread":0.37720586814724816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078894097","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":[0.990914,0.0008281891,0.003913799,0.002054484,0.0002905368,0.0010821793,0.000014324308,0.000067559806,0.0008349566],"genre_scores_gemma":[0.77784705,0.000029850251,0.2108943,0.000041767915,0.0004376925,0.0001547706,0.000006585109,0.000039728035,0.010548263],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99768645,0.00076687895,0.00022311072,0.00047914134,0.00030647975,0.00053793105],"domain_scores_gemma":[0.9982286,0.001093609,0.00007896875,0.0002827077,0.00021761248,0.00009851973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009185661,0.00012677253,0.00024003511,0.00025923376,0.00028786378,0.000043495234,0.00016833974,0.00013131496,0.00024001824],"category_scores_gemma":[0.0024130798,0.00010814591,0.00006897642,0.00029843123,0.000081213955,0.00014387243,0.00016767641,0.000584782,0.000012827857],"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":[0.00018703743,0.00076633395,0.12344007,0.0003392273,0.00009071378,0.000012383455,0.049610488,0.0000016852639,0.12421206,0.0031643226,0.008245429,0.68993026],"study_design_scores_gemma":[0.0003803948,0.0003885382,0.9059332,0.00049638905,0.00004802941,0.00007758937,0.004196454,0.00013833493,0.005504987,0.00007249905,0.08247784,0.00028573768],"about_ca_topic_score_codex":0.00004539764,"about_ca_topic_score_gemma":0.00001949985,"teacher_disagreement_score":0.7824931,"about_ca_system_score_codex":0.000052101932,"about_ca_system_score_gemma":0.000051405044,"threshold_uncertainty_score":0.44100624},"labels":[],"label_agreement":null},{"id":"W2083062973","doi":"10.3758/bf03193037","title":"Assessment of adolescent body perception: Development and characterization of a novel tool for morphing images of adolescent bodies","year":2007,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Eating Disorders and Behaviors","field":"Psychology","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":"McGill University","funders":"","keywords":"Body shape; Morphing; Perception; Computer science; Body surface; Artificial intelligence; Computer vision; Psychology; Mathematics","score_opus":0.23983690130810192,"score_gpt":0.5712538266076664,"score_spread":0.3314169252995645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083062973","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":[0.84300643,0.00006662928,0.15552619,0.00002682703,0.00012263058,0.0010961785,0.000044375833,0.000012863083,0.00009788547],"genre_scores_gemma":[0.73558843,0.00002274688,0.26389265,0.0000068726067,0.000029093926,0.00018014548,0.000037136288,0.00002406543,0.00021888151],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9974371,0.00039234254,0.0008227201,0.00036700166,0.00054918084,0.00043166158],"domain_scores_gemma":[0.9983373,0.0002762459,0.00031121145,0.00032381635,0.00066796836,0.00008342223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006723578,0.00016457814,0.00041296758,0.00041573617,0.00012421189,0.000017125962,0.00019568835,0.00013535655,0.00010157885],"category_scores_gemma":[0.00012286573,0.0001542339,0.000097432945,0.00023038055,0.0002932958,0.00007823628,0.00013804814,0.00027635018,4.1660226e-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":[0.00008718094,0.0019352771,0.2528846,0.0002741967,0.000016474354,0.0000015788974,0.001416269,1.8027734e-7,0.6179239,0.00017427195,0.000016567416,0.12526947],"study_design_scores_gemma":[0.000938722,0.0003558252,0.92162097,0.00023235686,0.00004682258,0.0000038710277,0.0021980614,0.000017133894,0.074247554,0.000005095687,0.00020094033,0.00013264322],"about_ca_topic_score_codex":0.000075530974,"about_ca_topic_score_gemma":0.000006755764,"teacher_disagreement_score":0.6687364,"about_ca_system_score_codex":0.00009347419,"about_ca_system_score_gemma":0.00012335439,"threshold_uncertainty_score":0.62894756},"labels":[],"label_agreement":null},{"id":"W2084990311","doi":"10.3758/bf03192800","title":"Behavioral phenotyping in zebrafish: Comparison of three behavioral quantification methods","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":299,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Family Physicians of Canada; University of Toronto","funders":"","keywords":"Zebrafish; Novelty; Aggression; Animal behavior; Brain function; Neuroscience; Behavioral pattern; Psychology; Biology; Computer science; Developmental psychology; Genetics; Zoology; Gene","score_opus":0.3236072011575465,"score_gpt":0.6104451046833086,"score_spread":0.2868379035257621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084990311","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":[0.7865521,0.0007044072,0.2105574,0.00016396416,0.000098742144,0.001291653,0.000047148187,0.00003151231,0.00055310945],"genre_scores_gemma":[0.7118279,0.0000244724,0.28654066,0.0000058898368,0.000122018915,0.00092592044,0.0003459478,0.00005442251,0.00015276116],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9932419,0.002730594,0.001045231,0.00091580965,0.0010399474,0.0010265126],"domain_scores_gemma":[0.9972018,0.00037263116,0.00021057758,0.001251849,0.0006805477,0.00028259892],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009440921,0.00027283258,0.0005036035,0.00073741784,0.00021937965,0.00007962889,0.0010249617,0.00045952472,0.00012617712],"category_scores_gemma":[0.000764214,0.00028195544,0.00019537202,0.001619822,0.0009831104,0.000021970889,0.0005586006,0.00088043616,0.000017820335],"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":[0.00007480612,0.0018387934,0.034327388,0.000022218956,0.000006250805,0.0000034252769,0.00004840542,0.0000070452606,0.7584465,0.00075896847,0.00048254375,0.20398366],"study_design_scores_gemma":[0.0007586907,0.0005693321,0.1507436,0.000033447774,0.000033718865,0.00000560017,0.00033704384,0.0005451348,0.8339726,0.0012251696,0.011447489,0.00032818437],"about_ca_topic_score_codex":0.0036002984,"about_ca_topic_score_gemma":0.0019696981,"teacher_disagreement_score":0.20365548,"about_ca_system_score_codex":0.00014500556,"about_ca_system_score_gemma":0.00035454938,"threshold_uncertainty_score":0.9999633},"labels":[],"label_agreement":null},{"id":"W2086532769","doi":"10.3758/s13428-015-0561-8","title":"The DalHouses: 100 new photographs of houses with ratings of typicality, familiarity, and degree of similarity to faces","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":25,"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":"Canadian Institutes of Health Research","keywords":"Degree (music); Similarity (geometry); Psychology; Communication; Cognitive psychology; Artificial intelligence; Pattern recognition (psychology); Computer science; Acoustics; Physics","score_opus":0.7083864237377904,"score_gpt":0.5889348991601996,"score_spread":0.11945152457759078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086532769","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":[0.99552906,0.000058296002,0.002696802,0.00019774567,0.000037498452,0.000720022,0.000043532764,0.000023061983,0.0006939587],"genre_scores_gemma":[0.95375717,0.00019564306,0.04574169,0.00003696981,0.000011376328,0.000047234404,9.0089515e-7,0.000017434733,0.00019157633],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960796,0.002125569,0.0003341175,0.00029852256,0.00088418805,0.0002779954],"domain_scores_gemma":[0.99722606,0.0015510146,0.00011300297,0.000369413,0.00046998513,0.0002705027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004433307,0.000109439075,0.0002680127,0.00020912984,0.00012684215,0.000045415632,0.00037190094,0.00008084701,0.00003709157],"category_scores_gemma":[0.003737259,0.00007149847,0.00005170154,0.0009480471,0.0009196013,0.00011275256,0.00026180493,0.0003019563,0.0000023177258],"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":[0.00038361203,0.00025488058,0.06685506,0.00006537909,0.0000047669723,0.000002004277,0.0024758978,0.000002824942,0.8069989,0.00019161258,0.00032946872,0.12243557],"study_design_scores_gemma":[0.0005733389,0.0011426056,0.11171592,0.000068661364,0.000022380164,0.000008739999,0.0027953228,0.00005283016,0.8816254,0.0009582151,0.00092196086,0.00011461678],"about_ca_topic_score_codex":0.0021915515,"about_ca_topic_score_gemma":0.00079948804,"teacher_disagreement_score":0.12232095,"about_ca_system_score_codex":0.000018333858,"about_ca_system_score_gemma":0.00023388337,"threshold_uncertainty_score":0.4474118},"labels":[],"label_agreement":null},{"id":"W2087093006","doi":"10.3758/s13428-011-0117-5","title":"Imageability and body–object interaction ratings for 599 multisyllabic nouns","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":85,"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 Calgary; University of Northern British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noun; Object (grammar); Computer science; Psychology; Cognitive psychology; Linguistics; Natural language processing; Artificial intelligence; Philosophy","score_opus":0.34644763393504435,"score_gpt":0.5887497293982573,"score_spread":0.24230209546321296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087093006","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":[0.95904166,0.00037036717,0.026298584,0.0000483308,0.0007732542,0.0019223944,0.0000441351,0.0001106705,0.011390581],"genre_scores_gemma":[0.80236775,0.000027723452,0.19117914,0.000055358298,0.0002191422,0.002579609,0.00003678626,0.000057383433,0.0034771198],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99519295,0.0029546048,0.00035124875,0.0006334206,0.00028297745,0.0005847758],"domain_scores_gemma":[0.9973832,0.001339736,0.00008885537,0.00051704363,0.00049384893,0.00017736526],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008242314,0.0001715322,0.00026403513,0.00028152697,0.00029050847,0.00007745824,0.00021183652,0.00018112328,0.0023150344],"category_scores_gemma":[0.0015212797,0.00015151534,0.00012614432,0.00030317725,0.00030544391,0.00023095043,0.00010569544,0.00057224254,0.00008085021],"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":[0.00070455327,0.0009302904,0.011118242,0.00007189612,0.00005213517,0.000039198196,0.01770953,7.973939e-9,0.15465343,0.0011424177,0.00088866585,0.8126896],"study_design_scores_gemma":[0.0047179866,0.0029345641,0.7043853,0.00009530732,0.00035345217,0.00019958774,0.036619447,0.00014933739,0.22334665,0.0121169565,0.014150199,0.0009312294],"about_ca_topic_score_codex":0.0019290182,"about_ca_topic_score_gemma":0.00009257142,"teacher_disagreement_score":0.8117584,"about_ca_system_score_codex":0.00007408386,"about_ca_system_score_gemma":0.00004797875,"threshold_uncertainty_score":0.99859697},"labels":[],"label_agreement":null},{"id":"W2088635395","doi":"10.3758/brm.42.4.1087","title":"Visual regulation of manual aiming: A comparison of methods","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","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":"Brock University","funders":"","keywords":"Kinematics; Trajectory; Computer science; Physical medicine and rehabilitation; Movement (music); Visual control; Artificial intelligence; Outcome (game theory); Medicine; Mathematics","score_opus":0.4759983818703678,"score_gpt":0.6604666333591513,"score_spread":0.18446825148878354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088635395","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":[0.8709686,0.000028919123,0.12712015,0.000069078706,0.00031282342,0.00060936576,0.000008152177,0.000031152278,0.0008517894],"genre_scores_gemma":[0.67219573,0.0000027081321,0.32734242,0.000004523055,0.00004689341,0.00007037586,0.0000019849685,0.000014822325,0.00032051408],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931862,0.004630237,0.0006064157,0.00040203033,0.0008004077,0.00037475573],"domain_scores_gemma":[0.99580264,0.0030169464,0.00025234997,0.0004211165,0.00037188435,0.00013507875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00903116,0.0001229054,0.00037595254,0.00044973023,0.0001515658,0.000031289033,0.0003890861,0.00014900604,0.00026803327],"category_scores_gemma":[0.0058705863,0.00011090498,0.000119282995,0.00070935366,0.00047268876,0.00017900368,0.00014989213,0.00069427956,0.0000061099977],"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":[0.0000656003,0.00026218753,0.001067279,0.000019305015,0.0000014753045,7.945431e-7,0.00034834153,0.0000048848237,0.6756912,0.0027910857,0.0000116114825,0.31973627],"study_design_scores_gemma":[0.00034402564,0.00028797053,0.08097989,0.00001179456,0.000016544473,0.000003850905,0.00019448527,0.010402438,0.9052447,0.00076166156,0.0016630819,0.000089577006],"about_ca_topic_score_codex":0.00011294611,"about_ca_topic_score_gemma":0.000012627983,"teacher_disagreement_score":0.3196467,"about_ca_system_score_codex":0.00002209475,"about_ca_system_score_gemma":0.00010751795,"threshold_uncertainty_score":0.7028064},"labels":[],"label_agreement":null},{"id":"W2089598428","doi":"10.3758/brm.42.3.733","title":"Self-coded indirect memory associations and","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":32,"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, Okanagan Campus; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Coding (social sciences); Psychology; Substance use; Feeling; Social psychology; Cognitive psychology; Developmental psychology; Clinical psychology; Statistics; Mathematics","score_opus":0.23993648627419395,"score_gpt":0.5629900760061969,"score_spread":0.32305358973200293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089598428","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":[0.9932409,0.00033255504,0.000038411516,0.00041825615,0.00019091878,0.0007349331,0.0000034591715,0.00016045984,0.0048801294],"genre_scores_gemma":[0.5838109,0.00020176545,0.4081805,0.000070007474,0.00019939484,0.00037920638,0.000027738097,0.000045519748,0.0070849275],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99810815,0.0005240332,0.00017428321,0.0002751849,0.00050319347,0.00041517508],"domain_scores_gemma":[0.998061,0.0010380617,0.00003560136,0.00037985953,0.00023851832,0.00024697487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036740736,0.000117946875,0.00028679034,0.00030612233,0.00024665656,0.000042027645,0.00009599798,0.0001573528,0.00031162144],"category_scores_gemma":[0.001049737,0.000093468865,0.00007776352,0.0004498663,0.00013647704,0.0000959333,0.00006174006,0.0007994108,0.000044396053],"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":[0.00003682315,0.0004298848,0.7387533,0.000013527395,0.00008009194,0.00011036152,0.0023872177,6.250564e-9,0.083392985,0.00020704286,0.00049416564,0.17409457],"study_design_scores_gemma":[0.001838338,0.00014387628,0.90472215,0.000012406321,0.0001941469,0.000046214762,0.0006875764,0.00001681062,0.08721421,0.00019807901,0.004793286,0.00013292997],"about_ca_topic_score_codex":0.00003258371,"about_ca_topic_score_gemma":0.00009216403,"teacher_disagreement_score":0.40942994,"about_ca_system_score_codex":0.00009269018,"about_ca_system_score_gemma":0.00015760212,"threshold_uncertainty_score":0.38115498},"labels":[],"label_agreement":null},{"id":"W2089800891","doi":"10.3758/s13428-011-0155-z","title":"A test for psychometric function shift","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","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":"Queen's University","funders":"","keywords":"Psychometric function; Statistics; Test statistic; Nonparametric statistics; Statistic; Homogeneity (statistics); Contingency table; Mathematics; Psychometrics; Null distribution; Weibull distribution; Statistical hypothesis testing; Psychology","score_opus":0.6640702287473397,"score_gpt":0.5703768996849142,"score_spread":0.09369332906242545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089800891","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":[0.61819744,0.0004253759,0.3679207,0.00042600115,0.0005653441,0.00207705,0.00023668376,0.00020865069,0.0099427765],"genre_scores_gemma":[0.40724763,0.000023829683,0.5906276,0.000061745544,0.0002692266,0.00061968004,0.000029340623,0.0000029127234,0.0011179795],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967004,0.0016048973,0.0002872332,0.00046363234,0.00039122015,0.000552608],"domain_scores_gemma":[0.99261147,0.006663932,0.000052656116,0.00012725836,0.00029992522,0.0002447881],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077696876,0.00012919672,0.0002447022,0.00011444367,0.0004197109,0.0000710634,0.00033083753,0.00013116346,0.0027791578],"category_scores_gemma":[0.004702338,0.00004910409,0.00018824326,0.002007906,0.00014758721,0.00008504915,0.00006252201,0.0002875358,0.000047326692],"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":[0.00008691445,0.00041662683,0.009889688,0.0000049203613,0.000009430905,0.0000024393796,0.000048360598,2.3575096e-8,0.09584755,0.0030194416,0.00032691503,0.8903477],"study_design_scores_gemma":[0.00016369917,0.0017786393,0.9341694,0.0000060889997,0.00006180328,0.0000027147714,0.00023019098,0.00009078885,0.0077471645,0.025116527,0.030435989,0.00019696647],"about_ca_topic_score_codex":0.00023348285,"about_ca_topic_score_gemma":0.00006165857,"teacher_disagreement_score":0.92427975,"about_ca_system_score_codex":0.000027004264,"about_ca_system_score_gemma":0.000008929618,"threshold_uncertainty_score":0.9981324},"labels":[],"label_agreement":null},{"id":"W2090246898","doi":"10.3758/s13428-012-0244-7","title":"Assessing the evidence for response time mixture distributions","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","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":"University of Alberta","funders":"","keywords":"Quantile; Multinomial distribution; Statistics; Range (aeronautics); Mathematics; Mixture model; Categorical distribution; Residual; Sample size determination; Econometrics; Computer science; Probability distribution; Inverse-chi-squared distribution; Algorithm; Distribution fitting","score_opus":0.8694633089275018,"score_gpt":0.7394179691682082,"score_spread":0.13004533975929355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090246898","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":[0.9864513,0.0005897984,0.0037651667,0.007059834,0.00054308027,0.0013043077,0.000058907164,0.00009517575,0.00013241736],"genre_scores_gemma":[0.97460353,0.000039043964,0.018343413,0.00020545057,0.0003043175,0.0015727839,0.0000031334994,0.00003127988,0.0048970724],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9896479,0.008017083,0.00025586982,0.00048044723,0.0005419158,0.0010567557],"domain_scores_gemma":[0.9834625,0.015466072,0.00006706593,0.0005982109,0.00020940069,0.00019675557],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.014913289,0.00017195464,0.00020262372,0.00012198837,0.0018248806,0.00022274091,0.0006887015,0.000114186485,0.00012964584],"category_scores_gemma":[0.016047828,0.00010334259,0.00015420366,0.0008557778,0.0010152259,0.00074072176,0.0003414897,0.0007434001,0.00014029192],"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":[0.00016652052,0.00021689359,0.003655756,0.000004645576,0.000001637926,0.0000075811176,0.0001660734,4.3188358e-8,0.9585495,0.00010550014,0.0040626386,0.033063214],"study_design_scores_gemma":[0.00020628881,0.00021252925,0.13182217,0.00003782145,0.000050992814,0.00007102826,0.00025448593,0.0000088112365,0.8316357,0.0003390232,0.035171982,0.00018914414],"about_ca_topic_score_codex":0.000008523818,"about_ca_topic_score_gemma":5.170192e-7,"teacher_disagreement_score":0.1281664,"about_ca_system_score_codex":0.00010173168,"about_ca_system_score_gemma":0.00006831865,"threshold_uncertainty_score":0.9994746},"labels":[],"label_agreement":null},{"id":"W2091525225","doi":"10.3758/bf03192745","title":"NUANCE: Naturalistic University of Alberta Nonlinear Correlation Explorer","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Evolutionary Algorithms and Applications","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":true,"ca_institutions":"University of Alberta","funders":"Government of Canada","keywords":"Naturalism; Computer science; Correlation; Nonlinear system; Value (mathematics); Space (punctuation); Java; Selection (genetic algorithm); Artificial intelligence; Machine learning; Mathematics; Programming language; Epistemology; Operating system; Physics","score_opus":0.1288585428441985,"score_gpt":0.46415939054078387,"score_spread":0.33530084769658536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091525225","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":[0.025654864,0.00012414406,0.9718016,0.00043824833,0.000093629424,0.00027235673,0.0000053272747,0.00004054537,0.0015692802],"genre_scores_gemma":[0.07910639,0.000016831998,0.9175525,0.00000400915,0.000052158255,0.000013879804,0.00002212413,0.000006145009,0.0032259705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984481,0.00049408356,0.00014630746,0.00028878942,0.00038389736,0.00023882039],"domain_scores_gemma":[0.9984238,0.00061210233,0.000055761386,0.00048695004,0.00036771587,0.00005367033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012158959,0.000068316745,0.0001069744,0.00014143159,0.00026939664,0.000027779164,0.0006553092,0.00006837442,0.000066900226],"category_scores_gemma":[0.00007879367,0.00007062499,0.00005604389,0.00083694415,0.00018237131,0.00029286122,0.0002376771,0.00026995715,0.000050188068],"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":[0.00003413096,0.0016940596,0.017756049,0.00004732122,0.000019282184,0.000046333436,0.0016759577,0.00066723814,0.041263524,0.74084187,0.007189946,0.1887643],"study_design_scores_gemma":[0.0010597552,0.00022557091,0.5030967,0.00005861969,0.00003474585,0.000035420086,0.00053917215,0.37708342,0.007465663,0.0339404,0.075912476,0.0005480806],"about_ca_topic_score_codex":0.0019738628,"about_ca_topic_score_gemma":0.000052539388,"teacher_disagreement_score":0.70690143,"about_ca_system_score_codex":0.000076029624,"about_ca_system_score_gemma":0.000103956496,"threshold_uncertainty_score":0.29839033},"labels":[],"label_agreement":null},{"id":"W2092104032","doi":"10.3758/s13428-013-0335-0","title":"Models with discrete latent variables for analysis of categorical data: A framework and a MATLAB MDLV toolbox","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Time Series Analysis and Forecasting","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","funders":"","keywords":"Categorical variable; Toolbox; Latent variable; Computer science; Latent variable model; Data mining; Latent class model; Range (aeronautics); Machine learning; Econometrics; Probabilistic latent semantic analysis; Artificial intelligence; Mathematics","score_opus":0.3903748827202807,"score_gpt":0.5216524745550551,"score_spread":0.13127759183477444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092104032","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":[0.018232858,0.00022570328,0.9805408,0.0002735176,0.000020815998,0.0005363315,0.000035080404,0.000029953862,0.00010494214],"genre_scores_gemma":[0.19903329,0.000028545848,0.80044,0.000008961809,0.000020713005,0.00025530954,0.000028531082,0.000012841599,0.000171775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708897,0.00059931516,0.00039272246,0.0007457175,0.00061610295,0.00055717217],"domain_scores_gemma":[0.996266,0.0013175623,0.00012576065,0.001516535,0.000556771,0.00021736971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004510189,0.00015795275,0.00055162533,0.0005166385,0.00023576822,0.00047063403,0.0013231878,0.000104557745,0.000057858077],"category_scores_gemma":[0.0003441165,0.00010833043,0.000111420246,0.0027842696,0.00020108756,0.000976728,0.00101387,0.00030542564,0.0000012807199],"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":[0.00012433867,0.0005345615,0.013083254,0.00016552936,0.002183894,0.000030734845,0.0025917185,0.0047099064,0.004354902,0.370735,0.0005575182,0.60092866],"study_design_scores_gemma":[0.00016670479,0.00023948368,0.007619038,0.00002097067,0.00054603966,0.0000049556456,0.00020080298,0.9768404,0.0002477735,0.013658936,0.00027174893,0.0001831431],"about_ca_topic_score_codex":0.0018208335,"about_ca_topic_score_gemma":0.000037317754,"teacher_disagreement_score":0.9721305,"about_ca_system_score_codex":0.000033926623,"about_ca_system_score_gemma":0.00008825795,"threshold_uncertainty_score":0.45383346},"labels":[],"label_agreement":null},{"id":"W209594168","doi":"10.3758/s13428-015-0600-5","title":"PsiMLE: A maximum-likelihood estimation approach to estimating psychophysical scaling and variability more reliably, efficiently, and flexibly","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":29,"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; Bayesian probability; Statistics; Gaussian; Algorithm; Variance (accounting); Artificial intelligence; Mathematics; Pattern recognition (psychology)","score_opus":0.3820229668864004,"score_gpt":0.5778684082558168,"score_spread":0.19584544136941634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W209594168","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":[0.47029105,0.000012307774,0.5277348,0.00026934283,0.00015440861,0.0006622754,0.0000072593202,0.00011962673,0.0007488976],"genre_scores_gemma":[0.40364268,0.0000019480553,0.5958931,0.00012834482,0.00006183236,0.00018438278,0.0000032683422,0.000027674443,0.000056797715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943506,0.0024960092,0.0003597891,0.0010643794,0.0010675447,0.00066166034],"domain_scores_gemma":[0.9977375,0.00068385154,0.00006630632,0.00045032287,0.0002674244,0.0007945668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011495479,0.00022522327,0.0002986507,0.00031828144,0.00054424413,0.00047077378,0.000311867,0.00015083152,0.000013401485],"category_scores_gemma":[0.007175003,0.00020302509,0.000039074803,0.0011804112,0.00047619836,0.0002940411,0.0004063473,0.0006545332,0.000024615376],"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":[0.00014203749,0.00062767585,0.00013712764,0.00012428084,0.0000014646974,0.0000056340696,0.0040594703,0.00037255412,0.33153483,0.0011105136,0.00013759424,0.6617468],"study_design_scores_gemma":[0.0014457486,0.0008854965,0.002858668,0.00015023639,0.000040484934,0.0001370932,0.0015409411,0.87988365,0.0653635,0.04677136,0.000297307,0.000625519],"about_ca_topic_score_codex":0.000044787066,"about_ca_topic_score_gemma":2.827159e-7,"teacher_disagreement_score":0.8795111,"about_ca_system_score_codex":0.000107237654,"about_ca_system_score_gemma":0.00014394074,"threshold_uncertainty_score":0.8589667},"labels":[],"label_agreement":null},{"id":"W2097184733","doi":"10.3758/brm.41.3.664","title":"Randomization tests and the unequal-N/unequal-variance problem","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":21,"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":"Variance (accounting); Statistics; Value (mathematics); Analysis of variance; Type I and type II errors; Word error rate; Mathematics; Computer science; Econometrics; Algorithm; Speech recognition; Economics","score_opus":0.5240400499227096,"score_gpt":0.6774203494091746,"score_spread":0.15338029948646503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097184733","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":[0.04472293,0.0030830153,0.9244085,0.004957608,0.00039946364,0.005131354,0.000011757029,0.00015291444,0.017132461],"genre_scores_gemma":[0.14535812,0.00010386743,0.8496844,0.00020780778,0.00010563886,0.00046979843,0.0000023842085,0.00002678597,0.004041207],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9625892,0.03114322,0.0011257926,0.0010342356,0.0032829049,0.0008246419],"domain_scores_gemma":[0.9751085,0.021994848,0.00026080693,0.0013175973,0.0009873183,0.0003309188],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13020396,0.00026840589,0.000701457,0.000547941,0.0007807363,0.0010812175,0.0014340441,0.00018160902,0.0003485864],"category_scores_gemma":[0.0295601,0.00015472759,0.00017883966,0.0028094912,0.001104982,0.0006152187,0.00040340933,0.0006181231,0.0001083054],"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":[0.0014267263,0.00020918448,0.0004520642,0.000003453317,0.00000771756,0.000022739427,0.0015587636,0.000093309754,0.11126951,0.03581606,0.0008696936,0.8482708],"study_design_scores_gemma":[0.042202737,0.0024294558,0.05318082,0.0001642974,0.00014610137,0.00012495957,0.005244955,0.04489345,0.16514705,0.6534899,0.031327635,0.0016486772],"about_ca_topic_score_codex":0.00009767659,"about_ca_topic_score_gemma":0.0000046097744,"teacher_disagreement_score":0.8466221,"about_ca_system_score_codex":0.00010251862,"about_ca_system_score_gemma":0.0001754634,"threshold_uncertainty_score":0.9999558},"labels":[],"label_agreement":null},{"id":"W2102418552","doi":"10.3758/s13428-015-0671-3","title":"Tap Arduino: An Arduino microcontroller for low-latency auditory feedback in sensorimotor synchronization experiments","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":49,"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; International Laboratory for Brain, Music and Sound Research","funders":"","keywords":"Arduino; Latency (audio); Computer science; Microcontroller; Synchronization (alternating current); Psychology; Computer hardware; Embedded system; Telecommunications","score_opus":0.4710063187495546,"score_gpt":0.5808894954880336,"score_spread":0.10988317673847897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102418552","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":[0.9866362,0.000025014908,0.007685575,0.00009318309,0.0018149461,0.0030693563,0.000027529783,0.00009993028,0.000548224],"genre_scores_gemma":[0.9714741,0.00004206036,0.022465566,0.00024564995,0.0006876114,0.0025902053,0.000013659775,0.00007462819,0.0024065066],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931897,0.0029589029,0.00049294886,0.0011628738,0.0011146998,0.0010808908],"domain_scores_gemma":[0.9978224,0.0004686987,0.000112193804,0.0006974522,0.00039029418,0.00050897914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0051675295,0.00026251777,0.00035243385,0.00061727356,0.0003543852,0.0002289053,0.00069152476,0.00019953317,0.000111119894],"category_scores_gemma":[0.0028184801,0.00024941596,0.00010556454,0.00096152263,0.0004376169,0.00091834716,0.0001912437,0.0005066081,0.00011526315],"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":[0.00017311401,0.0006762954,0.0006510493,0.000015817282,7.447256e-7,0.00004458841,0.0009229055,0.000020121623,0.9650164,0.000044409244,0.0010109525,0.03142355],"study_design_scores_gemma":[0.005065003,0.0014657223,0.03897846,0.000067253786,0.000021625232,0.00005124242,0.0012402061,0.0043734345,0.9347315,0.0005692216,0.012755186,0.0006811603],"about_ca_topic_score_codex":0.00010386696,"about_ca_topic_score_gemma":0.000012631022,"teacher_disagreement_score":0.03832741,"about_ca_system_score_codex":0.0005248593,"about_ca_system_score_gemma":0.00044929015,"threshold_uncertainty_score":0.9999958},"labels":[],"label_agreement":null},{"id":"W2112767951","doi":"10.3758/bf03192797","title":"The use of digital video recorders (DVRs) for capturing digital video files for use in both The Observer and Ethovision","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture Food and Rural Development","funders":"","keywords":"Computer science; Observer (physics); Digital recording; Digital video; Software; Uncompressed video; Data compression; Multimedia; Video capture; Video processing; Real-time computing; Computer vision; Video tracking; Computer graphics (images); Computer hardware; Telecommunications","score_opus":0.34555193713925075,"score_gpt":0.47788746533170984,"score_spread":0.13233552819245908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112767951","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":[0.2712802,0.00018548037,0.7265932,0.00058892893,0.000082971215,0.0011588901,0.00006935347,0.00002372839,0.000017241167],"genre_scores_gemma":[0.5187135,0.00011115708,0.47826222,0.00003434678,0.00008797557,0.00070170825,0.00006833577,0.0000466503,0.0019740954],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974612,0.00062838977,0.00048553126,0.00046200908,0.0004902572,0.00047262732],"domain_scores_gemma":[0.9892015,0.009571627,0.00012432433,0.00065903726,0.00037500428,0.000068522175],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004563616,0.0001435116,0.00023356806,0.00021556251,0.00044568736,0.002305298,0.00067140325,0.000088793466,0.0000014131244],"category_scores_gemma":[0.0034326352,0.00008742534,0.00016900118,0.00065425254,0.00021917232,0.0019576761,0.00041360804,0.00021810678,4.2851502e-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":[0.00011210479,0.00019035302,0.08290124,0.000032256085,0.000022456074,0.0000041297662,0.00040534572,0.00044712477,0.002719791,0.0057750936,0.0020860701,0.905304],"study_design_scores_gemma":[0.0023241779,0.0007204793,0.4673295,0.0001935986,0.00008266582,0.000010262105,0.00084989396,0.36549386,0.005485448,0.020779142,0.13595688,0.00077408645],"about_ca_topic_score_codex":0.00075358554,"about_ca_topic_score_gemma":0.00052695564,"teacher_disagreement_score":0.9045299,"about_ca_system_score_codex":0.000056954825,"about_ca_system_score_gemma":0.00008299605,"threshold_uncertainty_score":0.9987304},"labels":[],"label_agreement":null},{"id":"W2115529213","doi":"10.3758/s13428-010-0056-6","title":"SMART-T: A system for novel fully automated anticipatory eye-tracking paradigms","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","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":"University of Waterloo","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health","keywords":"Computer science; Eye tracking; Toolbox; Gaze; Generalization; Artificial intelligence; Categorization; Human–computer interaction; Scripting language; BitTorrent tracker; Machine learning","score_opus":0.5290336555325987,"score_gpt":0.6079804468599023,"score_spread":0.07894679132730353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115529213","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":[0.9381183,0.0004770784,0.03213745,0.00008612109,0.0018788655,0.0025973278,0.000050821047,0.0015775062,0.023076575],"genre_scores_gemma":[0.7728857,0.0000024303736,0.22355486,0.000024381206,0.00015442188,0.0012465824,0.000016601083,0.000090226844,0.0020248317],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954849,0.001509594,0.00053629396,0.00078048365,0.00049498235,0.0011937433],"domain_scores_gemma":[0.9979111,0.000632147,0.00012920538,0.00063673983,0.000379996,0.00031079145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009596342,0.00025474728,0.00043156798,0.0004363081,0.0004810131,0.000087372624,0.0005519433,0.00025219523,0.0005352521],"category_scores_gemma":[0.00044628527,0.00023312855,0.00018447168,0.00051857025,0.00022065984,0.00009495744,0.00016453228,0.00069412444,0.00027161933],"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":[0.0017133424,0.003731627,0.22485963,0.00075093005,0.0005512819,0.00072817167,0.04632861,0.0000017395091,0.28232577,0.0881571,0.0065028598,0.34434894],"study_design_scores_gemma":[0.0012988162,0.00050379307,0.95536125,0.00016982385,0.000064508065,0.00006309675,0.00291806,0.00020863552,0.007939799,0.000043417513,0.031026332,0.00040247603],"about_ca_topic_score_codex":0.00032822037,"about_ca_topic_score_gemma":0.000008248038,"teacher_disagreement_score":0.73050165,"about_ca_system_score_codex":0.00019319862,"about_ca_system_score_gemma":0.00018286749,"threshold_uncertainty_score":0.9506706},"labels":[],"label_agreement":null},{"id":"W2124006395","doi":"10.3758/brm.42.2.393","title":"Exploring lexical co-occurrence space using HiDEx","year":2010,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":154,"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; Representation (politics); Co-occurrence; Set (abstract data type); Space (punctuation); A priori and a posteriori; Semantic space; Lexical decision task; Natural language processing; Artificial intelligence; Basis (linear algebra); Semantic data model; Hyperspace; Mathematics; Cognition","score_opus":0.8360044474353515,"score_gpt":0.6474662355025267,"score_spread":0.18853821193282483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124006395","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":[0.38136914,0.000021662781,0.61704075,0.00022201872,0.00070271804,0.00021176887,0.000003043973,0.00012160437,0.00030728517],"genre_scores_gemma":[0.19802347,0.000010282287,0.80154175,0.000013067284,0.0001819388,0.0001256436,0.0000013392211,0.000013019642,0.000089482026],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995764,0.0012340819,0.00030190145,0.00075770053,0.0010371456,0.0009051346],"domain_scores_gemma":[0.9970671,0.0007812361,0.000051303017,0.0014315515,0.00027977768,0.00038902316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008494222,0.00016674571,0.00022395492,0.0003922172,0.00041409256,0.00038646997,0.0018214254,0.00011168966,0.000073107636],"category_scores_gemma":[0.0010712431,0.00016110092,0.00008964767,0.00081148755,0.00022357336,0.0010389443,0.0009058259,0.0017216079,0.000051338742],"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":[0.0000039833626,0.00011736069,0.0041662026,0.000016270282,0.0000037835737,0.000096642456,0.00076991855,0.000040034887,0.39333966,0.026266815,0.000086853215,0.5750925],"study_design_scores_gemma":[0.00093081285,0.00022101378,0.019870378,0.00011863639,0.000024347959,0.0003467642,0.0004939048,0.32668617,0.58774334,0.00729882,0.054878734,0.0013870758],"about_ca_topic_score_codex":0.00022102374,"about_ca_topic_score_gemma":0.000008650139,"teacher_disagreement_score":0.5737054,"about_ca_system_score_codex":0.000086892935,"about_ca_system_score_gemma":0.0002970342,"threshold_uncertainty_score":0.74796253},"labels":[],"label_agreement":null},{"id":"W2130509954","doi":"10.3758/s13428-011-0067-y","title":"A novel integrative method for analyzing eye and hand behaviour during reaching and grasping in an MRI environment","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","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 Manitoba","funders":"","keywords":"Computer science; Kinematics; Artificial intelligence; Neuroimaging; Computer vision; Gaze; Functional magnetic resonance imaging; Software; Human–computer interaction; Neuroscience; Psychology","score_opus":0.34878348153452177,"score_gpt":0.5227324701129151,"score_spread":0.17394898857839336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130509954","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":[0.6099896,0.00006802438,0.38911003,0.00002831053,0.0000230762,0.0007384872,0.000008159641,0.000013800684,0.00002053194],"genre_scores_gemma":[0.5645398,0.000041279207,0.43485692,0.000008117731,0.000019325427,0.00043758884,0.0000015235115,0.00002184159,0.00007365435],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9961474,0.0019364618,0.00032188944,0.0007724237,0.00030212087,0.00051968364],"domain_scores_gemma":[0.99861944,0.0007814911,0.000086519314,0.00025224983,0.000048790873,0.00021149084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005665158,0.00018781955,0.00028613486,0.0004978788,0.00052011467,0.0001710962,0.00019465362,0.00009212956,0.000012978225],"category_scores_gemma":[0.0009603553,0.0001641529,0.000047980007,0.00023369046,0.00023699032,0.0004836638,0.000183008,0.0005262548,4.4903894e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011788902,0.0001707981,0.015864395,0.00001833519,0.0000021818387,0.000017489705,0.0059661176,0.000003665368,0.91400117,0.0006038359,8.570228e-8,0.06323404],"study_design_scores_gemma":[0.0016356331,0.00047230007,0.58661914,0.000084624786,0.000039741502,0.000024674608,0.0019410577,0.009456172,0.3985541,0.00085150125,0.000029266841,0.00029180516],"about_ca_topic_score_codex":0.00084310427,"about_ca_topic_score_gemma":0.00015402965,"teacher_disagreement_score":0.57075477,"about_ca_system_score_codex":0.00010253257,"about_ca_system_score_gemma":0.000035073634,"threshold_uncertainty_score":0.6693961},"labels":[],"label_agreement":null},{"id":"W2131425739","doi":"10.3758/s13428-011-0154-0","title":"The Slip Induction Task: Creating a window into cognitive control failures","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":10,"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":"Task (project management); Action (physics); Cognition; sort; Cognitive psychology; Slip (aerodynamics); Psychology; Computer science; Engineering; Neuroscience","score_opus":0.654021635508505,"score_gpt":0.6161776168764262,"score_spread":0.03784401863207876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131425739","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":[0.9930535,0.00017580773,0.0007085143,0.0007360326,0.00055801036,0.0012665397,0.0000131662355,0.00012048766,0.003367925],"genre_scores_gemma":[0.99337536,0.00006259266,0.0037943097,0.00014932081,0.00014836817,0.001058445,7.6112127e-7,0.000030309946,0.0013805077],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9923189,0.00510399,0.00034915598,0.00072463846,0.00066355796,0.00083970337],"domain_scores_gemma":[0.9960232,0.0029561042,0.00011337913,0.000388169,0.00034558788,0.00017356842],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0042787036,0.00022302406,0.00026329595,0.00019995593,0.0023407245,0.00013305913,0.0005864123,0.00013514954,0.00011492698],"category_scores_gemma":[0.004280068,0.00013926171,0.0001236854,0.00074543443,0.001902747,0.00027047624,0.00027707306,0.001166871,0.000110410845],"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":[0.00023452297,0.00022676957,0.010495763,0.0000037127782,0.0000070974625,0.00007755563,0.0016796931,2.0688413e-8,0.74347955,0.00026303815,0.00015737323,0.24337488],"study_design_scores_gemma":[0.0009803573,0.00076010346,0.1519188,0.000032538333,0.000069762835,0.000075163254,0.0041632303,0.0000043180967,0.8374684,0.0024008057,0.0018659746,0.00026057995],"about_ca_topic_score_codex":0.0006510444,"about_ca_topic_score_gemma":0.00007543417,"teacher_disagreement_score":0.2431143,"about_ca_system_score_codex":0.000057366473,"about_ca_system_score_gemma":0.00005194053,"threshold_uncertainty_score":0.9989581},"labels":[],"label_agreement":null},{"id":"W2138172448","doi":"10.3758/brm.40.2.531","title":"The Montreal Affective Voices: A validated set of nonverbal affect bursts for research on auditory affective processing","year":2008,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":476,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"Economic and Social Research Council; Medical Research Council","keywords":"Sadness; Psychology; Disgust; Anger; Surprise; Affect (linguistics); Happiness; Valence (chemistry); Audiology; Nonverbal communication; Arousal; Facial expression; Developmental psychology; Clinical psychology; Social psychology; Communication","score_opus":0.5345840841783612,"score_gpt":0.6108165772882865,"score_spread":0.0762324931099253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138172448","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":[0.9916743,0.000033291173,0.0022515515,0.00017501148,0.0006229156,0.0038316916,0.00007038907,0.000092154965,0.001248691],"genre_scores_gemma":[0.994338,0.00013044337,0.0014812079,0.000037251695,0.00042332328,0.002256948,0.000004124967,0.000056700486,0.0012719972],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98292863,0.011444076,0.0003576235,0.0012463782,0.002527962,0.0014953221],"domain_scores_gemma":[0.98321325,0.014615627,0.00015669916,0.00079868507,0.0009330713,0.0002826653],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0178037,0.00027255638,0.0003765534,0.00070864335,0.0032971797,0.00017724275,0.0011573503,0.0001918509,0.000016908798],"category_scores_gemma":[0.0106373,0.00019266029,0.00020470534,0.0025808753,0.0032715981,0.00046219514,0.00035755843,0.001381092,0.000032245476],"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":[0.00060507003,0.00035111932,0.000110646084,0.0000480727,0.0000029416433,0.00005862567,0.0028800769,0.000009045314,0.89086765,0.000085204956,0.0019927477,0.10298877],"study_design_scores_gemma":[0.0010911487,0.0033909983,0.06494212,0.00012969576,0.00001873293,0.000068688765,0.0014033135,0.00096900685,0.92461884,0.00057694095,0.0025184979,0.00027202736],"about_ca_topic_score_codex":0.00048557948,"about_ca_topic_score_gemma":0.000105069965,"teacher_disagreement_score":0.102716744,"about_ca_system_score_codex":0.00041756936,"about_ca_system_score_gemma":0.00071393093,"threshold_uncertainty_score":0.9994409},"labels":[],"label_agreement":null},{"id":"W2142398106","doi":"10.3758/s13428-012-0203-3","title":"Recognizing vocal emotions in Mandarin Chinese: A validated database of Chinese vocal emotional stimuli","year":2012,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":123,"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":"Sadness; Disgust; Mandarin Chinese; Anger; Happiness; Surprise; Psychology; Prosody; Audiology; Cognitive psychology; Speech recognition; Social psychology; Computer science; Linguistics","score_opus":0.37637237552285974,"score_gpt":0.6081377045351003,"score_spread":0.23176532901224056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142398106","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":[0.9612498,0.00022321328,0.029241132,0.00027314413,0.0012379013,0.0009274975,0.00024914398,0.00008594541,0.0065122126],"genre_scores_gemma":[0.92796004,0.000029289542,0.06890664,0.000033513264,0.00037619701,0.00034203997,0.00059892936,0.0000602526,0.0016931006],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9914575,0.0054966854,0.000683083,0.00054754724,0.00079362973,0.00102151],"domain_scores_gemma":[0.9972009,0.0011304162,0.00013304625,0.0006473224,0.00045335313,0.00043495168],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010747268,0.00027861824,0.00045410378,0.0012137583,0.00022238518,0.000041051368,0.00036890755,0.00030579354,0.0065647867],"category_scores_gemma":[0.0018462519,0.00024161753,0.00017967196,0.0019452963,0.0003781555,0.00040596246,0.00028987433,0.0013155956,0.0003306413],"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":[0.00041439754,0.0066660866,0.63320285,0.0001333799,0.00008280495,0.00008653336,0.0039421576,0.000004756005,0.06693611,0.001327358,0.0016434953,0.2855601],"study_design_scores_gemma":[0.0019929912,0.00018666414,0.99410427,0.00010759162,0.000028291122,0.00012066859,0.000616515,0.000138041,0.0009494856,0.00056590635,0.00092605915,0.00026352724],"about_ca_topic_score_codex":0.0004788173,"about_ca_topic_score_gemma":0.00010826741,"teacher_disagreement_score":0.36090145,"about_ca_system_score_codex":0.00013747597,"about_ca_system_score_gemma":0.00012769153,"threshold_uncertainty_score":0.99434334},"labels":[],"label_agreement":null},{"id":"W2143342006","doi":"10.3758/s13428-015-0682-0","title":"Quantifying online visuomotor feedback utilization in the frequency domain","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":13,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequency domain; Computer science; Acceleration; Detrended fluctuation analysis; Feedback control; Control (management); Artificial intelligence; Mathematics; Computer vision; Control engineering","score_opus":0.7533497313562453,"score_gpt":0.6120796684353152,"score_spread":0.14127006292093003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143342006","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":[0.9771397,0.00016030029,0.018685648,0.0010252073,0.0002508679,0.0012788393,0.000018698847,0.00005466406,0.0013860759],"genre_scores_gemma":[0.916977,0.000036493308,0.082036704,0.00018382253,0.00014641749,0.00033525933,0.000013350507,0.000025978437,0.00024496508],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9897756,0.007815328,0.00033381346,0.0004358688,0.0011238254,0.0005155373],"domain_scores_gemma":[0.9978425,0.0013062629,0.000066830886,0.0004407083,0.00019347639,0.00015024841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010794049,0.00012773593,0.00016598987,0.000325509,0.0002138618,0.00016725494,0.00062224787,0.00008782652,0.00005555084],"category_scores_gemma":[0.005664094,0.000089836656,0.000055313325,0.0013243533,0.0001863027,0.0002970667,0.00009182211,0.00058463385,0.00004900248],"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":[0.000056500216,0.0005124375,0.0035408775,0.000011462179,7.687398e-7,0.00009465928,0.0023782263,0.0000056833005,0.8943621,0.010197303,0.000064964814,0.08877503],"study_design_scores_gemma":[0.007351467,0.0018262302,0.7697163,0.0001998102,0.0000423437,0.00017778763,0.021444125,0.012161478,0.09851093,0.054564763,0.032834794,0.0011699566],"about_ca_topic_score_codex":0.0003698813,"about_ca_topic_score_gemma":0.00018281133,"teacher_disagreement_score":0.7958512,"about_ca_system_score_codex":0.00012409041,"about_ca_system_score_gemma":0.00018093991,"threshold_uncertainty_score":0.67808586},"labels":[],"label_agreement":null},{"id":"W2148999650","doi":"10.3758/s13428-015-0667-z","title":"Effect size measures in a two-independent-samples case with nonnormal and nonhomogeneous data","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":83,"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":"Statistics; Computer science; Mathematics","score_opus":0.9138052411701298,"score_gpt":0.754588885036263,"score_spread":0.15921635613386687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148999650","genre_codex":"empirical","genre_gemma":"methods","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":[0.80796933,0.00033410738,0.18629968,0.00011146805,0.00031738429,0.003517406,0.00038348595,0.00013390977,0.00093322434],"genre_scores_gemma":[0.12591474,0.000015586162,0.8732692,0.000013373797,0.0001810149,0.00039196856,0.00000480559,0.000079038444,0.00013025869],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.963642,0.03142296,0.00094439863,0.0011389913,0.0018158832,0.001035775],"domain_scores_gemma":[0.78370845,0.21261178,0.0001616978,0.002150407,0.0005286045,0.0008390655],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1264354,0.00034646178,0.0010464878,0.00028269083,0.00017308493,0.00020635131,0.0009911794,0.00021073862,0.000096069976],"category_scores_gemma":[0.33380154,0.00025169257,0.000058353267,0.0007451635,0.0007577518,0.00020587424,0.0015107729,0.0014132543,0.00001281175],"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":[0.002492505,0.0009369171,0.02821771,0.0003417199,0.00009777203,0.02567615,0.0006471905,0.0000030587187,0.0028971918,0.0031216976,0.00032236433,0.93524575],"study_design_scores_gemma":[0.067055,0.021375934,0.019569408,0.0018764902,0.0026957844,0.048842784,0.006403408,0.0054405723,0.0713721,0.7460118,0.0042204564,0.0051362463],"about_ca_topic_score_codex":0.0015045638,"about_ca_topic_score_gemma":0.0012985477,"teacher_disagreement_score":0.9301095,"about_ca_system_score_codex":0.00015234793,"about_ca_system_score_gemma":0.00036556122,"threshold_uncertainty_score":0.9999935},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2151069696","doi":"10.3758/s13428-010-0049-5","title":"A tutorial on a practical Bayesian alternative to null-hypothesis significance testing","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":773,"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","funders":"","keywords":"Null hypothesis; Null (SQL); Statistical hypothesis testing; Bayesian probability; Bayes factor; Alternative hypothesis; Computer science; p-value; Worksheet; Bayesian inference; Significance testing; Multiple comparisons problem; Bayesian statistics; Econometrics; Artificial intelligence; Statistics; Data mining; Psychology; Mathematics","score_opus":0.7699708216302553,"score_gpt":0.5899453915272571,"score_spread":0.1800254301029982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151069696","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":[0.7409453,0.000026345424,0.09828166,0.013166258,0.006257567,0.008760469,0.0001502386,0.00095795107,0.13145426],"genre_scores_gemma":[0.5004508,0.0000032189891,0.4948706,0.00084545143,0.00074999116,0.00184372,1.932028e-7,0.00006830219,0.0011677044],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99104625,0.0052533383,0.00028696287,0.0011579557,0.0014050953,0.0008503984],"domain_scores_gemma":[0.9271729,0.07132912,0.0000832514,0.00061652454,0.0004306823,0.00036751438],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063574794,0.00023383298,0.0002987778,0.00045102419,0.0006274379,0.00011054155,0.00051252765,0.00009061792,0.00027923932],"category_scores_gemma":[0.30547068,0.00021120123,0.00008853028,0.0014885732,0.0004268976,0.00023872755,0.00041574013,0.00092126144,0.00033610722],"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":[0.00096352847,0.0012269847,0.0015893808,0.000015688242,0.000015730247,0.00056962663,0.002313235,0.000005893584,0.84267807,0.008820749,0.0037988888,0.1380022],"study_design_scores_gemma":[0.00044358207,0.002204234,0.018847084,0.000053680684,0.000020743944,0.000051381518,0.00042493225,0.00019635231,0.9618233,0.0063370536,0.009199695,0.00039794904],"about_ca_topic_score_codex":0.00049283553,"about_ca_topic_score_gemma":0.000019424455,"teacher_disagreement_score":0.39658895,"about_ca_system_score_codex":0.00032070468,"about_ca_system_score_gemma":0.0002712688,"threshold_uncertainty_score":0.8612536},"labels":[],"label_agreement":null},{"id":"W2167848283","doi":"10.3758/s13428-011-0101-0","title":"The nature of orthographic–phonological and orthographic–semantic relationships for Japanese kana and kanji words","year":2011,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":22,"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":"Kana; Kanji; Linguistics; Word (group theory); Natural language processing; Psychology; Reading (process); Orthographic projection; Artificial intelligence; Computer science; Chinese characters","score_opus":0.3132455091299252,"score_gpt":0.5334611814445118,"score_spread":0.2202156723145866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167848283","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":[0.9905383,0.0047648004,0.0006184892,0.0002105949,0.00029780617,0.0010562554,0.0000136804465,0.000042239943,0.002457831],"genre_scores_gemma":[0.930707,0.0004049089,0.06599627,0.000015013189,0.000034191526,0.0007709772,0.000008495801,0.000027680931,0.0020355056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99505794,0.003019608,0.00045880067,0.0005275338,0.00032962498,0.0006065159],"domain_scores_gemma":[0.99468756,0.004104949,0.000113881244,0.0005770071,0.0003166337,0.00019995485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012411784,0.00018264509,0.00029829633,0.00052591827,0.0006987772,0.000064489286,0.00032922905,0.00043602556,0.000079569094],"category_scores_gemma":[0.0013751218,0.00011900166,0.000109276414,0.00092355465,0.0010534539,0.00007598908,0.00015713586,0.0013579113,0.000002701669],"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":[0.00045902785,0.00030699483,0.74266154,0.00007003164,0.00012631435,0.000030272358,0.016617503,1.6365695e-8,0.0009375432,0.038755484,0.00054842007,0.19948688],"study_design_scores_gemma":[0.00047370375,0.00031545584,0.98046774,0.000041324358,0.000053783515,0.00005793335,0.0049659996,0.0000060633533,0.00018178382,0.004369674,0.008905653,0.00016090149],"about_ca_topic_score_codex":0.00017005253,"about_ca_topic_score_gemma":0.00007053384,"teacher_disagreement_score":0.23780622,"about_ca_system_score_codex":0.000010646851,"about_ca_system_score_gemma":0.000040180177,"threshold_uncertainty_score":0.58995247},"labels":[],"label_agreement":null},{"id":"W2188479190","doi":"10.3758/s13428-015-0679-8","title":"Thematic relatedness production norms for 100 object concepts","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":28,"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":"Thematic map; Locative case; Attributive; Computer science; Object (grammar); Similarity (geometry); Cognition; Cognitive science; Psychology; Cognitive psychology; Linguistics; Natural language processing; Artificial intelligence","score_opus":0.6433840902575432,"score_gpt":0.6503699384502034,"score_spread":0.006985848192660238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188479190","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":[0.99354213,0.00014802208,0.0012475221,0.00053525803,0.0011575215,0.001959037,0.000011451662,0.00015774876,0.0012412805],"genre_scores_gemma":[0.9134035,0.000034330085,0.06383658,0.0002511213,0.0006090519,0.0015546908,0.000014260882,0.000088297944,0.020208148],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9948781,0.0029668433,0.0003051406,0.00070718775,0.0005034948,0.0006391929],"domain_scores_gemma":[0.99712104,0.0016217896,0.00008354527,0.0005904448,0.00036843715,0.00021474468],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008474381,0.00015878353,0.0002604897,0.00024965772,0.00030990856,0.00006900417,0.00049912755,0.00015231539,0.000068642075],"category_scores_gemma":[0.018404577,0.00011687819,0.000096346994,0.00066152774,0.0005711661,0.000200131,0.00016272427,0.0005590818,0.00007692538],"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":[0.00009581171,0.00021996858,0.00011668102,0.00003720864,0.00000264542,0.0001695356,0.002677288,0.0000023125285,0.9250015,0.00021639129,0.0013940001,0.07006663],"study_design_scores_gemma":[0.0005523084,0.0005248606,0.0000758507,0.00003163333,0.00001970639,0.00046095092,0.0016596142,0.000041199077,0.9893222,0.0023237085,0.004802707,0.00018525061],"about_ca_topic_score_codex":0.000039197108,"about_ca_topic_score_gemma":0.0000055045252,"teacher_disagreement_score":0.08013864,"about_ca_system_score_codex":0.000085428714,"about_ca_system_score_gemma":0.00022556564,"threshold_uncertainty_score":0.9898638},"labels":[],"label_agreement":null},{"id":"W2229247805","doi":"10.3758/s13428-015-0699-4","title":"Erratum to: Manipulability agreement as a predictor of action initiation latency","year":2016,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","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; Douglas Mental Health University Institute; Université de Moncton","funders":"","keywords":"Latency (audio); Agreement; Computer science; Action (physics); Psychology; Physics; Telecommunications; Philosophy; Linguistics","score_opus":0.4731936428423508,"score_gpt":0.6126827588171884,"score_spread":0.13948911597483754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229247805","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":[0.063053645,0.0012939941,0.17848101,0.004745653,0.18158056,0.015236933,0.00095247984,0.0007461636,0.55390954],"genre_scores_gemma":[0.013419729,0.00034512713,0.010988716,0.00014877741,0.0023350702,0.0028363136,0.001093778,0.00016754663,0.96866494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898768,0.0057115904,0.0010785306,0.0009888429,0.0016358633,0.0007083477],"domain_scores_gemma":[0.99513036,0.00053176575,0.0005033917,0.0013609839,0.0021376356,0.0003358666],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007380059,0.00036010967,0.0005859235,0.0010746189,0.00025458008,0.00006605301,0.0005863554,0.0011570873,0.01843612],"category_scores_gemma":[0.0024452528,0.0003192121,0.00020954378,0.001212062,0.00020924969,0.00025929578,0.00023429691,0.0015558513,0.0010830921],"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":[0.00021579555,0.00073556177,0.004542202,0.00020598543,0.00008153473,0.000013621534,0.0011640202,5.4531495e-7,0.0074077924,0.0011943718,0.8466434,0.1377952],"study_design_scores_gemma":[0.0011012146,0.0013021892,0.26144332,0.00038614488,0.00012587503,0.000015805404,0.0010811535,0.000035224963,0.002755633,0.0021838667,0.7289745,0.00059503614],"about_ca_topic_score_codex":0.0005023028,"about_ca_topic_score_gemma":0.0000877313,"teacher_disagreement_score":0.4147554,"about_ca_system_score_codex":0.00095157546,"about_ca_system_score_gemma":0.00073901616,"threshold_uncertainty_score":0.999926},"labels":[],"label_agreement":null},{"id":"W2260068509","doi":"10.3758/s13428-015-0696-7","title":"A simple technique to study embodied language processes: the grip force sensor","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":31,"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":"Centre National de la Recherche Scientifique","keywords":"Embodied cognition; Computer science; Artifact (error); Brain activity and meditation; Modality (human–computer interaction); Perception; Cognition; Action (physics); Human–computer interaction; Measure (data warehouse); Motor cortex; Cognitive psychology; Artificial intelligence; Electroencephalography; Psychology; Neuroscience; Data mining","score_opus":0.4750688339849863,"score_gpt":0.6410319682460859,"score_spread":0.1659631342610996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260068509","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":[0.65003705,0.00011165836,0.3244545,0.0013351984,0.00040732825,0.00888628,0.00002187827,0.00038569304,0.0143604195],"genre_scores_gemma":[0.91452307,0.000001808754,0.051283892,0.00031186774,0.00024159873,0.007818373,0.000027197357,0.00007074041,0.025721436],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9939114,0.004261049,0.00030133539,0.0004121071,0.0006693256,0.00044480799],"domain_scores_gemma":[0.9973245,0.0006242006,0.0000641327,0.0007665995,0.00097318925,0.0002473623],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010080698,0.00013517297,0.0001797786,0.00025470433,0.00028957604,0.00010191568,0.00047260852,0.000112461734,0.000980441],"category_scores_gemma":[0.0031033186,0.00009631428,0.00003587438,0.0016338144,0.00007982968,0.00013259306,0.00017161906,0.00048010668,0.00028786645],"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":[0.0008890736,0.006549438,0.14688757,0.000092809525,0.0001786589,0.00037361335,0.3003738,0.000042703778,0.059187505,0.003718082,0.06944484,0.4122619],"study_design_scores_gemma":[0.0044068974,0.004161343,0.17768575,0.00003538055,0.00013920358,0.00014504905,0.5792789,0.00014256492,0.04465416,0.0028046484,0.18549566,0.0010504426],"about_ca_topic_score_codex":0.00058690057,"about_ca_topic_score_gemma":0.00010060524,"teacher_disagreement_score":0.41121146,"about_ca_system_score_codex":0.00014765373,"about_ca_system_score_gemma":0.00018844665,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W2288693139","doi":"10.3758/s13428-016-0720-6","title":"The Calgary semantic decision project: concrete/abstract decision data for 10,000 English words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":101,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Lexical decision task; Computer science; Lexicon; Natural language processing; Semantics (computer science); Semantic memory; Artificial intelligence; Variance (accounting); Word (group theory); Task (project management); Semantic property; Linguistics; Psychology; Cognitive psychology; Cognition","score_opus":0.4123654394581135,"score_gpt":0.5860038097873501,"score_spread":0.17363837032923662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288693139","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":[0.9785309,0.0004994902,0.014362133,0.00034893077,0.0016240237,0.0032683269,0.0004717071,0.00019813643,0.00069639616],"genre_scores_gemma":[0.6623589,0.0024485127,0.30856287,0.0006799525,0.002663203,0.0025528108,0.00012343975,0.00038921108,0.020221084],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99323124,0.002546976,0.00061267515,0.0014392722,0.0009898095,0.0011800337],"domain_scores_gemma":[0.9482292,0.048326544,0.00013440922,0.0026888987,0.00041347416,0.00020748498],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017015845,0.00026669636,0.0003413282,0.0002909276,0.001194354,0.00027524706,0.00314365,0.00024411327,0.00027151054],"category_scores_gemma":[0.070922025,0.00013499486,0.0001418692,0.0006260252,0.00100867,0.00041475927,0.0015590946,0.0006203178,0.00005905383],"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":[0.0003972859,0.000035376735,0.000059314014,0.000006790058,0.000002543905,0.00022633698,0.00018199293,1.7094141e-8,0.42775524,0.00005719122,0.006131289,0.5651466],"study_design_scores_gemma":[0.0021504797,0.0008184655,0.001126311,0.00023679751,0.00004970259,0.0002606533,0.00045788003,0.00011072216,0.5035612,0.0021057413,0.48860696,0.0005150758],"about_ca_topic_score_codex":0.0000891411,"about_ca_topic_score_gemma":0.000041426876,"teacher_disagreement_score":0.5646315,"about_ca_system_score_codex":0.000071681745,"about_ca_system_score_gemma":0.00031695742,"threshold_uncertainty_score":0.936904},"labels":[],"label_agreement":null},{"id":"W2290759784","doi":"10.3758/s13428-015-0700-2","title":"Norms of valence and arousal for 14,031 Spanish words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":202,"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":"Valence (chemistry); Psychology; Arousal; Verb; Emotional valence; Linguistics; Stimulus (psychology); Neuroscience of multilingualism; Cognitive psychology; Age of Acquisition; Social psychology; Cognition","score_opus":0.42588741391414275,"score_gpt":0.6267026890361848,"score_spread":0.200815275122042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290759784","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":[0.8491518,0.00028970305,0.14038762,0.000627252,0.0008399328,0.0013776943,0.00014589875,0.0000649147,0.007115173],"genre_scores_gemma":[0.7897479,0.00020732959,0.18036968,0.000049173053,0.00025767635,0.0011629537,0.000013716828,0.000059013204,0.028132573],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976489,0.0010633699,0.00024674964,0.0003437678,0.00027709937,0.00042014272],"domain_scores_gemma":[0.9978992,0.0012210396,0.000061757215,0.00031240773,0.0003560419,0.00014955737],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048356773,0.00009479003,0.00018794653,0.00022320065,0.00009635897,0.000016773974,0.00017392455,0.00014969124,0.0010503519],"category_scores_gemma":[0.0007079476,0.00006485917,0.00007147763,0.00020174672,0.0003494352,0.000084380204,0.00007886607,0.00018390524,0.000044828612],"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":[0.000114616276,0.00023504462,0.0080250725,0.00003217818,0.000013542628,0.000005616427,0.00045587664,4.63181e-9,0.12398506,0.002341881,0.0017084219,0.8630827],"study_design_scores_gemma":[0.0075203897,0.003506569,0.62836134,0.00039324016,0.0001430417,0.0001496976,0.0028489858,0.000009175431,0.281437,0.021192726,0.053795185,0.0006426527],"about_ca_topic_score_codex":0.000056016797,"about_ca_topic_score_gemma":0.000014282652,"teacher_disagreement_score":0.86244005,"about_ca_system_score_codex":0.000028507568,"about_ca_system_score_gemma":0.000042199405,"threshold_uncertainty_score":0.99986285},"labels":[],"label_agreement":null},{"id":"W2331470947","doi":"10.3758/bf03192768","title":"Word frequency effects in high-dimensional co-occurrence models: A new approach","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"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":"Word (group theory); Word lists by frequency; Computer science; Distributional semantics; Lexical decision task; Natural language processing; Orthographic projection; Hyperspace; Space (punctuation); Semantics (computer science); Artificial intelligence; Linguistics; Semantic similarity; Cognition; Psychology","score_opus":0.30327505621301126,"score_gpt":0.5142418890998628,"score_spread":0.21096683288685153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331470947","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":[0.078565896,0.0003934283,0.91820455,0.0001632772,0.00022181435,0.0007550533,0.0000055688274,0.00013012528,0.0015602672],"genre_scores_gemma":[0.11363433,0.0000048097113,0.8853924,0.000025479538,0.00010468829,0.00030085054,0.000017454564,0.000014764784,0.00050521566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937172,0.0025212625,0.00044661685,0.0010497292,0.0012823207,0.0009828551],"domain_scores_gemma":[0.9973173,0.00097174087,0.00006226815,0.0011993183,0.00017261371,0.00027674835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065716286,0.00022451002,0.0003395778,0.00065181253,0.00017683688,0.00022379031,0.0016889224,0.00016875913,0.000026776564],"category_scores_gemma":[0.0002860095,0.00021325573,0.000083883526,0.0013730554,0.00012692435,0.00067149976,0.0005721863,0.0010002783,0.000041733067],"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":[0.000018359031,0.00085649115,0.0053783148,0.0000831517,0.0000068194163,0.00028351185,0.0005388282,0.008016048,0.011648798,0.193157,0.002581303,0.77743137],"study_design_scores_gemma":[0.001862085,0.00014821209,0.024925794,0.00013866257,0.000011652512,0.000062538784,0.00002608271,0.67008585,0.0058125337,0.29575756,0.00041440682,0.00075463555],"about_ca_topic_score_codex":0.004528762,"about_ca_topic_score_gemma":0.000039319824,"teacher_disagreement_score":0.7766767,"about_ca_system_score_codex":0.0002456937,"about_ca_system_score_gemma":0.00057552283,"threshold_uncertainty_score":0.8696316},"labels":[],"label_agreement":null},{"id":"W2469509554","doi":"10.3758/s13428-016-0757-6","title":"Testing the accuracy of timing reports in visual timing tasks with a consumer-grade digital camera","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":1,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); CLIPS; Display size; Software; Computer vision; Artificial intelligence; Computer hardware; Real-time computing; Display device","score_opus":0.4994695931328663,"score_gpt":0.5752938594666791,"score_spread":0.07582426633381278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469509554","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":[0.9963131,0.00001089722,0.0013544795,0.00031692532,0.0001020218,0.0005567324,0.00001376048,0.000043846896,0.0012882206],"genre_scores_gemma":[0.9920733,0.0000070417036,0.007164212,0.000024050001,0.000034727,0.00016183159,6.228063e-7,0.00003046435,0.0005037735],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99644107,0.0012923328,0.0004770208,0.0005057071,0.0006993971,0.00058446],"domain_scores_gemma":[0.98233175,0.016566467,0.00022922367,0.00053797784,0.00021265536,0.000121915735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014137066,0.00014982471,0.00022829455,0.00033849335,0.0003003872,0.00015278072,0.00029465917,0.000060428436,0.00007939126],"category_scores_gemma":[0.025341349,0.000082278966,0.000061501196,0.0009453746,0.00058160094,0.0006121855,0.00018780414,0.0006125912,0.000013258993],"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":[0.000032523996,0.0001584558,0.023975288,0.00000629095,0.0000024642607,0.00041863773,0.0003440892,0.0000019211143,0.75024325,0.000017681612,0.000029199864,0.2247702],"study_design_scores_gemma":[0.00032959078,0.00026706234,0.023634491,0.00025639834,0.000015831838,0.0011287145,0.0010190437,0.00015870148,0.96923107,0.000088399305,0.0036752797,0.00019543996],"about_ca_topic_score_codex":0.00035848632,"about_ca_topic_score_gemma":0.000022707107,"teacher_disagreement_score":0.22457477,"about_ca_system_score_codex":0.00009788434,"about_ca_system_score_gemma":0.0002166326,"threshold_uncertainty_score":0.9828686},"labels":[],"label_agreement":null},{"id":"W2498664058","doi":"10.3758/s13428-016-0772-7","title":"One tamed at a time: A new approach for controlling continuous magnitudes in numerical comparison tasks","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":49,"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":"European Research Council; Israel Science Foundation; European Commission","keywords":"Numerosity adaptation effect; Numerical cognition; Convex hull; Cognition; Equating; Computer science; Mathematics; Algorithm; Regular polygon; Statistics; Psychology; Neuroscience; Geometry","score_opus":0.37783024330210274,"score_gpt":0.5580013170808487,"score_spread":0.18017107377874592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498664058","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":[0.123587824,0.000177506,0.8653806,0.00061304076,0.00004119956,0.004211173,0.00004064188,0.0001325853,0.005815427],"genre_scores_gemma":[0.08904269,0.000008920696,0.8979263,0.000029657771,0.00009252839,0.0012971015,0.000012442354,0.00006567429,0.011524725],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956614,0.0011982789,0.0007486875,0.0006085045,0.0008231012,0.00096002873],"domain_scores_gemma":[0.9861367,0.012661667,0.00012607702,0.0003743669,0.0003207693,0.00038044754],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006619849,0.0002514752,0.0009473064,0.00028318912,0.00017204821,0.00007851025,0.0004124529,0.00017689461,0.0010575606],"category_scores_gemma":[0.010652404,0.00018079957,0.00018058508,0.00041519752,0.00022551509,0.00011555504,0.00038688982,0.00035695801,0.00022198947],"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":[0.0012912131,0.0053640096,0.0044490593,0.00029739467,0.0001175898,0.00003887066,0.0011556601,2.562452e-7,0.16441463,0.005863616,0.008374299,0.8086334],"study_design_scores_gemma":[0.03589674,0.0025302814,0.026092997,0.002140492,0.00051328103,0.000076266435,0.0018182821,0.0033341853,0.3558703,0.55867773,0.010071439,0.0029779968],"about_ca_topic_score_codex":0.00004229333,"about_ca_topic_score_gemma":0.000011318333,"teacher_disagreement_score":0.8056554,"about_ca_system_score_codex":0.0003905256,"about_ca_system_score_gemma":0.00014605028,"threshold_uncertainty_score":0.99985564},"labels":[],"label_agreement":null},{"id":"W2509258559","doi":"10.3758/s13428-016-0802-5","title":"Validation of sleep-2-Peak: A smartphone application that can detect fatigue-related changes in reaction times during sleep deprivation","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sleep and Work-Related Fatigue","field":"Psychology","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Clinique Neuro-Outaouais; Cégep de l'Outaouais; Université du Québec en Outaouais","funders":"","keywords":"Sleep deprivation; Alertness; Psychomotor vigilance task; Wakefulness; Psychology; Context (archaeology); Audiology; Vigilance (psychology); Modafinil; Sleep (system call); Medicine; Electroencephalography; Computer science; Cognitive psychology; Cognition; Psychiatry","score_opus":0.16995006484946648,"score_gpt":0.4883889354198899,"score_spread":0.3184388705704234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509258559","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":[0.98600847,0.00020082858,0.01035776,0.00056285685,0.0003286383,0.001457678,0.000015381927,0.00013082633,0.0009375611],"genre_scores_gemma":[0.99292904,0.00008663335,0.0048371884,0.0000067435462,0.00006748912,0.0015715065,0.00005568953,0.00006508096,0.00038060572],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9944122,0.0029435446,0.0005990931,0.0007075334,0.00065559306,0.00068207574],"domain_scores_gemma":[0.9974234,0.0009668784,0.00031183852,0.00084976683,0.00030337513,0.00014475333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005075935,0.00023982697,0.0003480433,0.0012579558,0.00017832089,0.00002693719,0.0003568353,0.00049639633,0.0005305461],"category_scores_gemma":[0.0004756391,0.0002021643,0.000091638736,0.0016089788,0.00020657637,0.00021352859,0.00011106659,0.0006089104,0.0000823392],"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":[0.000140781,0.00016529713,0.059254054,0.000008213774,0.00003678968,0.000006959367,0.0009348758,0.000004571306,0.49687648,0.00019026015,0.000018440569,0.44236326],"study_design_scores_gemma":[0.0015324506,0.00013237027,0.4518065,0.00015631167,0.000043378703,0.000008051218,0.0003377721,0.000022548433,0.54542655,0.00026757203,0.00006144868,0.00020507866],"about_ca_topic_score_codex":0.001540898,"about_ca_topic_score_gemma":0.00034190988,"teacher_disagreement_score":0.4421582,"about_ca_system_score_codex":0.00039452853,"about_ca_system_score_gemma":0.000037833066,"threshold_uncertainty_score":0.8244021},"labels":[],"label_agreement":null},{"id":"W2522857466","doi":"10.3758/s13428-016-0811-4","title":"Test-based age-of-acquisition norms for 44 thousand English word meanings","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":151,"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":"Age of Acquisition; Word (group theory); Vocabulary; Test (biology); Word list; Psychology; Linguistics; Word recognition; Cognitive psychology; Computer science; Artificial intelligence; Cognition","score_opus":0.1987628173989918,"score_gpt":0.5479670901449614,"score_spread":0.34920427274596955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522857466","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":[0.8526614,0.00024769647,0.13505329,0.0004081256,0.0014288226,0.0021082228,0.00013474494,0.00022266753,0.0077350666],"genre_scores_gemma":[0.5207559,0.000010085513,0.45745304,0.00006815526,0.00038498142,0.0026145221,0.00005258357,0.00009631549,0.01856442],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99645156,0.0012505458,0.00047849477,0.0005416475,0.0005199859,0.00075777597],"domain_scores_gemma":[0.99291575,0.005448684,0.000117210846,0.00062458776,0.000689805,0.00020396529],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008806281,0.00018397336,0.0003351095,0.0004635684,0.0001780292,0.00006197498,0.00040448777,0.00018836242,0.0010752525],"category_scores_gemma":[0.0022207838,0.00012507821,0.0001493922,0.0004614771,0.0002732446,0.00012487556,0.00007546613,0.0002634828,0.000044964818],"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":[0.00035359515,0.00052483723,0.029904546,0.000051463245,0.000028634575,0.0000432634,0.0043894486,1.6398269e-7,0.16896416,0.0008952523,0.005315911,0.7895287],"study_design_scores_gemma":[0.0065017943,0.001981583,0.35259578,0.00061364076,0.00009718447,0.0000232668,0.0014421721,0.000015643443,0.25858486,0.0026514037,0.3746382,0.00085448165],"about_ca_topic_score_codex":0.00007307785,"about_ca_topic_score_gemma":0.0000031803647,"teacher_disagreement_score":0.78867424,"about_ca_system_score_codex":0.00013819014,"about_ca_system_score_gemma":0.00012653935,"threshold_uncertainty_score":0.9998379},"labels":[],"label_agreement":null},{"id":"W2539586339","doi":"10.3758/s13428-016-0823-0","title":"Performance of growth mixture models in the presence of time-varying covariates","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","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":"Université de Sherbrooke; Statistics Canada","funders":"","keywords":"Akaike information criterion; Bayesian information criterion; Statistics; Covariate; Deviance information criterion; Mathematics; Sample size determination; Contrast (vision); Model selection; Information Criteria; Bayesian probability; Entropy (arrow of time); Mixture model; Standard error; Econometrics; Bayesian inference; Computer science; Artificial intelligence","score_opus":0.0994531219014636,"score_gpt":0.43448942460041307,"score_spread":0.33503630269894946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539586339","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":[0.9793304,0.00037780765,0.018519575,0.00008079187,0.00003290651,0.0003453033,0.00001736697,0.0000023771668,0.0012934703],"genre_scores_gemma":[0.85503817,0.00012192344,0.14432256,0.000006696739,0.000034079316,0.00007289766,0.0000037119594,0.00000985524,0.00039009098],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99788713,0.001073596,0.00023256088,0.00022919079,0.00031187414,0.0002656601],"domain_scores_gemma":[0.9989028,0.00033981394,0.00005906044,0.000434201,0.00022557739,0.000038553862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029237797,0.00008886066,0.00014185967,0.00007255328,0.000044684795,0.000005473735,0.0005728688,0.000116027266,0.00003171485],"category_scores_gemma":[0.00038187683,0.000050944687,0.000050369003,0.0002060374,0.00032708465,0.000006707355,0.00016547553,0.00014019276,0.0000017587731],"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":[0.00011534285,0.00013208002,0.010264934,0.000039509898,0.000008687482,4.1130082e-7,0.00031214274,0.0000860906,0.9645556,0.0014853795,0.00014016974,0.022859612],"study_design_scores_gemma":[0.0005178959,0.00083480135,0.119373545,0.00008899499,0.000014201981,0.00000847988,0.00008842706,0.00016961874,0.8746067,0.0039785067,0.00019058758,0.00012823666],"about_ca_topic_score_codex":0.000044758068,"about_ca_topic_score_gemma":0.0000018614292,"teacher_disagreement_score":0.12580298,"about_ca_system_score_codex":0.000006268774,"about_ca_system_score_gemma":0.00009863448,"threshold_uncertainty_score":0.2077464},"labels":[],"label_agreement":null},{"id":"W2553430072","doi":"10.3758/s13428-016-0832-z","title":"Silex: A database for silent-letter endings in French words","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spelling; Consistency (knowledge bases); Computer science; Reading (process); Orthography; Set (abstract data type); Linguistics; Natural language processing; Artificial intelligence","score_opus":0.3212763358013591,"score_gpt":0.6067207794575348,"score_spread":0.28544444365617566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553430072","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":[0.9310856,0.00040865818,0.053966466,0.003045635,0.0018170268,0.0025027464,0.000231749,0.00017574517,0.0067663747],"genre_scores_gemma":[0.40017137,0.00003347915,0.5000442,0.00047774316,0.0007365177,0.011264035,0.00008943453,0.00014858453,0.087034605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99505,0.002031919,0.00048086018,0.0007680531,0.0004989218,0.001170216],"domain_scores_gemma":[0.99567384,0.0030568962,0.00006295068,0.00080945535,0.00016377625,0.00023307165],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011002835,0.00020072972,0.0002993922,0.00079440436,0.0001358276,0.000070531336,0.00055691524,0.00016623372,0.0024209674],"category_scores_gemma":[0.0010507171,0.00014098306,0.00010278672,0.00058212876,0.00018862009,0.00018097895,0.00020873119,0.0004664195,0.00031310544],"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":[0.00015441183,0.00050647405,0.056405634,0.000030503203,0.000025238596,0.00015912957,0.0048424914,2.3780677e-8,0.111939445,0.0015425092,0.10298778,0.72140634],"study_design_scores_gemma":[0.003265944,0.00033210867,0.23410872,0.00032542527,0.00002128999,0.000036210382,0.00058920914,0.0000063822104,0.024337731,0.0008960681,0.73554486,0.0005360683],"about_ca_topic_score_codex":0.000491539,"about_ca_topic_score_gemma":0.000024315108,"teacher_disagreement_score":0.7208703,"about_ca_system_score_codex":0.00024863545,"about_ca_system_score_gemma":0.000095028015,"threshold_uncertainty_score":0.9984909},"labels":[],"label_agreement":null},{"id":"W2554172262","doi":"10.3758/s13428-016-0829-7","title":"SyllabO+: A new tool to study sublexical phenomena in spoken Quebec French","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université Laval; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec - Santé; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Université Laval","keywords":"Phonotactics; Computer science; Syllable; Spoken language; Phonology; Psycholinguistics; Speech corpus; Phonetics; Linguistics; Natural language processing; Vocabulary; Artificial intelligence; Psychology; Speech recognition; Cognition; Speech synthesis","score_opus":0.2624615032136157,"score_gpt":0.5939136269055684,"score_spread":0.33145212369195265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554172262","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":[0.98563445,0.00021825824,0.0028838976,0.0009688828,0.0003576891,0.0019914615,0.0000064763894,0.00008056717,0.007858306],"genre_scores_gemma":[0.75296324,0.000009650619,0.07729866,0.00021379223,0.00044932228,0.0023928422,0.000008283372,0.00009968575,0.16656451],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99427676,0.0026826428,0.0004546904,0.0007733599,0.0007086194,0.0011039304],"domain_scores_gemma":[0.9978186,0.0007981119,0.000034517132,0.00079992675,0.0001368235,0.00041202124],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00659971,0.00021802599,0.00035164933,0.00072797906,0.000104582694,0.00008044284,0.0006959252,0.00015028362,0.01370614],"category_scores_gemma":[0.000904803,0.0001513323,0.00006436989,0.001367711,0.00010038768,0.0001277139,0.00036649048,0.00040706134,0.0013010558],"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":[0.00015981436,0.0011153615,0.19106534,0.000002563099,0.00002290527,0.00028612418,0.013874225,4.5472575e-8,0.00265604,0.000506421,0.0050959773,0.7852152],"study_design_scores_gemma":[0.0031304737,0.00044361962,0.96375394,0.000020869658,0.000012460417,0.000004706593,0.006482077,1.8482102e-7,0.00058919494,0.0005040466,0.024723215,0.0003352177],"about_ca_topic_score_codex":0.033988535,"about_ca_topic_score_gemma":0.012024323,"teacher_disagreement_score":0.78488,"about_ca_system_score_codex":0.00027782007,"about_ca_system_score_gemma":0.00038440854,"threshold_uncertainty_score":0.99947655},"labels":[],"label_agreement":null},{"id":"W2560525638","doi":"10.3758/s13428-016-0830-1","title":"Chronset: An automated tool for detecting speech onset","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital","funders":"","keywords":"Multitaper; Computer science; Speech recognition; Measure (data warehouse); Artificial intelligence; Natural language processing; Data mining","score_opus":0.2584792315470756,"score_gpt":0.5748492312116953,"score_spread":0.3163699996646197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560525638","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":[0.34244722,0.00006405921,0.65544236,0.0004413371,0.00018149886,0.0005476732,0.000010804213,0.00078778266,0.0000772892],"genre_scores_gemma":[0.11704633,0.0000051800585,0.88180196,0.000044115797,0.000116906,0.0003901138,0.000001926036,0.000031505835,0.00056198105],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99575055,0.0014421361,0.00032484587,0.0007607306,0.00065924914,0.0010625115],"domain_scores_gemma":[0.9963647,0.0017494538,0.00008242207,0.0010050348,0.00052587385,0.0002724918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011249194,0.00017951598,0.0002316605,0.00039132746,0.0006299706,0.00046918256,0.0014884601,0.00013519326,0.000054279997],"category_scores_gemma":[0.002583198,0.00012730737,0.000095183204,0.00086741813,0.00016531521,0.0009791908,0.00041633478,0.00027217847,0.000050357165],"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":[0.00001144013,0.000056590816,0.0006863081,0.000010627568,0.0000029246398,0.000022300597,0.00007749016,1.15193146e-7,0.3517207,0.00004275428,0.0002772113,0.6470915],"study_design_scores_gemma":[0.00060993095,0.00039576978,0.0073626623,0.00007162667,0.0000061286137,0.00010457389,0.000040391795,0.0023242773,0.9841607,0.0018280253,0.0028307603,0.00026512868],"about_ca_topic_score_codex":0.000030882562,"about_ca_topic_score_gemma":0.000012636352,"teacher_disagreement_score":0.6468264,"about_ca_system_score_codex":0.00019128398,"about_ca_system_score_gemma":0.0004011141,"threshold_uncertainty_score":0.51914436},"labels":[],"label_agreement":null},{"id":"W2562201257","doi":"10.3758/s13428-016-0845-7","title":"Q2Stress: A database for multiple cues to stress assignment in Italian","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","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":"Western University","funders":"","keywords":"Computer science; Stress (linguistics); Lexicon; Orthography; Phonology; Vowel; Natural language processing; Scripting language; Lexical database; Word (group theory); Consonant; Linguistics; Database; Reading (process); Artificial intelligence; Speech recognition","score_opus":0.38679342917853143,"score_gpt":0.623878790254951,"score_spread":0.23708536107641953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562201257","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":[0.86413443,0.00027381338,0.12491427,0.0019537164,0.0010846782,0.0040562544,0.0009863344,0.000112142116,0.0024843698],"genre_scores_gemma":[0.580419,0.000019057652,0.375359,0.0000840826,0.0002031843,0.011517638,0.000076744844,0.00008605988,0.032235224],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99537385,0.0019276642,0.00043813497,0.00073994097,0.00050547847,0.0010149129],"domain_scores_gemma":[0.9958932,0.0026901828,0.000046805064,0.0008190816,0.00018441648,0.00036631196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006701056,0.00018680225,0.0002763271,0.00062415766,0.00012724123,0.000073013085,0.0005303289,0.00011243483,0.00082621403],"category_scores_gemma":[0.0015336684,0.00013142583,0.00007303572,0.0004430873,0.000102241276,0.00013339802,0.00024272135,0.00024624667,0.00021771247],"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":[0.00034193278,0.00087079935,0.15514432,0.00003239644,0.000024800367,0.00010613228,0.0041786474,6.1256884e-7,0.061775416,0.00069396495,0.011679662,0.7651513],"study_design_scores_gemma":[0.0048643774,0.00085017784,0.45101246,0.0009175189,0.000023692572,0.000015249909,0.004781476,0.00001712236,0.12093444,0.00041678964,0.4153803,0.00078640145],"about_ca_topic_score_codex":0.0006616998,"about_ca_topic_score_gemma":0.0001801105,"teacher_disagreement_score":0.7643649,"about_ca_system_score_codex":0.00028634383,"about_ca_system_score_gemma":0.000087555825,"threshold_uncertainty_score":0.9046464},"labels":[],"label_agreement":null},{"id":"W2592069066","doi":"10.3758/s13428-018-1061-4","title":"Miami University deception detection database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Deception detection and forensic psychology","field":"Psychology","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":"University of Toronto","funders":"","keywords":"Deception; Psychology; Lie detection; Social psychology; Statement (logic); Computer science; Applied psychology; Linguistics","score_opus":0.3876640780767517,"score_gpt":0.6254059579783624,"score_spread":0.23774187990161072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592069066","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":[0.55765045,0.000051465435,0.36220554,0.00018947008,0.005047924,0.0006660186,0.000031391024,0.00034166503,0.073816076],"genre_scores_gemma":[0.89576554,0.000032744287,0.059283882,0.00013003964,0.00091351575,0.000084794774,0.000028376047,0.000053483098,0.043707628],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99417883,0.003985911,0.0002167961,0.00063724647,0.0003756134,0.0006055784],"domain_scores_gemma":[0.99804395,0.00027711914,0.00006655052,0.00085406814,0.0005017364,0.00025657835],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004747014,0.00013968973,0.00016649184,0.0008065766,0.00053059845,0.000035373556,0.00034507812,0.00026208378,0.016487278],"category_scores_gemma":[0.00021067966,0.0001493862,0.00009719122,0.0012895729,0.0009853838,0.00016815835,0.00014461899,0.00069626456,0.005265812],"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":[0.00038213658,0.00025569345,0.0007508474,0.0000024882133,0.000018323237,0.00004556933,0.00054075854,2.733761e-8,0.13206647,0.0012349247,0.009974659,0.8547281],"study_design_scores_gemma":[0.0016484377,0.0011882083,0.1779497,0.000010870035,0.00004006134,0.00024632865,0.0039003156,0.000056889963,0.025099112,0.00041759352,0.78911406,0.00032841752],"about_ca_topic_score_codex":0.00036851436,"about_ca_topic_score_gemma":0.00026248183,"teacher_disagreement_score":0.8543997,"about_ca_system_score_codex":0.00018504688,"about_ca_system_score_gemma":0.000037845868,"threshold_uncertainty_score":0.99550873},"labels":[],"label_agreement":null},{"id":"W2594456685","doi":"10.3758/s13428-017-0867-9","title":"The language and social background questionnaire: Assessing degree of bilingualism in a diverse population","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":415,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Aging; National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada","keywords":"Neuroscience of multilingualism; Psychology; Cognition; Population; Language proficiency; Developmental psychology; Cognitive psychology; Medicine; Mathematics education","score_opus":0.5036851353495614,"score_gpt":0.6149425197020493,"score_spread":0.11125738435248789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594456685","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":[0.99877995,0.00015217504,0.00004327668,0.00033905837,0.00018667297,0.00029370468,0.000005981274,0.000018622866,0.00018052779],"genre_scores_gemma":[0.99700034,0.00003345367,0.0026119454,0.000026831034,0.000093311035,0.000027601,0.000001664427,0.000012851153,0.000191993],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9957691,0.002922572,0.000253755,0.00035894773,0.0003331016,0.00036253498],"domain_scores_gemma":[0.9980206,0.0012446069,0.00016341134,0.0004480811,0.00007778858,0.000045513592],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00577977,0.00010061472,0.00017841808,0.00015220269,0.0015075427,0.00030168146,0.000517513,0.00011161174,0.000009105659],"category_scores_gemma":[0.0046082027,0.00007218356,0.000048371803,0.00014107017,0.0010457566,0.0002818226,0.00040357452,0.00048161967,0.0000019029454],"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":[0.000028400591,0.00006416985,0.022495782,0.000017962628,0.0000011677179,0.0003570671,0.002927343,6.891989e-8,0.67141926,0.00054945773,0.0000062327244,0.3021331],"study_design_scores_gemma":[0.00071413117,0.000096715514,0.8000749,0.00006758052,0.000016206664,0.00012149825,0.0058449646,0.00004556762,0.1912778,0.0013940228,0.00015573381,0.00019092615],"about_ca_topic_score_codex":0.0019526945,"about_ca_topic_score_gemma":0.0005047308,"teacher_disagreement_score":0.77757907,"about_ca_system_score_codex":0.000041874195,"about_ca_system_score_gemma":0.000058339734,"threshold_uncertainty_score":0.99979234},"labels":[],"label_agreement":null},{"id":"W2596404217","doi":"10.3758/s13428-017-0855-0","title":"Are multiple-trial experiments appropriate for eyewitness identification studies? Accuracy, choosing, and confidence across trials","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":49,"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":"Queen Margaret University","keywords":"Eyewitness identification; Psychology; Eyewitness memory; Identification (biology); Confidence interval; Social psychology; Cognitive psychology; Statistics; Computer science; Data mining; Mathematics","score_opus":0.8594029769708219,"score_gpt":0.7296825916912955,"score_spread":0.12972038527952645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596404217","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":[0.9878739,0.0008360209,0.0048418776,0.00031310585,0.0013994641,0.004586952,0.000072731775,0.000052089956,0.000023829638],"genre_scores_gemma":[0.98436797,0.000577667,0.009134348,0.000050898885,0.0003706384,0.004700232,0.000002282229,0.000036735506,0.00075925933],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9929919,0.0032230592,0.00090141036,0.0011526406,0.0009328977,0.00079806783],"domain_scores_gemma":[0.98792785,0.0082986485,0.0014438808,0.0012759607,0.00082158705,0.00023204053],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.027852636,0.00024595854,0.0007122666,0.00012479744,0.0042670243,0.0024118684,0.0013933842,0.00015195913,0.000027402328],"category_scores_gemma":[0.20796882,0.00019411286,0.00013240243,0.00016269402,0.0017672274,0.0012427979,0.0007290521,0.00037725043,0.000013854114],"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":[0.003306205,0.00020411995,0.0015051157,0.00016592178,0.000013548738,0.0000126589675,0.0015625948,6.873862e-7,0.9008106,0.00021731538,0.000118532924,0.09208271],"study_design_scores_gemma":[0.010098029,0.0002117072,0.010384702,0.00010474307,0.000030648473,0.000006202916,0.0029163712,0.00015222831,0.97174317,0.001919179,0.002175965,0.0002570409],"about_ca_topic_score_codex":0.00008869582,"about_ca_topic_score_gemma":0.000013658897,"teacher_disagreement_score":0.18011619,"about_ca_system_score_codex":0.00006759351,"about_ca_system_score_gemma":0.0001295113,"threshold_uncertainty_score":0.9986237},"labels":[],"label_agreement":null},{"id":"W2610034246","doi":"10.3758/s13428-017-0892-8","title":"The Montreal Protocol for Identification of Amusia","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; International Laboratory for Brain, Music and Sound Research","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Psychology; Neuropsychology; Identification (biology); Protocol (science); Montreal Protocol; Audiology; Neuroscience; Medicine; Cognition; Pathology","score_opus":0.6423844433893441,"score_gpt":0.6825533388179035,"score_spread":0.04016889542855939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610034246","genre_codex":"empirical","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5072849,0.000001848983,0.023981154,0.0017109362,0.001034065,0.4598303,0.00006472416,0.00010410451,0.0059879893],"genre_scores_gemma":[0.35137168,0.0000067736387,0.0039272993,0.000026782694,0.00012368405,0.6394982,5.012372e-7,0.00002122501,0.0050238967],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973956,0.00092770194,0.00028366488,0.00039472876,0.0006110231,0.00038729378],"domain_scores_gemma":[0.997497,0.0008641316,0.00021335189,0.0011243522,0.00022562634,0.00007549396],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0071693985,0.00007323813,0.00009917052,0.00009030335,0.0023506356,0.0004317335,0.0012562515,0.00004623166,0.000014931236],"category_scores_gemma":[0.008066367,0.000048699443,0.00007669351,0.00014977806,0.0010890953,0.00033530805,0.0002240476,0.00019206289,0.000010373719],"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":[0.000050579045,0.000071911374,0.00008115952,0.000009694094,1.64911e-7,0.0000010886204,0.000077427,2.0324757e-7,0.7516917,0.00074995204,0.0003540545,0.24691206],"study_design_scores_gemma":[0.00036711938,0.00015227114,0.13320284,0.000009127286,0.0000032467906,0.0000038375897,0.000055586497,0.00035145026,0.845435,0.002077945,0.01828335,0.00005818644],"about_ca_topic_score_codex":0.00010968433,"about_ca_topic_score_gemma":0.000028917857,"teacher_disagreement_score":0.24685387,"about_ca_system_score_codex":0.000031861466,"about_ca_system_score_gemma":0.00010266651,"threshold_uncertainty_score":0.99894816},"labels":[],"label_agreement":null},{"id":"W2618664687","doi":"10.3758/s13428-017-0898-2","title":"Scoring best-worst data in unbalanced many-item designs, with applications to crowdsourcing semantic judgments","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":44,"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":"Crowdsourcing; Computer science; Set (abstract data type); Rank (graph theory); Scaling; Artificial intelligence; Natural language processing; Scoring rule; Machine learning; Data mining; Quality (philosophy); Information retrieval; Mathematics","score_opus":0.8789947781800274,"score_gpt":0.7240679895118148,"score_spread":0.15492678866821252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618664687","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":[0.4419804,0.00008924911,0.5540556,0.00051186146,0.00020302158,0.0022848195,0.00004677537,0.000045038374,0.00078328454],"genre_scores_gemma":[0.49934736,0.000007675524,0.49822202,0.000029241737,0.00010695028,0.000751376,0.0000072675207,0.000049692004,0.0014784164],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9882504,0.0029529028,0.0011559421,0.0021091544,0.004317763,0.0012138538],"domain_scores_gemma":[0.98305917,0.005606873,0.0003934357,0.009432202,0.0009239921,0.00058434537],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04960864,0.0003118518,0.0006632626,0.0017330708,0.0016833033,0.0034818824,0.009576035,0.00014709668,0.00026340896],"category_scores_gemma":[0.022007708,0.00024551933,0.00006931555,0.0019927237,0.00032245688,0.0013392852,0.0053085475,0.0008767196,0.0005637828],"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":[0.00012520207,0.00026679705,0.30323756,0.000015768006,0.00000873786,0.00016140267,0.00043482214,0.00006846611,0.045598716,0.0001950904,0.00031525485,0.6495722],"study_design_scores_gemma":[0.0019572086,0.00026454843,0.947202,0.0008197446,0.000044834287,0.000049219907,0.0030275204,0.012019206,0.010854124,0.0027005295,0.020163031,0.0008980081],"about_ca_topic_score_codex":0.00058282336,"about_ca_topic_score_gemma":0.00049544196,"teacher_disagreement_score":0.6486742,"about_ca_system_score_codex":0.00025202744,"about_ca_system_score_gemma":0.00026257752,"threshold_uncertainty_score":0.9999997},"labels":[],"label_agreement":null},{"id":"W2622780478","doi":"10.3758/s13428-017-0899-1","title":"AGSuite: Software to conduct feature analysis of artificial grammar learning performance","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Natural language processing; Grammaticality; Grammar; Task (project management); Machine learning; String (physics); Levenshtein distance; Linguistics; Mathematics","score_opus":0.4500381688493872,"score_gpt":0.5853024771923007,"score_spread":0.13526430834291348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622780478","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":[0.45053437,0.000042096173,0.54850054,0.00031063447,0.0001627694,0.00023765113,0.0000022423499,0.000058269805,0.00015142444],"genre_scores_gemma":[0.31112772,0.000009320399,0.68695694,0.00001261769,0.000058764872,0.000072580275,0.0000030484875,0.000012049129,0.0017469955],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996268,0.0011312613,0.00030919688,0.0006569848,0.0009925074,0.0006420533],"domain_scores_gemma":[0.99646103,0.00044469378,0.00015948847,0.002070286,0.00061228225,0.00025220728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008269521,0.00015002787,0.00042370593,0.00087091385,0.0009669013,0.0005058974,0.002684097,0.00013415574,0.000050275685],"category_scores_gemma":[0.0030053796,0.00013831051,0.00018469545,0.0012885403,0.00017263491,0.00050173147,0.0013723323,0.0008613429,0.000015122272],"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":[0.000011250866,0.000051847026,0.04474884,0.000018506707,0.0000569014,0.000018462215,0.0007995289,0.0009911468,0.026981238,0.0009794148,0.000067006775,0.92527586],"study_design_scores_gemma":[0.00035481135,0.0005503892,0.6344246,0.00009563634,0.00032763625,0.000011215191,0.000308951,0.25388575,0.0972223,0.00044584935,0.011660451,0.000712356],"about_ca_topic_score_codex":0.00023479843,"about_ca_topic_score_gemma":0.00004570999,"teacher_disagreement_score":0.9245635,"about_ca_system_score_codex":0.00008099026,"about_ca_system_score_gemma":0.00015388161,"threshold_uncertainty_score":0.7436721},"labels":[],"label_agreement":null},{"id":"W2734609056","doi":"10.3758/s13428-017-0941-3","title":"Erratum to: The Montreal Protocol for Identification of Amusia","year":2017,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Nuclear and radioactivity studies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; International Laboratory for Brain, Music and Sound Research","funders":"","keywords":"Identification (biology); Montreal Protocol; Protocol (science); Psychology; Computer science; Audiology; Medicine; Geography; Biology; Meteorology","score_opus":0.27907645818314236,"score_gpt":0.5741072867000924,"score_spread":0.29503082851695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734609056","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000095375326,0.0005698375,0.02961752,0.0013120078,0.032504946,0.8218538,0.0010378909,0.0005383752,0.11247021],"genre_scores_gemma":[0.00015112694,0.000047579695,0.011848008,0.000004094767,0.0015987316,0.7864151,0.000039786526,0.00018349124,0.19971211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99733955,0.000566911,0.00043791175,0.00039083118,0.00068794435,0.00057685655],"domain_scores_gemma":[0.9974336,0.00040369545,0.00013381509,0.0014007522,0.0005110781,0.00011705486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005290383,0.00026966364,0.0005149052,0.00032456874,0.0005940332,0.00020102254,0.0011493487,0.0003709309,0.00002119981],"category_scores_gemma":[0.0011088643,0.00019469419,0.00023650182,0.0002364212,0.000245317,0.00010367678,0.00025323397,0.0013314044,0.00002038095],"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":[0.000032756237,0.00006288702,0.000008220073,0.0005164084,0.00006217186,0.000002384207,0.00041603277,0.00001835979,0.0036398207,0.000016177444,0.86758846,0.12763634],"study_design_scores_gemma":[0.00024908662,0.00013424165,0.0120148035,0.00015232555,0.00005951188,0.000002750563,0.00013395869,0.00075149414,0.0027675426,0.00017545391,0.983331,0.00022780681],"about_ca_topic_score_codex":0.0002423469,"about_ca_topic_score_gemma":0.0003131771,"teacher_disagreement_score":0.12740853,"about_ca_system_score_codex":0.00015892668,"about_ca_system_score_gemma":0.00013556943,"threshold_uncertainty_score":0.7939399},"labels":[],"label_agreement":null},{"id":"W2743598012","doi":"10.3758/s13428-017-0939-x","title":"Direct-location versus verbal report methods for measuring auditory distance perception in the far field","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","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":"McGill University; International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music; Douglas Mental Health University Institute","funders":"Agencia Nacional de Promoción Científica y Tecnológica; Universidad Nacional de Quilmes; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Perception; Stimulus (psychology); Sound localization; Auditory perception; Modality (human–computer interaction); Psychology; Computer science; Audiology; Set (abstract data type); Cognitive psychology; Artificial intelligence","score_opus":0.5455580172396415,"score_gpt":0.6340813677204105,"score_spread":0.08852335048076898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743598012","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":[0.68871903,0.000077098615,0.2985228,0.0017512625,0.002896512,0.0024473579,0.0000059376557,0.000072723145,0.005507277],"genre_scores_gemma":[0.8518837,0.00003314608,0.14591195,0.000023101435,0.0002906825,0.0012957214,0.0000022521242,0.000021407837,0.00053805386],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9932117,0.0046995883,0.00035246523,0.0006149504,0.00063847366,0.00048282737],"domain_scores_gemma":[0.9906525,0.007684902,0.00013902504,0.0011815312,0.00025966158,0.000082392165],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02407202,0.00012475134,0.0001889674,0.00015528241,0.0013508552,0.0003189073,0.0007617778,0.00013879903,0.000017758637],"category_scores_gemma":[0.04856958,0.000095137264,0.00010311328,0.00026667217,0.00032710223,0.0003600026,0.00013511139,0.0005319906,0.0000064846517],"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":[0.00014860912,0.000105982515,0.0009884131,0.00004107105,0.0000012260938,0.000013262402,0.0011814192,0.0000062454983,0.5636091,0.0003950486,0.00009992218,0.43340966],"study_design_scores_gemma":[0.0011418043,0.0006222038,0.8104923,0.00010150422,0.000026560498,0.000023226783,0.0013463809,0.0016063254,0.14579517,0.0010510569,0.037470475,0.00032301032],"about_ca_topic_score_codex":0.00042139532,"about_ca_topic_score_gemma":0.000050593797,"teacher_disagreement_score":0.80950385,"about_ca_system_score_codex":0.00024873187,"about_ca_system_score_gemma":0.00014343494,"threshold_uncertainty_score":0.9999493},"labels":[],"label_agreement":null},{"id":"W2747940070","doi":"10.3758/s13428-017-0963-x","title":"The cognitive reflection test is robust to multiple exposures","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":159,"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":"Test (biology); Computer science; Cognition; Reflection (computer programming); Psychology; Cognitive psychology; Artificial intelligence; Statistics; Mathematics; Geology; Programming language; Neuroscience","score_opus":0.7821180915133141,"score_gpt":0.736822124123797,"score_spread":0.04529596738951713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747940070","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":[0.5714381,0.00066458684,0.034763973,0.080714345,0.0023681822,0.017517913,0.0001731018,0.0010872103,0.29127258],"genre_scores_gemma":[0.891676,0.00035283895,0.074999794,0.00008365303,0.0005656469,0.0032775993,0.0000020776388,0.000057547877,0.028984852],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991716,0.003976754,0.00028501466,0.0005540193,0.0022000866,0.001268076],"domain_scores_gemma":[0.98643434,0.009926327,0.000104647595,0.0011641799,0.0018806959,0.00048982847],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03896362,0.00014269815,0.00018257256,0.00030018008,0.011938344,0.0018742742,0.0022915623,0.0002174209,0.00024773425],"category_scores_gemma":[0.07929762,0.00011261921,0.00010731357,0.00066218997,0.0022553024,0.00035976546,0.0008875641,0.0010691475,0.00021101792],"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":[0.00011348024,0.00024466502,0.12285252,0.0000069414277,0.000013005423,0.000049428916,0.006269635,2.824372e-7,0.018191604,0.0010439178,0.023135684,0.82807887],"study_design_scores_gemma":[0.0006315969,0.00069129374,0.37562233,0.00014207311,0.000026392887,0.000006634591,0.026903914,0.00006895861,0.11504271,0.0038722046,0.47648028,0.0005116041],"about_ca_topic_score_codex":0.014340238,"about_ca_topic_score_gemma":0.008990362,"teacher_disagreement_score":0.8275672,"about_ca_system_score_codex":0.00036537717,"about_ca_system_score_gemma":0.0005069834,"threshold_uncertainty_score":0.9991619},"labels":[],"label_agreement":null},{"id":"W2751852067","doi":"10.3758/s13428-020-01355-x","title":"Two-stage maximum likelihood approach for item-level missing data in regression","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"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; University of British Columbia Hospital","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Univariate; Regression; Scale (ratio); Regression analysis; Context (archaeology); Econometrics; Restricted maximum likelihood; Mathematics; Computer science; Maximum likelihood; Multivariate statistics","score_opus":0.9595380073134077,"score_gpt":0.7275446994992708,"score_spread":0.23199330781413685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751852067","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":[0.0265774,0.00096375664,0.9646374,0.0018696976,0.00032861572,0.0015846721,0.00023412808,0.00009380941,0.0037105056],"genre_scores_gemma":[0.012105732,0.00003096982,0.9864144,0.0001453905,0.00026207167,0.00021503629,0.00006127898,0.000048940667,0.00071619416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98094076,0.011098019,0.0013577897,0.002188683,0.0030497676,0.00136498],"domain_scores_gemma":[0.89657444,0.09796237,0.00042417462,0.0033491284,0.00087633147,0.0008135633],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12227027,0.00028806084,0.0007930764,0.0013690565,0.00048762115,0.00070967985,0.0051424666,0.00021956582,0.00026448545],"category_scores_gemma":[0.4432789,0.0002041742,0.00016073456,0.0073746247,0.0002646999,0.0006203628,0.0029645844,0.0012145751,0.00002447553],"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":[0.000119533775,0.0002203957,0.03142401,0.0000394466,0.000005145443,0.0000347684,0.0003449152,0.000008992409,0.01323352,0.000084538515,0.0043081045,0.95017666],"study_design_scores_gemma":[0.0113331815,0.001878168,0.27888548,0.00040578766,0.000104847444,0.000085127656,0.02860781,0.34655696,0.026232122,0.07311597,0.230161,0.002633531],"about_ca_topic_score_codex":0.00018530033,"about_ca_topic_score_gemma":0.0000063997713,"teacher_disagreement_score":0.9475431,"about_ca_system_score_codex":0.000094712304,"about_ca_system_score_gemma":0.00039566797,"threshold_uncertainty_score":0.9556068},"labels":[],"label_agreement":null},{"id":"W2756024538","doi":"10.3758/s13428-017-0962-y","title":"Norms for 10,491 Spanish words for five discrete emotions: Happiness, disgust, anger, fear, and sadness","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotions and Moral Behavior","field":"Psychology","cited_by":53,"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":"Comunidad de Madrid","keywords":"Sadness; Disgust; Anger; Happiness; Psychology; Emotion classification; Set (abstract data type); Social psychology; Cognitive psychology; Computer science","score_opus":0.4337136039477885,"score_gpt":0.6410584227082299,"score_spread":0.20734481876044136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756024538","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":[0.868027,0.0013223615,0.10416446,0.0035824662,0.0033326666,0.011020346,0.0021737718,0.00024661477,0.0061303633],"genre_scores_gemma":[0.29904702,0.00019821044,0.40297276,0.000069020796,0.0012627809,0.021434892,0.00044511765,0.00030916225,0.27426103],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99626416,0.00072840985,0.00045803486,0.00097848,0.00039953185,0.0011713909],"domain_scores_gemma":[0.9960051,0.0009077258,0.00019795504,0.0017210376,0.00077172293,0.00039643157],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0052069263,0.00032937306,0.00054105447,0.00032947303,0.0023276696,0.0005850217,0.0009297873,0.00034913194,0.00082396576],"category_scores_gemma":[0.0014839021,0.00028410144,0.00027565617,0.00022638244,0.00091731705,0.00041687288,0.00045072997,0.0005165246,0.000044659326],"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":[0.0007565492,0.0012946981,0.0348756,0.00023604502,0.00011196654,0.000062537794,0.0017822711,4.7593667e-7,0.008389951,0.017726867,0.039467104,0.8952959],"study_design_scores_gemma":[0.004156438,0.0012542952,0.85604256,0.00014101031,0.0002989305,0.000048674752,0.0030795643,0.00009238508,0.0011873513,0.0044393633,0.12850642,0.00075297337],"about_ca_topic_score_codex":0.0010747265,"about_ca_topic_score_gemma":0.00024166328,"teacher_disagreement_score":0.89454293,"about_ca_system_score_codex":0.00010056886,"about_ca_system_score_gemma":0.00011322808,"threshold_uncertainty_score":0.99996114},"labels":[],"label_agreement":null},{"id":"W2759584423","doi":"10.3758/s13428-018-1097-5","title":"Quaddles: A multidimensional 3-D object set with parametrically controlled and customizable features","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Object (grammar); Scripting language; Feature (linguistics); Set (abstract data type); Artificial intelligence; Task (project management); Computer vision; Feature vector; Human–computer interaction; Parametric statistics; Scratch; Pattern recognition (psychology); Programming language; Mathematics","score_opus":0.17297376419914134,"score_gpt":0.5344835669519601,"score_spread":0.36150980275281874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759584423","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":[0.3605458,0.0002582559,0.63566095,0.0004005097,0.0002828931,0.0013068494,0.000003905899,0.00023218649,0.0013086144],"genre_scores_gemma":[0.42108554,0.00001744045,0.57651526,0.0000828819,0.000070207876,0.00028239182,0.0000017200672,0.000015199452,0.0019293283],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99515444,0.0024509672,0.00025892557,0.00063441636,0.00094751973,0.0005537252],"domain_scores_gemma":[0.9973067,0.0010885173,0.000071228525,0.0005032673,0.00075451436,0.00027575367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006275194,0.00016746606,0.00033387262,0.00061520236,0.00058467634,0.00030024978,0.00043154802,0.00011630874,0.000060419934],"category_scores_gemma":[0.0009691496,0.00011404865,0.000075764576,0.0015924736,0.0004476648,0.0003240414,0.00031155333,0.0004768015,0.00004719925],"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":[0.002989055,0.0015933566,0.008877627,0.000057860718,0.00016308147,0.00024249316,0.0036820725,0.000016279651,0.15516229,0.02900608,0.0044736937,0.7937361],"study_design_scores_gemma":[0.052791383,0.024178866,0.5047525,0.00037673794,0.00025243164,0.0020181574,0.0032652882,0.16854924,0.19453248,0.006406779,0.039689034,0.003187072],"about_ca_topic_score_codex":0.00019734858,"about_ca_topic_score_gemma":0.00003724918,"teacher_disagreement_score":0.79054904,"about_ca_system_score_codex":0.000066081826,"about_ca_system_score_gemma":0.00016593392,"threshold_uncertainty_score":0.4650769},"labels":[],"label_agreement":null},{"id":"W2767253414","doi":"10.3758/s13428-017-0981-8","title":"MorphoLex: A derivational morphological database for 70,000 English words","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":92,"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; Centres Intégré Universitaires de Santé et de Services Sociaux","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Suffix; Computer science; Natural language processing; Lexicon; Word (group theory); Root (linguistics); Artificial intelligence; Lexical decision task; Noun; Linguistics; Cognition; Psychology","score_opus":0.4441928567752986,"score_gpt":0.6216715043181028,"score_spread":0.17747864754280424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767253414","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":[0.92239225,0.00027851126,0.04355606,0.0008999029,0.003061233,0.002282411,0.0005519212,0.00019777198,0.026779931],"genre_scores_gemma":[0.33219,0.000020906786,0.6294411,0.00016006759,0.0010185789,0.0060050334,0.00036028668,0.000081666825,0.030722383],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955681,0.0014653675,0.0004460692,0.0008396989,0.0006734388,0.0010073109],"domain_scores_gemma":[0.9953814,0.0017194336,0.00014845667,0.0017242271,0.0006901525,0.0003363026],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011390741,0.00022546924,0.00033648775,0.00031635843,0.0012257231,0.0004395732,0.0012939809,0.00023379624,0.0039181137],"category_scores_gemma":[0.00557165,0.00019573772,0.00014450551,0.00018972518,0.00053728366,0.00026842268,0.00048296005,0.00078053033,0.00013950648],"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":[0.0009786937,0.0019759198,0.091858104,0.000063775544,0.00014670393,0.00093995215,0.008393152,0.0000010141431,0.043845206,0.032546286,0.12868512,0.69056606],"study_design_scores_gemma":[0.0021750228,0.00032609666,0.47041723,0.00006643568,0.00003792096,0.00009410323,0.0010480033,0.000037997852,0.0061515463,0.0014783527,0.5176719,0.00049543387],"about_ca_topic_score_codex":0.00029072372,"about_ca_topic_score_gemma":0.0000040439795,"teacher_disagreement_score":0.6900706,"about_ca_system_score_codex":0.00012481963,"about_ca_system_score_gemma":0.0001389822,"threshold_uncertainty_score":0.99699247},"labels":[],"label_agreement":null},{"id":"W2772107854","doi":"10.3758/s13428-017-0983-6","title":"Trajectory analysis of discrete goal-directed pointing movements: How many trials are needed for reliable data?","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":15,"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":"Generalizability theory; Trajectory; Reliability (semiconductor); Clinical trial; Computer science; Movement (music); Statistics; Psychology; Physical medicine and rehabilitation; Mathematics; Medicine","score_opus":0.6192949276183322,"score_gpt":0.5981432500761731,"score_spread":0.021151677542159075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772107854","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":[0.83618546,0.00022064253,0.14994356,0.0022249266,0.00086736854,0.006474547,0.0028134247,0.00023910585,0.0010309968],"genre_scores_gemma":[0.81466645,0.00010559768,0.17491528,0.00009371509,0.00026358617,0.0012235949,0.00017448934,0.00006823072,0.008489049],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9929724,0.0038169166,0.0006577648,0.00087274716,0.0010478148,0.00063236314],"domain_scores_gemma":[0.9922472,0.004017403,0.0009060818,0.0021683055,0.00048813663,0.00017286347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024757093,0.00018861995,0.00093582744,0.0007322605,0.00093935913,0.0005079515,0.0016978121,0.0001232032,0.0000960591],"category_scores_gemma":[0.059807576,0.00015657849,0.00035187416,0.0007686442,0.00026945423,0.0007471734,0.00047189492,0.00034724205,0.0000019205615],"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":[0.00025472435,0.00013653163,0.0015360347,0.00004241684,0.00010767045,0.000008601255,0.00012603939,0.000016094902,0.9623838,0.00016110434,0.00033425263,0.034892734],"study_design_scores_gemma":[0.0047317566,0.0003814245,0.25395432,0.00014403227,0.001874933,0.000001317491,0.0020138128,0.12774412,0.5971699,0.0004054883,0.011002306,0.0005766327],"about_ca_topic_score_codex":0.0011823976,"about_ca_topic_score_gemma":0.00012648897,"teacher_disagreement_score":0.36521393,"about_ca_system_score_codex":0.000064238324,"about_ca_system_score_gemma":0.000104646395,"threshold_uncertainty_score":0.9481121},"labels":[],"label_agreement":null},{"id":"W2783136253","doi":"10.3758/s13428-017-1009-0","title":"When is best-worst best? A comparison of best-worst scaling, numeric estimation, and rating scales for collection of semantic norms","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Best practice; Scaling; Generalizability theory; Norm (philosophy); Valence (chemistry); Natural language processing; Psychology; Scale (ratio); Data collection; Cognitive psychology; Artificial intelligence; Statistics; Mathematics","score_opus":0.23785970297431935,"score_gpt":0.5684250069755211,"score_spread":0.33056530400120177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783136253","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":[0.87525827,0.0010508709,0.12062666,0.000097445394,0.00033948605,0.0015153483,0.000048784303,0.000029736126,0.0010333891],"genre_scores_gemma":[0.7830165,0.000030423318,0.21476658,0.000014972717,0.00016406186,0.00058056915,0.000034365,0.000046514455,0.0013460189],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960867,0.0014590358,0.00079473085,0.00053805375,0.00058392127,0.0005375674],"domain_scores_gemma":[0.99658704,0.001189173,0.0003463698,0.00047334033,0.0012488338,0.00015525107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004495426,0.00021701319,0.0005966943,0.0005953382,0.00047772392,0.000066044064,0.0002622123,0.00024264943,0.0005095207],"category_scores_gemma":[0.001075398,0.0001963801,0.00013822413,0.0009240015,0.00077192,0.00016314973,0.00010696332,0.0003526225,0.00003702644],"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":[0.0005960638,0.0022772343,0.062906854,0.00049254077,0.0001474923,0.0000048724323,0.038209748,0.0000021569697,0.06579365,0.00049889664,0.0020147508,0.82705575],"study_design_scores_gemma":[0.009844948,0.01729676,0.09090348,0.0020228305,0.0023319216,0.00017679825,0.09827704,0.034723803,0.7133011,0.02593514,0.003257258,0.0019289107],"about_ca_topic_score_codex":0.0024293517,"about_ca_topic_score_gemma":0.00027918056,"teacher_disagreement_score":0.8251268,"about_ca_system_score_codex":0.00006107766,"about_ca_system_score_gemma":0.00008653162,"threshold_uncertainty_score":0.80081487},"labels":[],"label_agreement":null},{"id":"W2785261305","doi":"10.3758/s13428-018-1016-9","title":"Reliability of the sliding scale for collecting affective responses to words","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Color perception and design","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; National Institutes of Health; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Reliability (semiconductor); Scale (ratio); Computer science; Psychology; Reliability engineering; Cognitive psychology; Applied psychology; Engineering","score_opus":0.4810218303105388,"score_gpt":0.6599140794620999,"score_spread":0.1788922491515611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785261305","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":[0.9544484,0.000013019513,0.035208456,0.00030297702,0.0007465668,0.0025603424,0.000023693743,0.000043046875,0.006653475],"genre_scores_gemma":[0.8754064,6.007995e-7,0.10790397,0.000053660835,0.00018005187,0.0015385406,4.497721e-7,0.00002640984,0.014889927],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.990524,0.0077773035,0.0002938013,0.00047560214,0.00039993797,0.0005293443],"domain_scores_gemma":[0.99211705,0.0059529883,0.00006357558,0.0008060952,0.00091566134,0.00014462371],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019884435,0.000111025416,0.00023609061,0.0003104049,0.0006185489,0.000036786903,0.0004453919,0.0001379563,0.0013380602],"category_scores_gemma":[0.008452976,0.00008247621,0.00016282313,0.0015065796,0.00039828557,0.000044449276,0.00024010119,0.00035541557,0.00005764101],"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":[0.004408304,0.0006580487,0.06206504,0.00003112096,0.000017543372,0.0000021757216,0.027914269,6.412455e-7,0.7012402,0.0006945721,0.01679766,0.18617043],"study_design_scores_gemma":[0.0006911883,0.0017483131,0.86277765,0.000043526554,0.000028550898,0.0000084626345,0.007890878,0.000030149233,0.10959265,0.0008205254,0.016203474,0.00016461448],"about_ca_topic_score_codex":0.00033398444,"about_ca_topic_score_gemma":0.00013475737,"teacher_disagreement_score":0.80071265,"about_ca_system_score_codex":0.0002174936,"about_ca_system_score_gemma":0.00016528956,"threshold_uncertainty_score":0.99989927},"labels":[],"label_agreement":null},{"id":"W2788006214","doi":"10.3758/s13428-018-1020-0","title":"Validating a visual version of the metronome response task","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":38,"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 Waterloo; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metronome; Mind-wandering; Task (project management); Modalities; Psychology; Modality (human–computer interaction); Context (archaeology); Cognitive psychology; Stimulus modality; Audiology; Rhythm; Computer science; Cognition; Neuroscience; Artificial intelligence; Medicine; Sensory system","score_opus":0.37594949032883684,"score_gpt":0.604832009901961,"score_spread":0.2288825195731241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788006214","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":[0.9957925,0.000009353906,0.0029568172,0.00013991653,0.00024205523,0.0002710092,0.000009148966,0.000022532822,0.00055663945],"genre_scores_gemma":[0.9873526,0.0000021348012,0.010858615,0.000016126427,0.00006776099,0.000036252546,4.777498e-7,0.0000139408385,0.0016520566],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.991686,0.0067513776,0.00020298861,0.00032352106,0.0006806012,0.0003555109],"domain_scores_gemma":[0.99780715,0.0014782341,0.000075741824,0.00041287902,0.00014873434,0.000077245044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010078155,0.00007724463,0.000116280935,0.0002153933,0.00049126195,0.00004998374,0.0004453568,0.000057209774,0.00028485333],"category_scores_gemma":[0.0064443857,0.000054128355,0.000090647234,0.000772594,0.00054875977,0.000098204575,0.00040626398,0.00032425407,0.000073664545],"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":[0.00018010619,0.00008462507,0.0011347511,0.000005490113,9.032185e-7,0.0000022698855,0.00022889134,2.7648758e-7,0.96571565,0.00006874495,0.000108840526,0.032469466],"study_design_scores_gemma":[0.00021523266,0.00031638285,0.03125355,0.000028521223,0.000007323192,0.00000609683,0.00022050463,0.00016743212,0.96431905,0.000092954266,0.003314142,0.000058800637],"about_ca_topic_score_codex":0.000046643454,"about_ca_topic_score_gemma":9.3328293e-7,"teacher_disagreement_score":0.032410666,"about_ca_system_score_codex":0.00007579096,"about_ca_system_score_gemma":0.00009727918,"threshold_uncertainty_score":0.77149975},"labels":[],"label_agreement":null},{"id":"W2788032477","doi":"10.3758/s13428-018-1024-9","title":"Methods for the effective study of collective behavior in a radial arm maze","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Army Research Office; Office of Naval Research; Fonds De La Recherche Scientifique - FNRS; National Science Foundation","keywords":"Categorization; Set (abstract data type); Context (archaeology); Radial arm maze; Computer science; Artificial intelligence; Cohesion (chemistry); Cognitive psychology; Psychology; Machine learning; Cognition; Neuroscience; Working memory","score_opus":0.352439896981346,"score_gpt":0.608060397139158,"score_spread":0.25562050015781207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788032477","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":[0.96340203,0.00003275104,0.024100251,0.00008661075,0.0008818465,0.011144959,0.00002707658,0.000033640972,0.00029085865],"genre_scores_gemma":[0.9379721,0.000009888329,0.049610317,0.000040689712,0.00018008518,0.011240619,0.000001063161,0.000052733725,0.00089246326],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9861509,0.01129816,0.00044306638,0.0008053492,0.00061783777,0.0006846547],"domain_scores_gemma":[0.98140043,0.017238429,0.00013194009,0.000632474,0.00047941567,0.00011732859],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014087548,0.00021263465,0.00040882963,0.0006081952,0.0005151893,0.00009098365,0.0006913674,0.00012212414,0.00007603486],"category_scores_gemma":[0.0087315375,0.00015010862,0.00015009496,0.0022990175,0.0007574549,0.00014093431,0.00033342856,0.0007316389,0.000005145047],"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":[0.000773078,0.0020478321,0.002638634,0.000009521189,0.000007858594,0.000013144746,0.0023016613,0.0000024481496,0.6185029,0.00025351116,0.000045006953,0.37340435],"study_design_scores_gemma":[0.0033796618,0.015369568,0.24976882,0.000020551624,0.00013398942,0.000026490032,0.002283631,0.005197729,0.7197526,0.0020301398,0.0017196179,0.00031719523],"about_ca_topic_score_codex":0.0005183994,"about_ca_topic_score_gemma":0.00023061551,"teacher_disagreement_score":0.37308717,"about_ca_system_score_codex":0.00029989998,"about_ca_system_score_gemma":0.00017636531,"threshold_uncertainty_score":0.99961835},"labels":[],"label_agreement":null},{"id":"W2788543801","doi":"10.3758/s13428-018-1015-x","title":"iTemplate: A template-based eye movement data analysis approach","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","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":"University of Toronto","funders":"Foundation for the National Institutes of Health","keywords":"Computer science; Eye movement; Consistency (knowledge bases); Eye tracking; Artificial intelligence; Software; Process (computing); Set (abstract data type); Data set; Data mining; Computer vision","score_opus":0.4956475261834326,"score_gpt":0.6034427315023565,"score_spread":0.10779520531892389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788543801","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":[0.025606014,0.000068708876,0.9714334,0.0005918435,0.0001839147,0.00041830825,0.000032078835,0.00041158882,0.0012541414],"genre_scores_gemma":[0.2519224,0.0000028543886,0.74726814,0.000068767135,0.000097479715,0.00017179048,0.000052398824,0.000016340193,0.00039983224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940512,0.0021200285,0.00039741737,0.001464784,0.0010222408,0.00094430626],"domain_scores_gemma":[0.99395275,0.0004992178,0.00010296451,0.004665268,0.00055072736,0.00022907052],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01301762,0.00022134712,0.00042843798,0.0015105132,0.0005482114,0.00034989303,0.0053991447,0.00019447168,0.00009468153],"category_scores_gemma":[0.0005386366,0.00019213953,0.00012764984,0.005505883,0.00067850645,0.00033668522,0.0023470132,0.00071271334,0.00009200901],"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":[0.00006298469,0.0024882269,0.09286949,0.000057188998,0.0006013591,0.0002204119,0.00044742232,0.000056238492,0.038465705,0.018268576,0.009764396,0.836698],"study_design_scores_gemma":[0.001683604,0.0013362814,0.35059342,0.00004600036,0.00055835216,0.000015609241,0.00029442142,0.5027153,0.085918345,0.004395461,0.051118735,0.001324453],"about_ca_topic_score_codex":0.00037989215,"about_ca_topic_score_gemma":0.000034784207,"teacher_disagreement_score":0.8353735,"about_ca_system_score_codex":0.00012103225,"about_ca_system_score_gemma":0.00022000833,"threshold_uncertainty_score":0.9999821},"labels":[],"label_agreement":null},{"id":"W2791802454","doi":"10.3758/s13428-018-1028-5","title":"Picture perfect: A stimulus set of 225 pairs of matched clipart and photographic images normed by Mechanical Turk and laboratory participants","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multisensory perception and integration","field":"Psychology","cited_by":26,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Normative; Artificial intelligence; Stimulus (psychology); Computer science; Set (abstract data type); Psychology; Modal; Computer vision; Pattern recognition (psychology); Cognitive psychology","score_opus":0.27826937664833906,"score_gpt":0.5845073464812839,"score_spread":0.3062379698329448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791802454","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":[0.9974398,0.00026461715,0.00095653115,0.000102658625,0.0001427367,0.000608927,0.0002185349,0.000029537998,0.0002366357],"genre_scores_gemma":[0.9868436,0.000100830475,0.012300986,0.000043118558,0.000057827907,0.00019368288,0.000016808242,0.00002609222,0.00041706258],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99491704,0.0033581378,0.0004349,0.00043952823,0.00039095661,0.00045942148],"domain_scores_gemma":[0.99809206,0.0005454422,0.000109311644,0.00042926223,0.00057142536,0.000252489],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044878777,0.00016594198,0.00039791275,0.000280353,0.00012029299,0.000025784806,0.00015404321,0.0002635846,0.002286372],"category_scores_gemma":[0.00061092025,0.00013742183,0.000060357423,0.00047021857,0.0011237272,0.00008732632,0.00009074193,0.00045436816,0.000012539468],"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":[0.00034110143,0.00024645514,0.02702445,0.000046923276,0.00003272982,0.000004565044,0.0046460256,2.704836e-8,0.94024026,0.0000890376,0.003913448,0.02341497],"study_design_scores_gemma":[0.0020940106,0.0020518834,0.5332113,0.000073057156,0.00011953684,0.000014552361,0.009581753,0.00026377858,0.44838607,0.00014225137,0.0037709337,0.0002909046],"about_ca_topic_score_codex":0.00042477454,"about_ca_topic_score_gemma":0.00008442303,"teacher_disagreement_score":0.5061868,"about_ca_system_score_codex":0.000020206173,"about_ca_system_score_gemma":0.000054049375,"threshold_uncertainty_score":0.9986257},"labels":[],"label_agreement":null},{"id":"W2805269870","doi":"10.3758/s13428-018-1058-z","title":"Procura-PALavras (P-PAL): A Web-based interface for a new European Portuguese lexical database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":42,"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; Lexical database; Word lists by frequency; Bigram; Unicode; Natural language processing; Pronunciation; Vowel; Syllable; Word (group theory); Speech recognition; Artificial intelligence; Sentence; Linguistics; Trigram; WordNet","score_opus":0.3698592726057386,"score_gpt":0.6163019402785802,"score_spread":0.24644266767284162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805269870","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":[0.40883815,0.0013263334,0.5278837,0.0025166026,0.003209912,0.0060049836,0.00026520414,0.00075321173,0.049201857],"genre_scores_gemma":[0.17565072,0.000010923796,0.747924,0.00030695435,0.0013745555,0.0014371772,0.0001691814,0.00020648085,0.07292002],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99233586,0.004135647,0.00061885343,0.0010285106,0.0006461823,0.001234946],"domain_scores_gemma":[0.9961202,0.001257663,0.00011139189,0.0012371022,0.0005682195,0.00070539716],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013374024,0.00030378622,0.00036609033,0.0005430723,0.00031739476,0.00015444556,0.0008992417,0.00014074204,0.0027350355],"category_scores_gemma":[0.0017005639,0.00026252813,0.00015827121,0.0007220465,0.00047848505,0.00014448723,0.0002940997,0.0007800123,0.0011362238],"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":[0.0010081952,0.0008825143,0.0036157821,0.00005974307,0.00005663519,0.00019922468,0.0038965708,1.8084543e-7,0.039630778,0.00097498426,0.15792058,0.79175484],"study_design_scores_gemma":[0.0034423925,0.0015798683,0.034456436,0.00021192268,0.00005644229,0.000068225716,0.00060342415,0.00021516164,0.024604658,0.00020364221,0.9339912,0.0005666532],"about_ca_topic_score_codex":0.00028957397,"about_ca_topic_score_gemma":0.00002786758,"teacher_disagreement_score":0.7911882,"about_ca_system_score_codex":0.00014112958,"about_ca_system_score_gemma":0.0005840928,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W2809193001","doi":"10.3758/s13428-018-1056-1","title":"The Massive Auditory Lexical Decision (MALD) database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":115,"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; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Killam Trusts; University of Alberta","keywords":"Lexical decision task; Computer science; Lexical database; Lexical access; Natural language processing; Set (abstract data type); Stimulus (psychology); Speech recognition; Artificial intelligence; Database; Psychology; Cognition; Cognitive psychology","score_opus":0.3306016750896725,"score_gpt":0.644614645825324,"score_spread":0.31401297073565154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809193001","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":[0.8070346,0.0015804595,0.09116922,0.0021605152,0.016505595,0.0021146543,0.000068071924,0.00027969162,0.07908719],"genre_scores_gemma":[0.23327348,0.0001482756,0.6481622,0.0002578027,0.005036814,0.002328651,0.000052356976,0.00014848111,0.11059194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99313277,0.004077114,0.00038860447,0.0005943849,0.0008853409,0.0009217682],"domain_scores_gemma":[0.992977,0.0049021314,0.000062834566,0.0012532317,0.00050110015,0.00030370237],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014450228,0.0001613584,0.00018529543,0.00023805906,0.0011080535,0.00018697778,0.0008460202,0.0001540013,0.0027928066],"category_scores_gemma":[0.0019450025,0.00010372632,0.00008548498,0.00055875734,0.00095212605,0.00010437604,0.00043889374,0.00088578253,0.0024084628],"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":[0.0002527057,0.00017716103,0.001671103,0.0000025459476,0.000021293707,0.00011431647,0.0015293307,2.9361814e-8,0.005595767,0.0041393875,0.16846639,0.81803],"study_design_scores_gemma":[0.00041319034,0.0002750557,0.10181633,0.00004023382,0.000012017048,0.000033205473,0.0010654187,0.000017731605,0.0035561477,0.0010693952,0.8915302,0.00017104603],"about_ca_topic_score_codex":0.0001423922,"about_ca_topic_score_gemma":0.000016031,"teacher_disagreement_score":0.81785893,"about_ca_system_score_codex":0.00013804322,"about_ca_system_score_gemma":0.00017029014,"threshold_uncertainty_score":0.99836826},"labels":[],"label_agreement":null},{"id":"W2810761248","doi":"10.3758/s13428-018-1073-0","title":"Are mind wandering rates an artifact of the probe-caught method? Using self-caught mind wandering in the classroom to test, and reject, this possibility","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":46,"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":"Mind-wandering; Artifact (error); Consistency (knowledge bases); Psychology; Reliability (semiconductor); Range (aeronautics); Test (biology); Cognitive psychology; Computer science; Artificial intelligence; Ecology; Engineering","score_opus":0.4103673811000614,"score_gpt":0.5647695724099545,"score_spread":0.15440219130989313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810761248","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":[0.9922175,0.000048687416,0.0055144364,0.00047636658,0.00012877399,0.001395611,0.000015979245,0.000021993339,0.00018069858],"genre_scores_gemma":[0.8619798,0.0000067190185,0.13735926,0.00004782282,0.00010619683,0.00010509625,6.006262e-7,0.000034702873,0.00035982826],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98997444,0.006671868,0.0005793296,0.0009967715,0.00095966185,0.00081791554],"domain_scores_gemma":[0.99591243,0.0023436707,0.00023294357,0.0010638565,0.00024470728,0.00020236324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014801491,0.00027352016,0.00038631243,0.00034702406,0.00086515787,0.00030982355,0.0008127299,0.0001612501,0.00011866533],"category_scores_gemma":[0.0049342797,0.0001722563,0.00010954361,0.0016067314,0.00046623897,0.0003430876,0.00051571464,0.0008738102,0.0000062852446],"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":[0.0000737636,0.0004427626,0.03159385,0.000055491648,0.0000038368207,0.0000199262,0.004545154,0.0000077866525,0.9285956,0.0000112249945,0.000016047083,0.034634545],"study_design_scores_gemma":[0.00035753992,0.00033124615,0.12161264,0.00017312697,0.000034729557,0.000080460995,0.002151532,0.0036241957,0.87052476,0.00035223566,0.0005254714,0.00023202745],"about_ca_topic_score_codex":0.00019619931,"about_ca_topic_score_gemma":0.00057327474,"teacher_disagreement_score":0.13184483,"about_ca_system_score_codex":0.00014445325,"about_ca_system_score_gemma":0.00015560167,"threshold_uncertainty_score":0.7024408},"labels":[],"label_agreement":null},{"id":"W2811114800","doi":"10.3758/s13428-018-1072-1","title":"Getting a grip on sensorimotor effects in lexical–semantic processing","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Semantic memory; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognition; Neuroscience","score_opus":0.22385796623857343,"score_gpt":0.5820056502941934,"score_spread":0.3581476840556199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811114800","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":[0.96989733,0.00036741555,0.006720246,0.00012768399,0.00063890766,0.001131384,0.000003010019,0.00011542478,0.020998621],"genre_scores_gemma":[0.95775664,0.0000041283447,0.037810545,0.00017785873,0.00081474165,0.00079961313,0.0000066446396,0.00006398,0.0025658312],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9920156,0.0053475047,0.00034601716,0.00068161794,0.0006321854,0.0009770837],"domain_scores_gemma":[0.9976071,0.0013349477,0.00007126667,0.00051464024,0.000283656,0.00018839218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007905429,0.00020041385,0.00031758068,0.0006542174,0.00029419822,0.000105413135,0.00030811527,0.00023989636,0.0006670619],"category_scores_gemma":[0.0015925353,0.00017081815,0.00009247045,0.0010079009,0.00034696475,0.00010338281,0.00009787293,0.0009850115,0.0006588102],"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":[0.000247843,0.00070704205,0.004934734,0.00010621133,0.000013380717,0.00048750007,0.0045655267,5.0289174e-8,0.08694325,0.0011704194,0.00031136995,0.9005127],"study_design_scores_gemma":[0.004422841,0.0036333217,0.80253583,0.00101404,0.00014105605,0.00015653367,0.006543929,0.0003240491,0.16662017,0.008242604,0.005297642,0.0010679614],"about_ca_topic_score_codex":0.00040550932,"about_ca_topic_score_gemma":0.000038859973,"teacher_disagreement_score":0.8994447,"about_ca_system_score_codex":0.00011643973,"about_ca_system_score_gemma":0.00007534457,"threshold_uncertainty_score":0.84678924},"labels":[],"label_agreement":null},{"id":"W2883349086","doi":"10.3758/s13428-018-1071-2","title":"Historical evolution of concrete and abstract language revisited","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Concreteness; Semantics (computer science); Cognition; Word (group theory); Computer science; Cognitive psychology; Linguistics; Psychology; Philosophy","score_opus":0.21497517597533058,"score_gpt":0.5804888822575975,"score_spread":0.365513706282267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883349086","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":[0.98087776,0.0037326058,0.0005984661,0.00024969192,0.00013297604,0.00037087974,0.0000043625278,0.000048697628,0.013984546],"genre_scores_gemma":[0.97970736,0.00008605062,0.015779365,0.0000064144606,0.00039371816,0.000025327161,0.0000020967157,0.0000070027613,0.0039926465],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9974318,0.0013465745,0.00017894023,0.00019184401,0.0005384494,0.0003123734],"domain_scores_gemma":[0.9989105,0.00026616832,0.000057330628,0.00016651598,0.00045669204,0.00014281606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061897133,0.000058320715,0.00014528728,0.000117298565,0.00040118533,0.000031410287,0.0001652237,0.00011844406,0.00048064181],"category_scores_gemma":[0.0018558259,0.000047847625,0.00004483555,0.0005095234,0.0006182412,0.00016582338,0.00006267392,0.00021532548,0.000016187869],"study_design_candidate":"bench_or_experimental","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":[0.00006568447,0.000037900027,0.009706965,0.00003729628,0.000010799097,0.000023692144,0.03388374,9.86544e-9,0.67233163,0.011587121,0.004632195,0.26768297],"study_design_scores_gemma":[0.0012252241,0.0010794522,0.5543813,0.00021329326,0.00012213853,0.000018833274,0.07778627,0.000031076637,0.052644216,0.0022308312,0.30958188,0.0006854746],"about_ca_topic_score_codex":0.017062688,"about_ca_topic_score_gemma":0.00028744814,"teacher_disagreement_score":0.6196874,"about_ca_system_score_codex":0.0005759415,"about_ca_system_score_gemma":0.00012283542,"threshold_uncertainty_score":0.98948276},"labels":[],"label_agreement":null},{"id":"W2885774321","doi":"10.3758/s13428-018-1083-y","title":"Argus: An open-source and flexible software application for automated quantification of behavior during social interaction in adult zebrafish","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Celiac Association; Université de Montréal; Dairy Farmers of Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Argus; Computer science; Software; Graphical user interface; Zebrafish; Human–computer interaction; Coding (social sciences); Artificial intelligence; Programming language; Biology; Statistics","score_opus":0.15138408359917835,"score_gpt":0.5581043177640113,"score_spread":0.40672023416483294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885774321","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":[0.9150699,0.0000249408,0.081917554,0.00016762652,0.000031462903,0.0026047807,0.000074268806,0.0000666053,0.00004287961],"genre_scores_gemma":[0.9110499,0.000027993663,0.08213622,0.00001865096,0.00017250559,0.0058207666,0.00053013855,0.000051006366,0.00019280791],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99729824,0.0007490181,0.00042780855,0.0006839573,0.00038011972,0.00046083907],"domain_scores_gemma":[0.99791163,0.00014432306,0.00013655267,0.0005457517,0.0010683,0.00019344463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032160624,0.00013820824,0.00020794763,0.00030457627,0.0003575278,0.00010689583,0.0006490888,0.00026301554,0.000019965884],"category_scores_gemma":[0.0015151689,0.00014711206,0.000043314034,0.00060869695,0.00058264815,0.000044405457,0.00046617212,0.0002567858,0.000004536936],"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":[0.00027673302,0.0005502281,0.0034693114,0.00004753748,0.000007643886,3.2940133e-7,0.00010956111,5.8920807e-7,0.8871185,0.00013139282,0.00024982207,0.10803833],"study_design_scores_gemma":[0.0010639164,0.0007388565,0.17274985,0.000024399591,0.000017701544,0.000007107792,0.00041996682,0.0010440012,0.81950957,0.00011985082,0.0041251574,0.00017965697],"about_ca_topic_score_codex":0.00044820094,"about_ca_topic_score_gemma":0.0002933939,"teacher_disagreement_score":0.16928054,"about_ca_system_score_codex":0.0000855444,"about_ca_system_score_gemma":0.00018145109,"threshold_uncertainty_score":0.5999056},"labels":[],"label_agreement":null},{"id":"W2887699552","doi":"10.3758/s13428-018-1089-5","title":"Probability of bivariate superiority: A non-parametric common-language statistic for detecting bivariate relationships","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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; University of Manitoba","funders":"","keywords":"Bivariate analysis; Copula (linguistics); Bivariate data; Nonparametric statistics; Statistic; Statistics; Parametric statistics; Estimator; Mathematics; Parametric model; Monte Carlo method; Correlation; Joint probability distribution; Econometrics; Computer science","score_opus":0.6911867135990772,"score_gpt":0.6567988206342216,"score_spread":0.03438789296485567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887699552","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":[0.23742928,0.000036949834,0.7595561,0.000026203616,0.00015082996,0.0022553147,0.0002457791,0.00006457801,0.00023496909],"genre_scores_gemma":[0.3102727,0.0000033689548,0.6887359,0.0000034966345,0.00008492386,0.0006913837,0.0000075527473,0.000057592824,0.0001430664],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99087566,0.005679673,0.0010540251,0.00071364193,0.0007424853,0.0009345285],"domain_scores_gemma":[0.9599078,0.037153564,0.0002722487,0.0010469785,0.0013122815,0.00030708042],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.028666375,0.00027637457,0.00080411293,0.0005929536,0.0007066046,0.00007591285,0.00048118638,0.00023570092,0.0001016042],"category_scores_gemma":[0.08016945,0.00024905393,0.00016142213,0.0016681137,0.0007486068,0.00017722764,0.00030589628,0.0009892307,0.000007251093],"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":[0.00071311876,0.001459459,0.004119166,0.0015505423,0.00011144793,0.00003108436,0.006857365,0.000010892592,0.11176465,0.26591244,0.000088516346,0.6073813],"study_design_scores_gemma":[0.00097550894,0.0010829902,0.008005813,0.000112459296,0.00016138346,0.000011361118,0.00082372566,0.014813857,0.028193433,0.9453567,0.000119197466,0.00034356717],"about_ca_topic_score_codex":0.00034691353,"about_ca_topic_score_gemma":0.00008808994,"teacher_disagreement_score":0.67944425,"about_ca_system_score_codex":0.00019934944,"about_ca_system_score_gemma":0.00023118731,"threshold_uncertainty_score":0.9999962},"labels":[],"label_agreement":null},{"id":"W2888587255","doi":"10.3758/s13428-018-1106-8","title":"Norms of conceptual familiarity for 3,596 French nouns and their contribution in lexical decision","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","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":"Université Laval; Institut Universitaire en Santé Mentale de Québec; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noun; Linguistics; Lexical decision task; Psychology; Cognitive psychology; Natural language processing; Computer science; Cognition; Philosophy","score_opus":0.24013816053285314,"score_gpt":0.5999140805722225,"score_spread":0.35977592003936937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888587255","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":[0.8332915,0.0002461936,0.16490759,0.000032987737,0.00027886828,0.00078326685,0.00009631766,0.000018116496,0.00034516933],"genre_scores_gemma":[0.9850941,0.000036840214,0.013853043,0.000016267753,0.00021621733,0.00026495347,0.000081726495,0.00001662519,0.0004202802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973468,0.0011759851,0.00038591304,0.00040024868,0.00025125963,0.00043976106],"domain_scores_gemma":[0.9972954,0.0014692218,0.000058066606,0.00036110295,0.000697384,0.00011886671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057921577,0.000122059246,0.00028713606,0.0002786843,0.00017495638,0.000024150766,0.00019846974,0.0002677521,0.0008977801],"category_scores_gemma":[0.001128275,0.000096719225,0.000068525165,0.00049916375,0.0012220377,0.00009163081,0.00007695267,0.0003046519,0.000014778852],"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":[0.0008259044,0.0012218634,0.307762,0.000027582471,0.000027307666,0.000007321213,0.044809043,3.1737682e-7,0.16632171,0.025849078,0.0016585235,0.45148936],"study_design_scores_gemma":[0.002333764,0.001100125,0.96500707,0.000024697403,0.000014678763,0.000012332524,0.011564548,0.00016288967,0.009155957,0.0053229905,0.0051299785,0.000170993],"about_ca_topic_score_codex":0.0019892545,"about_ca_topic_score_gemma":0.0011691847,"teacher_disagreement_score":0.65724504,"about_ca_system_score_codex":0.000079797865,"about_ca_system_score_gemma":0.000080690355,"threshold_uncertainty_score":0.9830063},"labels":[],"label_agreement":null},{"id":"W2889916852","doi":"10.3758/s13428-019-01293-3","title":"Survey-software implicit association tests: A methodological and empirical analysis","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":313,"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":"Psychology; Implicit-association test; Software; Applied psychology; Association (psychology); Empirical research; Data science; Computer science; Social psychology; Statistics","score_opus":0.679021047517433,"score_gpt":0.7112710266822435,"score_spread":0.03224997916481054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889916852","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":[0.98673934,0.0002058901,0.0058440277,0.0012249905,0.00035250618,0.00061816303,0.000026285277,0.00010411501,0.0048846807],"genre_scores_gemma":[0.82978135,0.00028810586,0.15203385,0.0004653932,0.00039798123,0.00036786168,0.00004390391,0.00003790715,0.016583666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9653525,0.03190354,0.000328435,0.00060678716,0.0009665944,0.0008421981],"domain_scores_gemma":[0.9810041,0.017597627,0.00011611988,0.00031699135,0.0006659335,0.0002992178],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05700442,0.00013287773,0.00054642133,0.0004447644,0.0005454669,0.00017399313,0.00044203788,0.00051237765,0.0018263909],"category_scores_gemma":[0.027686104,0.00011598949,0.00020539195,0.0030336413,0.0003864934,0.00015542039,0.00022110358,0.00077650533,0.00011510378],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002694307,0.00011127288,0.93854004,0.0000024224087,0.00009515036,0.0000035974713,0.0021667052,1.3074576e-7,0.0012003059,0.00037722313,0.0013328907,0.056143332],"study_design_scores_gemma":[0.00017935678,0.00015701941,0.97841424,0.0000026913021,0.00008505083,5.5068534e-7,0.001708975,0.000007355874,0.00003988471,0.0014588678,0.01780613,0.0001398806],"about_ca_topic_score_codex":0.008543738,"about_ca_topic_score_gemma":0.0032866725,"teacher_disagreement_score":0.15695801,"about_ca_system_score_codex":0.00048162634,"about_ca_system_score_gemma":0.0001581199,"threshold_uncertainty_score":0.9990861},"labels":[],"label_agreement":null},{"id":"W2891563639","doi":"10.3758/s13428-018-1118-4","title":"Conceptualizing syntactic categories as semantic categories: Unifying part-of-speech identification and semantics using co-occurrence vector averaging","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":31,"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; Artificial intelligence; Natural language processing; Simple (philosophy); Word (group theory); Replicate; Semantics (computer science); Identification (biology); Class (philosophy); Linguistics; Mathematics; Programming language; Statistics","score_opus":0.3004789857609664,"score_gpt":0.5616148356223938,"score_spread":0.2611358498614274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891563639","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":[0.98738885,0.00059913,0.009566789,0.00012433657,0.0009457604,0.0005682438,0.000022315899,0.000083811035,0.0007007653],"genre_scores_gemma":[0.984125,0.00006513262,0.014884005,0.000015693488,0.00025881876,0.00005668917,0.00003435605,0.00003962017,0.00052065356],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9951642,0.0021117884,0.00062589726,0.0007334347,0.0006228691,0.0007418068],"domain_scores_gemma":[0.9972318,0.0011367319,0.00026322078,0.00054219854,0.00063046045,0.00019560172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006135354,0.00024365238,0.0004072242,0.0004028352,0.0007857362,0.00022214728,0.0003412473,0.0001587796,0.00065692473],"category_scores_gemma":[0.0012908326,0.00024426798,0.00006342596,0.0007843095,0.0011433979,0.0002222359,0.00021293551,0.0006978997,0.000089399226],"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":[0.00031739761,0.0005405298,0.25489146,0.00062752987,0.00028445153,0.00031332663,0.10805832,0.000004696854,0.38313985,0.030772235,0.0006564519,0.22039373],"study_design_scores_gemma":[0.002420963,0.0015309921,0.3734679,0.0013335055,0.00056960067,0.0009911808,0.09264276,0.0016611533,0.4711146,0.0028276742,0.049115185,0.0023244862],"about_ca_topic_score_codex":0.0007404246,"about_ca_topic_score_gemma":0.000015024017,"teacher_disagreement_score":0.21806926,"about_ca_system_score_codex":0.00013640185,"about_ca_system_score_gemma":0.0002723835,"threshold_uncertainty_score":0.9960959},"labels":[],"label_agreement":null},{"id":"W2891614930","doi":"10.3758/s13428-018-1107-7","title":"A comparison of homonym meaning frequency estimates derived from movie and television subtitles, free association, and explicit ratings","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Ambiguity; Meaning (existential); Homonym (biology); Computer science; Consistency (knowledge bases); Context (archaeology); Categorization; Linguistics; Replicate; Interpretation (philosophy); Polysemy; Cognition; Natural language processing; Association (psychology); Cognitive psychology; Psychology; Artificial intelligence; Mathematics; Statistics","score_opus":0.2786611252142364,"score_gpt":0.5546806692884004,"score_spread":0.276019544074164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891614930","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":[0.99790806,0.0005491226,0.0005571718,0.00015443841,0.000083217856,0.00033488806,0.000039462786,0.00004562787,0.00032801184],"genre_scores_gemma":[0.88798386,0.00006964062,0.11167992,0.000056559365,0.000080126694,0.000031833606,0.0000045285806,0.000018628692,0.00007488052],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968819,0.0014723479,0.0003489034,0.0005213543,0.000402005,0.00037347246],"domain_scores_gemma":[0.9952172,0.0038678958,0.0001812438,0.00036903183,0.00025001002,0.00011462031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024480955,0.00013839631,0.00034275986,0.00016262764,0.0003601862,0.00008616158,0.00033543096,0.00014341624,0.00013095845],"category_scores_gemma":[0.012361186,0.00011773934,0.00003369326,0.00028821544,0.00047296425,0.00014332317,0.00039643212,0.00039918034,0.000005804266],"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":[0.000013688645,0.000064250446,0.080958694,0.000010569653,0.0000032172188,0.000029046645,0.0025272614,2.1331457e-8,0.8972157,0.00008494334,0.00013132005,0.018961243],"study_design_scores_gemma":[0.00034044628,0.00030685298,0.027177515,0.000045860175,0.000022315035,0.000015645068,0.00048469903,0.00012874484,0.9684905,0.0027620387,0.00010605476,0.000119369164],"about_ca_topic_score_codex":0.0008117399,"about_ca_topic_score_gemma":0.00009018161,"teacher_disagreement_score":0.11112275,"about_ca_system_score_codex":0.000040365,"about_ca_system_score_gemma":0.00005085902,"threshold_uncertainty_score":0.9959581},"labels":[],"label_agreement":null},{"id":"W2894255682","doi":"10.3758/s13428-018-1137-1","title":"Beyond subjective judgments: Predicting evaluations of creative writing from computational linguistic features","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":61,"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":"Imagination Institute","keywords":"Rubric; Creativity; Fluency; Readability; Psychology; Cohesion (chemistry); Writing assessment; Linguistics; Creativity technique; Context (archaeology); Creative writing; Cognitive psychology; Social psychology; Mathematics education","score_opus":0.32908617477775526,"score_gpt":0.6516848971259406,"score_spread":0.3225987223481853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894255682","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":[0.9365806,0.00012693615,0.017545277,0.00014371774,0.0011086225,0.0007314379,0.00019655356,0.000054085584,0.043512773],"genre_scores_gemma":[0.9056915,0.0000025376764,0.09184727,0.000046229656,0.00041990707,0.0002915617,0.000040404433,0.000020408028,0.0016401656],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99408174,0.0037383747,0.0003790376,0.0005430035,0.0008497217,0.00040813227],"domain_scores_gemma":[0.9916701,0.005922754,0.00016765641,0.0003895017,0.0017030858,0.00014692075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051747025,0.00013086942,0.00021761433,0.000402747,0.0005776829,0.000068778085,0.00034848702,0.0000927456,0.0024490217],"category_scores_gemma":[0.007726813,0.00013182267,0.000067434885,0.00095530367,0.0011546555,0.000097303055,0.00013870087,0.0005194798,0.000052515643],"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":[0.00040358098,0.00397931,0.41440213,0.000026293723,0.00016600438,0.000028868702,0.14760546,0.000035894387,0.14136429,0.023188177,0.00365358,0.2651464],"study_design_scores_gemma":[0.00045609512,0.00042954905,0.959783,0.000050897565,0.000048317037,0.000009314466,0.01087386,0.0003484113,0.0197033,0.007963671,0.00020458056,0.00012899896],"about_ca_topic_score_codex":0.0013885945,"about_ca_topic_score_gemma":0.000043274857,"teacher_disagreement_score":0.5453809,"about_ca_system_score_codex":0.00012733706,"about_ca_system_score_gemma":0.0002876642,"threshold_uncertainty_score":0.99846286},"labels":[],"label_agreement":null},{"id":"W2895796529","doi":"10.3758/s13428-018-1147-z","title":"The reliability of attentional biases for emotional images measured using a free-viewing eye-tracking paradigm","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","field":"Psychology","cited_by":76,"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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Attentional bias; Psychology; Cognitive psychology; Fixation (population genetics); Eye tracking; Anxiety; Reliability (semiconductor); Eye movement; Audiology; Cognition; Artificial intelligence; Computer science; Neuroscience","score_opus":0.5472372277828504,"score_gpt":0.6384359538892672,"score_spread":0.09119872610641677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895796529","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":[0.7613046,0.007073173,0.22461067,0.0005890056,0.0022687425,0.002561124,0.0004190889,0.00010497374,0.0010686028],"genre_scores_gemma":[0.76902044,0.000755786,0.22677091,0.000024200644,0.0010030011,0.0012957995,0.00004215284,0.000094701514,0.0009930292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99191576,0.004266269,0.000720912,0.0009212303,0.0012441666,0.0009316399],"domain_scores_gemma":[0.98602504,0.008698165,0.00032153734,0.0010865898,0.003670648,0.00019800644],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.016740073,0.00027681445,0.00040022418,0.00058106525,0.001413275,0.00014922417,0.00087876787,0.00020508576,0.00058474037],"category_scores_gemma":[0.02166639,0.00020778501,0.0003300954,0.0016082736,0.0017474636,0.00029046435,0.00029935912,0.0004933404,0.000023168548],"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":[0.0008395831,0.0020254254,0.33861756,0.000109306,0.00022917191,0.0000071850754,0.0011766674,0.000004143404,0.02677967,0.0011011133,0.0046453043,0.62446487],"study_design_scores_gemma":[0.002193922,0.0006788549,0.9156082,0.00030252838,0.00022562662,0.000029718522,0.001624494,0.00015054349,0.026601458,0.019819262,0.032361764,0.00040358774],"about_ca_topic_score_codex":0.00027840995,"about_ca_topic_score_gemma":0.000014382322,"teacher_disagreement_score":0.6240613,"about_ca_system_score_codex":0.00020210334,"about_ca_system_score_gemma":0.00025614153,"threshold_uncertainty_score":0.99988675},"labels":[],"label_agreement":null},{"id":"W2903145455","doi":"10.3758/s13428-018-1171-z","title":"Quantifying sensorimotor experience: Body–object interaction ratings for more than 9,000 English words","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":116,"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 Northern British Columbia; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexical decision task; Lexicon; Task (project management); Cognitive psychology; Psychology; Computer science; Referent; Semantics (computer science); Object (grammar); Age of Acquisition; Cognition; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.4921422929899069,"score_gpt":0.6493498938476473,"score_spread":0.15720760085774038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903145455","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":[0.8738052,0.0000346353,0.116617724,0.0002002704,0.004267353,0.0014984416,0.000020119405,0.00025672725,0.0032994752],"genre_scores_gemma":[0.9079846,0.000008339078,0.07960901,0.00011559346,0.0019101592,0.0020025377,0.000065938206,0.000080061975,0.008223768],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956235,0.0019673207,0.00050109584,0.0006628557,0.0005785706,0.00066664093],"domain_scores_gemma":[0.9962096,0.0010653369,0.00017368143,0.0006045785,0.0017609975,0.0001857598],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047427556,0.00020122205,0.0002556145,0.0004608757,0.00076333963,0.00020333882,0.0003254221,0.00026186925,0.0039479597],"category_scores_gemma":[0.0030943637,0.00019645288,0.00012763399,0.0009271725,0.00039243925,0.0004655226,0.000089966736,0.00055603596,0.00009995993],"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":[0.0011839315,0.0009981026,0.15408672,0.00008104901,0.00009344069,0.000020675296,0.1606106,0.000002766674,0.24936114,0.0043165693,0.02021143,0.40903357],"study_design_scores_gemma":[0.0027938809,0.0017328287,0.28388298,0.00012046326,0.00007116406,0.000043623917,0.12811975,0.0042194454,0.18279241,0.00015328356,0.39515248,0.0009176951],"about_ca_topic_score_codex":0.00034714374,"about_ca_topic_score_gemma":0.000034503566,"teacher_disagreement_score":0.40811586,"about_ca_system_score_codex":0.0002504784,"about_ca_system_score_gemma":0.00008728699,"threshold_uncertainty_score":0.99696255},"labels":[],"label_agreement":null},{"id":"W2909514154","doi":"10.3758/s13428-018-1184-7","title":"The spacing effect stands up to big data","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interval (graph theory); Computer science; Repetition (rhetorical device); Context (archaeology); Relevance (law); Statistics; Psychology; Information retrieval; Mathematics","score_opus":0.6473102502533267,"score_gpt":0.6323547153159895,"score_spread":0.014955534937337145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909514154","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":[0.98929274,0.00019744516,0.0019982762,0.00049075723,0.0015736329,0.0014217407,0.00003207648,0.00006426835,0.0049290434],"genre_scores_gemma":[0.9738574,0.00022038196,0.007366514,0.00026429395,0.00035442176,0.00036395015,0.000004132476,0.000058707206,0.01751019],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9934134,0.0034456144,0.00024554844,0.00085667305,0.0012176041,0.00082116376],"domain_scores_gemma":[0.99179524,0.0056437883,0.00004768263,0.002128722,0.00013459509,0.00024998223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018589634,0.00014545766,0.00020653434,0.00017067423,0.0007174901,0.0005149087,0.0024876317,0.00006160055,0.00017756394],"category_scores_gemma":[0.010807708,0.00008608554,0.00004243291,0.0011989402,0.0002302244,0.00031520872,0.0015158941,0.00061087933,0.00050710863],"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":[0.000070029906,0.000013586299,0.0021148436,0.00002753136,0.0000011833159,0.000009988616,0.00014898358,0.0000017078567,0.58884585,0.00024833265,0.00083934434,0.40767863],"study_design_scores_gemma":[0.00023906725,0.0005354355,0.0025084026,0.000038168386,0.000007092345,0.0000134251895,0.0003116012,0.00018175344,0.8165829,0.0001633648,0.17926365,0.00015509407],"about_ca_topic_score_codex":0.00008354679,"about_ca_topic_score_gemma":0.000013817046,"teacher_disagreement_score":0.40752354,"about_ca_system_score_codex":0.000050013987,"about_ca_system_score_gemma":0.00016859149,"threshold_uncertainty_score":0.9975247},"labels":[],"label_agreement":null},{"id":"W2912822799","doi":"10.3758/s13428-019-01197-2","title":"Development and validation of a high-speed video system for measuring saccadic eye movement","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Traumatic Brain Injury Research","field":"Medicine","cited_by":9,"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":"Computer science; Saccade; Computer vision; Reliability (semiconductor); Artificial intelligence; Video camera; Eye movement; Simulation; Physics","score_opus":0.43192333207829703,"score_gpt":0.5511577511445754,"score_spread":0.11923441906627841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912822799","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":[0.98927695,0.00013979319,0.0051051783,0.00018027502,0.00012999942,0.0045842933,0.000012383188,0.00007271631,0.0004983941],"genre_scores_gemma":[0.6255273,0.0000054684747,0.37260658,0.00000763715,0.000038010665,0.00061529386,0.000017715236,0.000040142626,0.0011418075],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995765,0.00094224565,0.0006430642,0.00048794592,0.0015373571,0.0006243922],"domain_scores_gemma":[0.99713844,0.001048485,0.00010832871,0.0005959277,0.0008192722,0.00028952007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016275143,0.00016542444,0.0005430238,0.00063276105,0.00014153874,0.000050507937,0.0002196323,0.00013490781,0.00011685802],"category_scores_gemma":[0.0008976082,0.00014327545,0.00007954281,0.00047280075,0.00012958737,0.00010412141,0.00020821713,0.00039031246,0.00002720343],"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":[0.0006952438,0.00033820258,0.029561669,0.0036214844,0.00013171279,0.000011982255,0.0014126129,0.0000026916537,0.7549062,0.001481423,0.000105411804,0.20773141],"study_design_scores_gemma":[0.0029807847,0.00057076267,0.12586997,0.00067333505,0.000060055885,0.000011404271,0.0018930167,0.00028284662,0.8662693,0.00008151491,0.0011553657,0.00015162138],"about_ca_topic_score_codex":0.00013205185,"about_ca_topic_score_gemma":0.0000029526327,"teacher_disagreement_score":0.3675014,"about_ca_system_score_codex":0.0005280632,"about_ca_system_score_gemma":0.00044744206,"threshold_uncertainty_score":0.58426034},"labels":[],"label_agreement":null},{"id":"W2913504998","doi":"10.3758/s13428-018-1155-z","title":"A thousand studies for the price of one: Accelerating psychological science with Pushkin","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":54,"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":"National Science Foundation","keywords":"Computer science; The Internet; Transformative learning; Software; Data science; World Wide Web; Mobile device; Range (aeronautics); Population; Computer security; Operating system","score_opus":0.9039247896964424,"score_gpt":0.749324593427155,"score_spread":0.15460019626928745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913504998","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":[0.9794797,0.00020317646,0.015200935,0.00068736257,0.00018836079,0.0020299212,0.000007917125,0.000023502675,0.0021791824],"genre_scores_gemma":[0.79748416,0.00003697139,0.19912985,0.00007865148,0.00004078879,0.00056884193,7.267164e-7,0.00001033906,0.0026496686],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99418294,0.00075113797,0.00059862656,0.0005290056,0.0033833901,0.0005548992],"domain_scores_gemma":[0.98852146,0.007720808,0.0002461892,0.00091378536,0.0024942441,0.00010353361],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046839148,0.00012666649,0.0003296045,0.0005820769,0.00071482494,0.0005166344,0.0020543828,0.00004178014,0.00029750977],"category_scores_gemma":[0.0047605843,0.000061409555,0.00009594246,0.0029438282,0.0012317593,0.00079973834,0.0005684833,0.00033143142,0.000049691964],"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":[0.00045981666,0.00051835494,0.07712918,0.000051400762,0.000046212357,0.0000038040673,0.005381875,0.00007519964,0.07402164,0.00936018,0.0027608832,0.83019143],"study_design_scores_gemma":[0.0016304943,0.0017720921,0.91839135,0.000082469654,0.00007371141,0.000011857055,0.0358331,0.0023730544,0.021753835,0.002472638,0.015243248,0.00036214248],"about_ca_topic_score_codex":0.000010935578,"about_ca_topic_score_gemma":0.000004936781,"teacher_disagreement_score":0.84126216,"about_ca_system_score_codex":0.00006096593,"about_ca_system_score_gemma":0.00012776749,"threshold_uncertainty_score":0.9814797},"labels":[],"label_agreement":null},{"id":"W2940968901","doi":"10.3758/s13428-019-01254-w","title":"Visual and auditory perceptual strength norms for 3,596 French nouns and their relationship with other psycholinguistic variables","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":30,"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 Laval; Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Perception; Noun; Cognitive psychology; Stimulus modality; Psychology; Modalities; Visual perception; Modality (human–computer interaction); Age of Acquisition; Semantics (computer science); Sensory system; Computer science; Cognition; Natural language processing; Artificial intelligence","score_opus":0.1524743936881985,"score_gpt":0.5181614210583495,"score_spread":0.365687027370151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940968901","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":[0.97486067,0.00051581,0.015675297,0.000034060922,0.00056026684,0.0011863207,0.00009741224,0.00005475595,0.007015402],"genre_scores_gemma":[0.9488987,0.000015695185,0.042415753,0.000047908612,0.0005619615,0.0006898629,0.000047711976,0.000068048575,0.0072543654],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969834,0.0013500768,0.00024350385,0.0006081123,0.00028602657,0.00052887003],"domain_scores_gemma":[0.9965288,0.002523545,0.00007035124,0.00039693818,0.00030149694,0.0001788805],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036669811,0.00020746423,0.00027991153,0.0002820919,0.0002770436,0.00010445045,0.00015827974,0.0002297163,0.0011488312],"category_scores_gemma":[0.00054264994,0.00014535924,0.0000509401,0.0002726214,0.0003281979,0.00009233442,0.000052624055,0.00056780706,0.000048255904],"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":[0.0013483588,0.0020950737,0.50788695,0.00031059823,0.00034722418,0.00003324373,0.050833505,0.0000010456517,0.02949878,0.018934445,0.0027451147,0.38596568],"study_design_scores_gemma":[0.004530896,0.0025448757,0.9294717,0.00012571891,0.00019884735,0.00010101248,0.03315539,0.00013681118,0.00054719095,0.006427128,0.022062654,0.00069782743],"about_ca_topic_score_codex":0.00042322004,"about_ca_topic_score_gemma":0.00008293767,"teacher_disagreement_score":0.42158473,"about_ca_system_score_codex":0.00003633414,"about_ca_system_score_gemma":0.00007449466,"threshold_uncertainty_score":0.99976426},"labels":[],"label_agreement":null},{"id":"W2955002705","doi":"10.3758/s13428-019-01282-6","title":"LADEC: The Large Database of English Compounds","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Bigram; Lexicon; Computer science; Natural language processing; Lexical database; Morpheme; Compound; WordNet; Parsing; Database; Artificial intelligence; Linguistics; Information retrieval; Trigram","score_opus":0.15682359605961013,"score_gpt":0.5424968809298324,"score_spread":0.38567328487022223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955002705","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":[0.06876929,0.0066889073,0.91403997,0.0006229797,0.0012184199,0.002062044,0.000056628443,0.0008692185,0.0056725414],"genre_scores_gemma":[0.16784365,0.000021475407,0.8312983,0.000051877047,0.00007156962,0.000090273235,0.0000063748444,0.000014758295,0.00060170505],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958351,0.0019838987,0.0002562639,0.0004250037,0.0009566222,0.000543091],"domain_scores_gemma":[0.99571264,0.0012741134,0.00008360219,0.0017534511,0.0010810078,0.000095197676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012233024,0.00012087922,0.00021062125,0.00025030167,0.00017189814,0.00019303703,0.0031246035,0.0000883022,0.00007786659],"category_scores_gemma":[0.001828557,0.00007927068,0.00007692231,0.0011969365,0.00017554036,0.0005433194,0.0018876246,0.00088468613,0.000022415528],"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":[0.000038603634,0.0007427862,0.010779438,0.00024136605,0.00002578068,0.00006240768,0.007028436,4.022865e-7,0.4152699,0.2771238,0.00985751,0.27882954],"study_design_scores_gemma":[0.0007788124,0.00038622782,0.0034282093,0.00021007229,0.000018577459,0.00002246152,0.00076824904,0.0020850596,0.88987696,0.012913849,0.08903513,0.00047640788],"about_ca_topic_score_codex":0.000090853966,"about_ca_topic_score_gemma":0.0000053994595,"teacher_disagreement_score":0.47460702,"about_ca_system_score_codex":0.00005240573,"about_ca_system_score_gemma":0.00015267915,"threshold_uncertainty_score":0.5806343},"labels":[],"label_agreement":null},{"id":"W2955707177","doi":"10.3758/s13428-019-01268-4","title":"The Semantic Librarian: A search engine built from vector-space models of semantics","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Text Analysis Techniques","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":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Computer science; Semantics (computer science); Space (punctuation); Cognition; Semantic space; Information retrieval; Cognitive science; Human–computer interaction; Artificial intelligence; World Wide Web; Data science; Psychology; Programming language","score_opus":0.1924456178434242,"score_gpt":0.5118749448262684,"score_spread":0.3194293269828442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955707177","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":[0.082346246,0.0007260222,0.91387194,0.0012601342,0.00012619182,0.00088301185,0.000005583328,0.00022415977,0.00055668585],"genre_scores_gemma":[0.41137132,0.00018503716,0.58729887,0.000009133648,0.000039182905,0.000090688074,0.0000031410361,0.000031631782,0.0009709609],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99345905,0.0027276853,0.00049924356,0.0007647766,0.0016579803,0.00089129194],"domain_scores_gemma":[0.99232394,0.0037674047,0.00012629303,0.0029141929,0.0006557446,0.00021240808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074089374,0.00023512814,0.00048738174,0.00046210745,0.00028188128,0.0003517965,0.0036563545,0.00016161405,0.000046628207],"category_scores_gemma":[0.0004218239,0.00017486562,0.00021364298,0.0021884567,0.0003188889,0.0009445429,0.0020560103,0.0010394123,0.000049446404],"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":[0.000057797704,0.00048566662,0.0045471564,0.000080122074,0.00015090076,0.00007376271,0.0021321329,0.0012433155,0.43087846,0.2161933,0.0006396927,0.34351766],"study_design_scores_gemma":[0.00041255343,0.00032987833,0.00545064,0.00009828412,0.000039034934,0.000008376853,0.00028724677,0.4345159,0.48899704,0.06659176,0.0028528043,0.00041647872],"about_ca_topic_score_codex":0.0005347918,"about_ca_topic_score_gemma":0.000021665046,"teacher_disagreement_score":0.4332726,"about_ca_system_score_codex":0.00010380582,"about_ca_system_score_gemma":0.00028255436,"threshold_uncertainty_score":0.7130813},"labels":[],"label_agreement":null},{"id":"W2960780327","doi":"10.3758/s13428-019-01270-w","title":"The role of number of items per trial in best–worst scaling experiments","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":15,"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":"Scaling; Latent semantic analysis; Set (abstract data type); Computer science; Dimension (graph theory); Value (mathematics); Statistics; Cognitive psychology; Natural language processing; Artificial intelligence; Psychology; Machine learning; Mathematics","score_opus":0.5703808539984128,"score_gpt":0.6897069463044384,"score_spread":0.11932609230602564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960780327","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":[0.9922188,0.00032544165,0.00009036763,0.000033737313,0.00070735347,0.00088931224,0.000011273288,0.0000068127033,0.005716931],"genre_scores_gemma":[0.9785376,0.000024621702,0.019793171,0.0000030892265,0.000053191292,0.00011967657,0.0000010175719,0.000023042263,0.001444542],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9919124,0.0031674656,0.0015179958,0.0005957253,0.0022517096,0.0005546602],"domain_scores_gemma":[0.98901427,0.008456059,0.00035314725,0.0013625058,0.0006749153,0.00013907981],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03751411,0.00015406874,0.00058677886,0.00049091125,0.00015970423,0.00022644667,0.0017416159,0.00017521753,0.0010447365],"category_scores_gemma":[0.0039971652,0.000098520504,0.00025697623,0.0010955716,0.00038354035,0.00025644386,0.00061150733,0.0005306545,0.00043795025],"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":[0.0019678383,0.00051742163,0.07867879,0.0000016787853,0.0000043709883,0.0000027743135,0.0007973807,0.000010987422,0.03218628,0.00039771316,0.000057289584,0.88537747],"study_design_scores_gemma":[0.0484401,0.003244326,0.07776773,0.00056231586,0.00010769662,0.000049764,0.106229365,0.0033589508,0.3913872,0.2590115,0.108180255,0.001660791],"about_ca_topic_score_codex":0.00045200664,"about_ca_topic_score_gemma":0.0000225137,"teacher_disagreement_score":0.8837167,"about_ca_system_score_codex":0.000099300145,"about_ca_system_score_gemma":0.00018240178,"threshold_uncertainty_score":0.99986845},"labels":[],"label_agreement":null},{"id":"W2963778838","doi":"10.3758/s13428-019-01277-3","title":"A computerized spatial orientation test","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":73,"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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Orientation (vector space); Task (project management); Artificial intelligence; Perspective (graphical); Computer vision; Human–computer interaction; Mathematics","score_opus":0.15379085207640492,"score_gpt":0.5222937646684322,"score_spread":0.36850291259202733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963778838","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":[0.7715548,0.000033337434,0.22259958,0.000030472827,0.00072319974,0.0008221222,0.0000142960025,0.00032318145,0.0038989754],"genre_scores_gemma":[0.92578316,0.0000139827425,0.0735307,0.000013074681,0.000097222735,0.00017802122,0.00007103095,0.000032336837,0.00028046005],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986186,0.00037104049,0.00017884118,0.0001768984,0.00038691983,0.00026770454],"domain_scores_gemma":[0.99900407,0.00048012723,0.00001527802,0.0002055033,0.00019719082,0.000097810786],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014444235,0.00008867868,0.00012482738,0.0002011029,0.00006553498,0.00006716049,0.00012367334,0.00007626256,0.00095520914],"category_scores_gemma":[0.0001743225,0.00009128217,0.000042629184,0.00042984716,0.000036069196,0.00012669174,0.000040230116,0.0003138974,0.00054690335],"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":[0.00001766267,0.000069006426,0.007753446,0.000035766352,0.0000051806046,0.0000064295823,0.00021914075,0.000057519104,0.52504444,0.00009092953,0.00026550013,0.466435],"study_design_scores_gemma":[0.0033013332,0.0006569059,0.31043693,0.00010852554,0.000032289543,0.000022188178,0.00034981527,0.12833282,0.5320194,0.00065682764,0.023439487,0.0006435311],"about_ca_topic_score_codex":0.00009540923,"about_ca_topic_score_gemma":0.000009430876,"teacher_disagreement_score":0.46579146,"about_ca_system_score_codex":0.00008552906,"about_ca_system_score_gemma":0.000024640309,"threshold_uncertainty_score":0.99995804},"labels":[],"label_agreement":null},{"id":"W2970802026","doi":"10.3758/s13428-019-01289-z","title":"The influence of place and time on lexical behavior: A distributional analysis","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Categorization, perception, and language","field":"Psychology","cited_by":23,"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; Artificial intelligence; Natural language processing; Lexical choice; Word (group theory); Language model; Experiential learning; Lexical density; Lexical item; Linguistics; Psychology","score_opus":0.1018397194881408,"score_gpt":0.5618026561742797,"score_spread":0.4599629366861389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970802026","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":[0.99731034,0.00012163372,0.0005135622,0.00008527752,0.000064899985,0.00050919486,0.000120047654,0.000022558386,0.0012525124],"genre_scores_gemma":[0.9892387,0.00002417936,0.0009064128,0.000011638824,0.000041532236,0.00021651138,0.00008272207,0.000013794297,0.009464545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964918,0.0018853537,0.00028850965,0.00037749636,0.00058215146,0.0003746967],"domain_scores_gemma":[0.9975235,0.0013799288,0.000067338144,0.0006087483,0.0002947988,0.00012571756],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0042545274,0.000114751005,0.00023198572,0.0002670499,0.00025228498,0.000055383134,0.00029229128,0.00013814663,0.0040329266],"category_scores_gemma":[0.00027405872,0.00008353811,0.00011787861,0.0010026781,0.0004555446,0.00006327385,0.00009406931,0.00039307072,0.00023026949],"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":[0.00061101234,0.001162906,0.7722135,0.000019018444,0.0002737743,0.00002704064,0.0038349417,0.00007463442,0.11000457,0.041276142,0.0010097966,0.06949266],"study_design_scores_gemma":[0.00029752424,0.00021308278,0.9958249,0.00000434309,0.00014175699,0.000008531357,0.00051283377,0.00004148712,0.00040692036,0.00009905176,0.002355036,0.00009455657],"about_ca_topic_score_codex":0.00044196862,"about_ca_topic_score_gemma":0.000030593783,"teacher_disagreement_score":0.22361137,"about_ca_system_score_codex":0.00007004396,"about_ca_system_score_gemma":0.000067524845,"threshold_uncertainty_score":0.99687755},"labels":[],"label_agreement":null},{"id":"W2972188906","doi":"10.3758/s13428-019-01288-0","title":"The Hoosier Vocal Emotions Corpus: A validated set of North American English pseudo-words for evaluating emotion processing","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Emotion and Mood Recognition","field":"Psychology","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":"Université de Montréal","funders":"","keywords":"Psychology; Sadness; Anger; Disgust; Stimulus (psychology); Set (abstract data type); Happiness; Cognitive psychology; Computer science; Social psychology","score_opus":0.3572854909454397,"score_gpt":0.6064557803683746,"score_spread":0.24917028942293484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972188906","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":[0.95889664,0.000051374976,0.03606536,0.00018119214,0.00084037404,0.002363268,0.00008269531,0.00009630188,0.0014228033],"genre_scores_gemma":[0.93330467,0.000023013725,0.062383287,0.000028608734,0.00026714115,0.0010075945,0.00018820653,0.000068121066,0.002729367],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9928499,0.004630737,0.0005676982,0.00052238716,0.00071156805,0.0007176961],"domain_scores_gemma":[0.99524075,0.0016628818,0.00031246166,0.0005617733,0.002061664,0.0001604687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010486772,0.00017950743,0.00032355267,0.00033024413,0.0005390346,0.00010921352,0.0003725549,0.00010741475,0.0002758356],"category_scores_gemma":[0.001986611,0.00014183836,0.0001752106,0.0013568244,0.00045372683,0.00014479666,0.00010145741,0.00065877807,0.00005178563],"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":[0.0001943174,0.00027867634,0.022362739,0.000057149384,0.000036338766,0.000001245531,0.003987916,0.0000058758083,0.007145695,0.00016548202,0.00045355308,0.965311],"study_design_scores_gemma":[0.002721453,0.002811097,0.96121466,0.0001645431,0.00020543218,0.000027492315,0.016767012,0.003384272,0.0057852054,0.00039424223,0.0060727294,0.00045187408],"about_ca_topic_score_codex":0.00015300106,"about_ca_topic_score_gemma":0.000089883775,"teacher_disagreement_score":0.9648591,"about_ca_system_score_codex":0.00010724592,"about_ca_system_score_gemma":0.00020627552,"threshold_uncertainty_score":0.5784001},"labels":[],"label_agreement":null},{"id":"W2986005510","doi":"10.3758/s13428-019-01297-z","title":"MorphoLex-FR: A derivational morphological database for 38,840 French words","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","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":"Dalhousie University; Université Laval","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Suffix; Lexicon; Prefix; Lexical database; Computer science; Natural language processing; Noun; Linguistics; Lexical decision task; Variable (mathematics); Artificial intelligence; Database; Psychology; Mathematics; WordNet; Cognition","score_opus":0.3431572925291088,"score_gpt":0.6009954129180568,"score_spread":0.257838120388948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986005510","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":[0.9494792,0.000294421,0.03489169,0.00049107865,0.0013089491,0.0021232152,0.0002196446,0.000120971825,0.01107081],"genre_scores_gemma":[0.2523395,0.000012285813,0.68571585,0.00021035649,0.00031177606,0.0042872946,0.0005919281,0.00007679597,0.0564542],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948002,0.001889649,0.0005201915,0.0009375628,0.00078922766,0.0010631722],"domain_scores_gemma":[0.99583936,0.0023441406,0.000088013185,0.0010290602,0.00040070916,0.00029871566],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009258565,0.0002451018,0.00037685438,0.00046997075,0.00024904122,0.00012630821,0.000714035,0.0002457028,0.0140389195],"category_scores_gemma":[0.0008553954,0.00020777342,0.00015832626,0.000674275,0.00021410431,0.00015496847,0.00030130087,0.00082623056,0.0011417613],"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":[0.0007052636,0.0026151508,0.14186454,0.00012807999,0.00018427672,0.0005087885,0.0062450175,0.0000053250674,0.26102138,0.021026418,0.11451621,0.45117953],"study_design_scores_gemma":[0.0032818918,0.0008298507,0.3959728,0.000100925135,0.000040419207,0.0002938969,0.0011224634,0.0001561098,0.009111283,0.0021429525,0.5861547,0.0007926903],"about_ca_topic_score_codex":0.0002543695,"about_ca_topic_score_gemma":0.0000024279188,"teacher_disagreement_score":0.6971397,"about_ca_system_score_codex":0.00015986642,"about_ca_system_score_gemma":0.00018836094,"threshold_uncertainty_score":0.999636},"labels":[],"label_agreement":null},{"id":"W2998136884","doi":"10.3758/s13428-019-01324-z","title":"Modeling list-strength and spacing effects using version 3 of the retrieving effectively from memory (REM.3) model and its superimposition-of-similar-images assumption","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mnemonic; Engram; Psychology; TRACE (psycholinguistics); Cognitive psychology; Arithmetic; Superimposition; Mathematics; Computer science; Artificial intelligence","score_opus":0.2974948444674319,"score_gpt":0.4911807530646138,"score_spread":0.19368590859718188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998136884","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":[0.9860904,0.0008401357,0.012246945,0.000076635544,0.000057008256,0.000584214,0.000044021665,0.000020057463,0.00004055176],"genre_scores_gemma":[0.97397196,0.00026459162,0.025653834,0.000035094665,0.000032116237,0.00001580329,9.672755e-7,0.000019684914,0.0000059701283],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963958,0.0018687453,0.00028198076,0.0005275521,0.00064879557,0.00027712816],"domain_scores_gemma":[0.997694,0.0016216601,0.00012881463,0.00020461253,0.0002053859,0.00014553839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018921379,0.00015571284,0.00030353936,0.00012094679,0.00039585956,0.000075527874,0.00026217953,0.000103321734,0.00001080059],"category_scores_gemma":[0.0057217306,0.000120432225,0.000061851904,0.00051302026,0.00023818719,0.0004950615,0.0004226409,0.0004620545,3.7298352e-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":[0.00011421606,0.000031322357,0.00078569166,0.0003488868,0.0000032989913,0.000004189307,0.00090727,0.004540344,0.9877558,0.000022871438,0.0000013337677,0.0054847794],"study_design_scores_gemma":[0.00019336962,0.00008591244,0.0010674213,0.00017862591,0.00002832362,0.0000024609913,0.00014284857,0.4366791,0.5614806,0.00007523837,5.181183e-7,0.00006559913],"about_ca_topic_score_codex":0.00014566204,"about_ca_topic_score_gemma":0.0000011528492,"teacher_disagreement_score":0.43213874,"about_ca_system_score_codex":0.00003812892,"about_ca_system_score_gemma":0.00008826489,"threshold_uncertainty_score":0.68498594},"labels":[],"label_agreement":null},{"id":"W3005165546","doi":"10.3758/s13428-020-01365-9","title":"Longform recordings of everyday life: Ethics for best practices","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Manitoba","funders":"National Institute of Mental Health; Social Sciences and Humanities Research Council of Canada; Universität Zürich; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Stanford Maternal and Child Health Research Institute; Agence Nationale de la Recherche; James S. McDonnell Foundation","keywords":"Autonomy; Beneficence; Set (abstract data type); Fidelity; Research ethics; Computer science; Everyday life; Data sharing; Informed consent; Economic Justice; Internet privacy; Data science; Psychology; Medicine","score_opus":0.8409786516589324,"score_gpt":0.7069141870663498,"score_spread":0.1340644645925826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005165546","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":[0.86577183,0.002612827,0.030742204,0.048129752,0.00195743,0.004813836,0.00012916331,0.00029548773,0.04554745],"genre_scores_gemma":[0.3776321,0.00021688623,0.6059509,0.0010852567,0.00091431936,0.0010065935,0.00003955144,0.000141203,0.013013159],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958259,0.0019773736,0.00044790676,0.0005645626,0.0006104465,0.00057382626],"domain_scores_gemma":[0.9932242,0.005143038,0.00033651936,0.00032398035,0.00061737583,0.0003548868],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012430427,0.00015389813,0.0003524129,0.0001641385,0.00027133984,0.000059064307,0.00048852444,0.0002766478,0.0013157206],"category_scores_gemma":[0.021318575,0.0001397568,0.00014575612,0.00057246524,0.00021671793,0.00012470622,0.00021394715,0.0017063146,0.00015982903],"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":[0.0019353199,0.0012664141,0.054046255,0.0005328383,0.00022545665,0.000060454906,0.043314684,0.0000012723219,0.06379101,0.011200324,0.028950965,0.794675],"study_design_scores_gemma":[0.0012442392,0.0024168815,0.093849994,0.000099513236,0.00009751596,0.000013767605,0.01000948,0.000033307148,0.009053392,0.00025318435,0.8825586,0.0003701616],"about_ca_topic_score_codex":0.00036975983,"about_ca_topic_score_gemma":0.000009967154,"teacher_disagreement_score":0.8536076,"about_ca_system_score_codex":0.000047211208,"about_ca_system_score_gemma":0.0004115969,"threshold_uncertainty_score":0.9995972},"labels":[],"label_agreement":null},{"id":"W3008656255","doi":"10.3758/s13428-020-01369-5","title":"Optimizing Detection of True Within-Person Effects for Intensive Measurement Designs: A Comparison of Multilevel SEM and Unit-Weighted Scale Scores","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","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":"University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada; National Institute on Aging; National Institutes of Health","keywords":"Covariate; Statistics; Reliability (semiconductor); Variance (accounting); Scale (ratio); Mathematics; Monte Carlo method; Observational error; Multilevel model; Hierarchical database model; Computer science; Variable (mathematics); Econometrics; Power (physics); Data mining","score_opus":0.736785635071355,"score_gpt":0.630519755261086,"score_spread":0.10626587981026903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008656255","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":[0.8117227,0.0012080475,0.18420134,0.0000973623,0.0002836562,0.0023844165,0.0000365784,0.000034828772,0.00003104652],"genre_scores_gemma":[0.84809977,0.0000054399097,0.15090427,0.000024300194,0.000033842956,0.00085827505,0.0000067617,0.00003333325,0.00003399677],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995242,0.0026547394,0.00064735446,0.0004510449,0.000528868,0.00047602292],"domain_scores_gemma":[0.9963344,0.00081639533,0.0002652594,0.00028792518,0.0019638923,0.0003321719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040352987,0.00018071366,0.000568885,0.00033921725,0.00020130337,0.000019722456,0.00021704497,0.00019411299,0.000047402787],"category_scores_gemma":[0.001232098,0.00016761478,0.0001652382,0.00046567875,0.00031772093,0.000090387,0.00007258277,0.0005729263,0.0000028080499],"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":[0.0013198281,0.000583907,0.009488194,0.0005128979,0.000046850026,0.000004060873,0.013844753,0.0000021504627,0.61599743,0.000094330826,0.00014786414,0.35795775],"study_design_scores_gemma":[0.0025807617,0.0062015257,0.0866375,0.00048436786,0.00019512126,0.000005792773,0.014723185,0.0038833623,0.8849613,0.000039246563,0.000087520566,0.00020030058],"about_ca_topic_score_codex":0.00082487194,"about_ca_topic_score_gemma":0.00011594273,"teacher_disagreement_score":0.35775745,"about_ca_system_score_codex":0.000087335335,"about_ca_system_score_gemma":0.00009532614,"threshold_uncertainty_score":0.6835132},"labels":[],"label_agreement":null},{"id":"W30187431","doi":"10.3758/s13428-018-1114-8","title":"Public Health Managers' Perspectives on the Use of Social Marketing Among Public Health Nurses in Saskatchewan","year":2006,"lang":"en","type":"dissertation","venue":"Behavior Research Methods","topic":"Service-Learning and Community Engagement","field":"Social Sciences","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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Nurses Foundation","keywords":"Public health; Social marketing; Marketing; Business; Public relations; Medicine; Political science; Nursing","score_opus":0.5615402895553624,"score_gpt":0.5857689816748963,"score_spread":0.024228692119533934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30187431","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":[0.95496714,0.00064692233,0.000058543064,0.019250339,0.00052545674,0.002705795,0.000030896965,0.00013545757,0.021679442],"genre_scores_gemma":[0.9150812,0.0010748185,0.012998186,0.00029526625,0.0004473683,0.0014619094,0.0007173244,0.00019099891,0.06773293],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.89606416,0.098612934,0.00075882924,0.0006120004,0.0023169303,0.00163514],"domain_scores_gemma":[0.99076813,0.006783508,0.000640819,0.00067935244,0.0008199901,0.00030819353],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.09402378,0.00029592172,0.0006420275,0.0013291177,0.0040641874,0.0007525538,0.0014087387,0.0003440516,0.0003421881],"category_scores_gemma":[0.005950149,0.00026746085,0.00023345723,0.0025759174,0.0007206595,0.00031600503,0.00016948214,0.0037066732,0.000005141467],"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":[0.000048061083,0.0009307385,0.0059777787,0.00017307176,0.000034771943,0.0000042155193,0.49585629,0.0000018106247,0.000018345248,0.0052475454,0.003693537,0.48801386],"study_design_scores_gemma":[0.00012713882,0.00009668291,0.23011261,0.00016534977,0.000005529421,7.379365e-8,0.7144798,0.000005636596,0.0000055161145,0.000043940145,0.054799233,0.00015848344],"about_ca_topic_score_codex":0.19032852,"about_ca_topic_score_gemma":0.23563306,"teacher_disagreement_score":0.48785537,"about_ca_system_score_codex":0.0018246202,"about_ca_system_score_gemma":0.0037880763,"threshold_uncertainty_score":0.99997777},"labels":[],"label_agreement":null},{"id":"W3027130718","doi":"10.3758/s13428-020-01403-6","title":"Assessing evidence for replication: A likelihood-based approach","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Replication (statistics); Computer science; Contrast (vision); Statistics; Econometrics; Artificial intelligence; Mathematics","score_opus":0.9916934429120137,"score_gpt":0.8138699872158525,"score_spread":0.1778234556961612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027130718","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":[0.011666243,0.0011355623,0.9761319,0.005550095,0.00007891258,0.003289295,0.000009250978,0.000019755917,0.0021189477],"genre_scores_gemma":[0.107909344,0.000006574377,0.8878068,0.0004111922,0.0002094965,0.0023794582,0.000010315582,0.000026793903,0.0012400539],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8943338,0.082609065,0.007594947,0.0032610989,0.011351374,0.0008497468],"domain_scores_gemma":[0.9143738,0.0635993,0.0027979128,0.010722194,0.0075153545,0.000991408],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5325486,0.00026154282,0.0023047542,0.00047246245,0.0005063638,0.0036011094,0.0037842188,0.00013568436,0.0024544913],"category_scores_gemma":[0.42896566,0.00014270822,0.0016564159,0.004518378,0.00017799264,0.00067415036,0.00031442763,0.00050112867,0.00058496214],"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":[0.00003582859,0.00018996173,0.013170698,0.000222803,0.000041569983,0.000005076894,0.0005197228,0.000047121466,0.020286072,0.00089994416,0.046426825,0.91815436],"study_design_scores_gemma":[0.00095830724,0.00060923625,0.042414095,0.00022512033,0.0006575446,0.000017710689,0.0049183383,0.36864522,0.013535167,0.006813861,0.5603094,0.0008960079],"about_ca_topic_score_codex":0.000011760035,"about_ca_topic_score_gemma":9.614033e-7,"teacher_disagreement_score":0.9172584,"about_ca_system_score_codex":0.00008120863,"about_ca_system_score_gemma":0.0005135962,"threshold_uncertainty_score":0.9984574},"labels":[],"label_agreement":null},{"id":"W3033146654","doi":"10.3758/s13428-020-01418-z","title":"The Metronome Counting Task for measuring meta-awareness","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","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 Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mind-wandering; Metronome; Task (project management); Cognitive psychology; Psychology; Computer science; Cognition","score_opus":0.8459687191205778,"score_gpt":0.6113941572223104,"score_spread":0.23457456189826742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033146654","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":[0.547606,0.0012180115,0.44059703,0.0057358285,0.00069027813,0.0028179095,0.00006759287,0.00029131866,0.0009760333],"genre_scores_gemma":[0.96835077,0.000043803313,0.028598877,0.00012779048,0.00024020138,0.0016367271,0.0000024605292,0.000051674808,0.00094769493],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9955472,0.0021406051,0.00029944748,0.00057111925,0.0007606617,0.00068097736],"domain_scores_gemma":[0.9958889,0.0032830213,0.00007817246,0.00035587462,0.00020028028,0.00019373317],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01010535,0.00014226789,0.0002702851,0.00009300469,0.0014437498,0.00037015884,0.0006591222,0.000056517485,0.00005955286],"category_scores_gemma":[0.007573911,0.00009440973,0.00026337002,0.0006061679,0.00020149503,0.00016248107,0.00023439544,0.00044281702,0.000024071493],"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":[0.000041478717,0.00003952495,0.0003155821,0.00003483844,0.00003105254,0.0000069444823,0.00021139873,0.000015738839,0.91106856,0.00092735596,0.00022123205,0.08708631],"study_design_scores_gemma":[0.00038532552,0.00015385076,0.0009369781,0.000008135393,0.0002453747,0.0000068551494,0.000463852,0.0023270168,0.9119803,0.00047344225,0.08280982,0.00020908291],"about_ca_topic_score_codex":0.00003208657,"about_ca_topic_score_gemma":0.0000035213377,"teacher_disagreement_score":0.42074478,"about_ca_system_score_codex":0.00005501497,"about_ca_system_score_gemma":0.00010066138,"threshold_uncertainty_score":0.99985623},"labels":[],"label_agreement":null},{"id":"W3036211922","doi":"10.3758/s13428-020-01397-1","title":"CompLex: an eye-movement database of compound word reading in English","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; McMaster University","keywords":"Eye movement; Sentence; Reading (process); Population; Natural language processing; Sample (material); Computer science; Word lists by frequency; Set (abstract data type); Word (group theory); Eye tracking; Word recognition; Artificial intelligence; Psychology; Database; Linguistics; Medicine","score_opus":0.46705324781155194,"score_gpt":0.6103505975625049,"score_spread":0.14329734975095293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036211922","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":[0.98613304,0.00014624953,0.0023738989,0.00035162095,0.00038657518,0.00089206337,0.000072724404,0.00008843705,0.009555388],"genre_scores_gemma":[0.7350037,0.00001929386,0.26277563,0.00026910962,0.00022072338,0.00042318396,0.00020258449,0.000057597466,0.0010281572],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933235,0.003975229,0.0006655967,0.00066270534,0.0006616971,0.0007112609],"domain_scores_gemma":[0.997772,0.00073015335,0.00009773787,0.00070604705,0.00030019647,0.00039388798],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007944384,0.00018244304,0.0004213206,0.0004301093,0.000106517946,0.00006936292,0.0006383058,0.000098543154,0.0017516772],"category_scores_gemma":[0.0006666445,0.000180718,0.00006248613,0.0010126018,0.00019817226,0.00018278087,0.0003097354,0.000783607,0.000045445264],"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":[0.00073572894,0.0023712402,0.2571914,0.00019462989,0.00007592891,0.0006652675,0.102106184,0.000006356802,0.24214108,0.0073210853,0.009626693,0.3775644],"study_design_scores_gemma":[0.0027326152,0.0008231991,0.8338286,0.00022302364,0.00003101127,0.0000062767526,0.018232957,0.0002960815,0.017207049,0.00028743016,0.12572215,0.00060959527],"about_ca_topic_score_codex":0.0009052476,"about_ca_topic_score_gemma":0.000023708662,"teacher_disagreement_score":0.5766372,"about_ca_system_score_codex":0.0001299576,"about_ca_system_score_gemma":0.00010434455,"threshold_uncertainty_score":0.9991609},"labels":[],"label_agreement":null},{"id":"W3045733287","doi":"10.3758/s13428-020-01393-5","title":"A thorough evaluation of the Language Environment Analysis (LENA) system","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":140,"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 Manitoba","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; James S. McDonnell Foundation; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Set (abstract data type); Language acquisition; Psychology; Computer science; Key (lock); Natural language processing; Mathematics education","score_opus":0.41493284419782056,"score_gpt":0.606574171447506,"score_spread":0.19164132724968547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045733287","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":[0.9727211,0.0016951935,0.00670972,0.00060330133,0.00016223469,0.0013804167,0.00002218591,0.00004534552,0.016660519],"genre_scores_gemma":[0.98715514,0.0000043994796,0.011425276,0.000039689137,0.00004553614,0.00050577,0.000017350098,0.000017186687,0.00078967435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991183,0.0065025035,0.00028046817,0.00035813366,0.001354315,0.00032156697],"domain_scores_gemma":[0.998788,0.00027106298,0.00009326839,0.0006083421,0.00013345566,0.000105867315],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009325061,0.00010627926,0.0002423948,0.00017322531,0.00011563911,0.000021371869,0.00046509723,0.00009254089,0.003814666],"category_scores_gemma":[0.00041310088,0.00007237838,0.00019657971,0.0013315663,0.00013294215,0.000037717542,0.00020706144,0.00028271548,0.000103160135],"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":[0.00018087095,0.0005918208,0.12413981,0.000104306826,0.0011924898,0.0000558393,0.109404296,0.00013032962,0.046673328,0.0021869405,0.0022392692,0.71310073],"study_design_scores_gemma":[0.0020783765,0.0001789904,0.83505636,0.000027725095,0.0030125245,0.0000054993866,0.13179627,0.002321493,0.021085935,0.000053490992,0.0039928197,0.00039048796],"about_ca_topic_score_codex":0.0003540811,"about_ca_topic_score_gemma":0.000015904296,"teacher_disagreement_score":0.7127102,"about_ca_system_score_codex":0.00012696866,"about_ca_system_score_gemma":0.00008732427,"threshold_uncertainty_score":0.997096},"labels":[],"label_agreement":null},{"id":"W3047542501","doi":"10.3758/s13428-020-01437-w","title":"Semi-automated transcription and scoring of autobiographical memory narratives","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Narrative; Computer science; Natural language processing; Python (programming language); Pipeline (software); Autobiographical memory; Software; Transcription (linguistics); World Wide Web; Artificial intelligence; Information retrieval; Cognitive psychology; Psychology; Programming language; Linguistics","score_opus":0.34199784367457753,"score_gpt":0.5841662341372162,"score_spread":0.24216839046263872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047542501","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":[0.991932,0.001498135,0.00273162,0.00067877566,0.00036910176,0.0005996153,0.00001310361,0.00023218138,0.0019454806],"genre_scores_gemma":[0.9878562,0.00012485683,0.011270825,0.000050961902,0.00013379108,0.00015568647,0.0000065752097,0.000036292735,0.00036481535],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.994913,0.003425281,0.00034429008,0.0004543077,0.00043110372,0.00043201266],"domain_scores_gemma":[0.99894667,0.00026138706,0.00006113222,0.00029356152,0.00019819691,0.00023902774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003431674,0.00014656664,0.00032606712,0.0003909268,0.00017791521,0.000047645113,0.00026460292,0.00018313975,0.0006936382],"category_scores_gemma":[0.00014316311,0.0001402128,0.000121844125,0.00091567216,0.00054683967,0.00012755451,0.00005576124,0.0006013846,0.000017710761],"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":[0.00026045236,0.00033043578,0.012702914,0.000088423665,0.000074518226,0.00006112749,0.024959957,6.095552e-7,0.9102109,0.0013461073,0.0006132434,0.049351275],"study_design_scores_gemma":[0.0040236833,0.0021995537,0.7636095,0.00011938859,0.00011085202,0.00006278876,0.03268392,0.0004354038,0.18958092,0.001964338,0.00457141,0.0006382376],"about_ca_topic_score_codex":0.0002282039,"about_ca_topic_score_gemma":0.000013007384,"teacher_disagreement_score":0.7509066,"about_ca_system_score_codex":0.000019167599,"about_ca_system_score_gemma":0.00004449398,"threshold_uncertainty_score":0.75948524},"labels":[],"label_agreement":null},{"id":"W3048953431","doi":"10.3758/s13428-020-01441-0","title":"On metrics for measuring scanpath similarity","year":2020,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":49,"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; University of Manitoba","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Similarity (geometry); Context (archaeology); Machine learning; Selection (genetic algorithm); Eye tracking; Process (computing); Data mining; Image (mathematics)","score_opus":0.782808445987271,"score_gpt":0.675500207103966,"score_spread":0.10730823888330498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048953431","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":[5.5326564e-7,0.4945629,0.5025954,0.000048040925,0.0006090957,0.0017227969,0.00001968005,0.00016718304,0.0002743186],"genre_scores_gemma":[0.0000026859134,0.7397999,0.25786117,0.00002530349,0.00015800956,0.0017092475,0.000013018337,0.000056212997,0.00037442482],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99050504,0.005235811,0.0006942855,0.0012577432,0.0015194628,0.00078764046],"domain_scores_gemma":[0.9949178,0.0028003044,0.00021981372,0.0010854886,0.000548984,0.00042758833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013746617,0.00040150183,0.0012883008,0.0014664255,0.0005481332,0.0005271579,0.0022951753,0.00040129447,0.000023421673],"category_scores_gemma":[0.0046647214,0.0003368406,0.0008881091,0.0041899034,0.00008486102,0.00023019515,0.00076030113,0.0016833396,0.00010180949],"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":[0.0000033348283,0.00013318886,5.127584e-7,0.0018275249,0.000019021289,0.000021282762,0.000029313123,1.7642168e-7,0.000008632695,0.005885968,0.00035531612,0.9917157],"study_design_scores_gemma":[0.00015214672,0.0005215466,0.0000062693953,0.0010261266,0.00010297035,0.000019854579,0.0000073596616,0.0008960252,0.00010415675,0.001069055,0.995741,0.00035345077],"about_ca_topic_score_codex":0.000016477494,"about_ca_topic_score_gemma":0.0000019913582,"teacher_disagreement_score":0.9953857,"about_ca_system_score_codex":0.00054585113,"about_ca_system_score_gemma":0.0006089468,"threshold_uncertainty_score":0.9999084},"labels":[],"label_agreement":null},{"id":"W3092821006","doi":"10.3758/s13428-020-01497-y","title":"Into a new decade","year":2020,"lang":"en","type":"editorial","venue":"Behavior Research Methods","topic":"Research Data Management Practices","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":"McMaster University","funders":"","keywords":"Computer science","score_opus":0.4932811838024936,"score_gpt":0.656737719488052,"score_spread":0.16345653568555846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092821006","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":[0.0000018137863,0.001052003,0.56893784,0.0046140337,0.42031538,0.0014237231,0.00003110061,0.00035739734,0.0032667015],"genre_scores_gemma":[8.332189e-7,0.0017494388,0.6067214,0.000035922087,0.37275586,0.0005096042,0.00014573331,0.000082495884,0.017998692],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9735556,0.011815775,0.00081249257,0.0028992875,0.008971864,0.0019449416],"domain_scores_gemma":[0.9733306,0.016900111,0.00037424828,0.0059550973,0.00147729,0.0019626415],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.031571813,0.0005759472,0.0008166873,0.0015823166,0.0005776862,0.011851328,0.021256194,0.0009763155,0.00014642283],"category_scores_gemma":[0.06838302,0.00055297744,0.00027398084,0.004007024,0.00035003084,0.017320639,0.01722547,0.008212982,0.0008380846],"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":[0.00002513989,0.000092762704,0.000006586108,0.000120648845,0.0000443255,0.0004882054,0.00022441818,1.8979725e-7,0.00057883776,0.0050872234,0.7346474,0.25868428],"study_design_scores_gemma":[0.00040395244,0.0003955198,0.00005046989,0.00007626741,0.00003648742,0.0000026650284,0.000050993243,0.00013921323,0.0007875564,0.0023773862,0.99517816,0.0005013551],"about_ca_topic_score_codex":0.0028799018,"about_ca_topic_score_gemma":0.00008428027,"teacher_disagreement_score":0.26053074,"about_ca_system_score_codex":0.0006447638,"about_ca_system_score_gemma":0.0050317603,"threshold_uncertainty_score":0.99993986},"labels":[],"label_agreement":null},{"id":"W3127637041","doi":"10.3758/s13428-020-01516-y","title":"NeuroKit2: A Python toolbox for neurophysiological signal processing","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":1285,"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 de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Courtois Foundation","keywords":"Python (programming language); Toolbox; Computer science; Neurophysiology; Suite; Signal processing; Human–computer interaction; Data processing; Digital signal processing; Software engineering; Artificial intelligence; Computer architecture; Programming language; Computer hardware; Database; Psychology; Neuroscience","score_opus":0.47697900905892937,"score_gpt":0.582458395201068,"score_spread":0.10547938614213864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127637041","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":[0.91599065,0.0001889211,0.07999997,0.0009514504,0.00041292526,0.0009894122,0.000042801377,0.0002476021,0.0011762597],"genre_scores_gemma":[0.7908048,0.000024847226,0.20395656,0.00082886603,0.00044229772,0.0006664432,0.0000067496367,0.0000774374,0.0031920143],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9929611,0.0040608253,0.00033704992,0.0010814869,0.0006653016,0.0008942491],"domain_scores_gemma":[0.99551105,0.003367271,0.00006391991,0.00042684728,0.0004025648,0.00022833873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022051784,0.00020600238,0.00030776192,0.00016655013,0.0005559985,0.0004391674,0.0006817187,0.00011921079,0.00017098682],"category_scores_gemma":[0.003035233,0.00016947686,0.00017908322,0.00086550496,0.0003568158,0.0002365605,0.0004237952,0.00080290355,0.000026256226],"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":[0.00005342702,0.00022443519,0.00003895244,0.00003451827,8.3373874e-7,0.00021574313,0.00009813417,0.000007837461,0.7067545,0.00022675368,0.00033472685,0.29201013],"study_design_scores_gemma":[0.0003349792,0.00055950327,0.0019550568,0.000032252556,0.000009118565,0.00013140189,0.000093011506,0.0034270904,0.96321386,0.0009135982,0.029126821,0.00020331494],"about_ca_topic_score_codex":0.000003505164,"about_ca_topic_score_gemma":8.906263e-7,"teacher_disagreement_score":0.29180682,"about_ca_system_score_codex":0.000040870826,"about_ca_system_score_gemma":0.00023871461,"threshold_uncertainty_score":0.6911066},"labels":[],"label_agreement":null},{"id":"W3127812953","doi":"10.3758/s13428-020-01511-3","title":"ASIA: Automated Social Identity Assessment using linguistic style","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health via Writing","field":"Psychology","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":"Institute of Population and Public Health; Engineering and Physical Sciences Research Council; European Association of Social Psychology","keywords":"Salient; Social identity theory; Identity (music); Variety (cybernetics); Style (visual arts); Social psychology; Field (mathematics); Computer science; Psychology; Protocol (science); Social media; Natural language processing; Interpretation (philosophy); Artificial intelligence; Social group; Cognitive psychology; Data science; World Wide Web; Mathematics","score_opus":0.5800148776480121,"score_gpt":0.739700750375458,"score_spread":0.15968587272744594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127812953","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":[0.94006497,0.00044581143,0.013518062,0.00025991246,0.0022640033,0.0010838053,0.000051030023,0.0005507613,0.041761626],"genre_scores_gemma":[0.6440716,0.000007369871,0.35305515,0.000061646424,0.0006617225,0.0003611264,0.0000422843,0.00008149654,0.001657617],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9856828,0.010527648,0.00063474633,0.0007324791,0.0011651606,0.0012571617],"domain_scores_gemma":[0.9971344,0.0010217222,0.00013400536,0.0005846127,0.0008033983,0.0003218637],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013271806,0.00019526649,0.00040408608,0.00034622021,0.001074129,0.00021190448,0.00040822645,0.00026934,0.0042269966],"category_scores_gemma":[0.0012829825,0.00022594778,0.00013465951,0.0014373389,0.0002367224,0.00014631709,0.00053608674,0.0013861698,0.00018015479],"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":[0.00018743055,0.0060670935,0.10149764,0.00088365504,0.00027832753,0.011278659,0.011986747,0.000002713847,0.40974757,0.08296982,0.0061082873,0.36899203],"study_design_scores_gemma":[0.0025460257,0.00031315247,0.95221394,0.00019486167,0.00018502072,0.00050743547,0.018181512,0.0032159206,0.009684864,0.0017478868,0.010435731,0.0007736339],"about_ca_topic_score_codex":0.0012453133,"about_ca_topic_score_gemma":0.00007840653,"teacher_disagreement_score":0.8507163,"about_ca_system_score_codex":0.000896469,"about_ca_system_score_gemma":0.0007021963,"threshold_uncertainty_score":0.9966833},"labels":[],"label_agreement":null},{"id":"W3135341785","doi":"10.3758/s13428-020-01528-8","title":"The Musical Ear Test: Norms and correlates from a large sample of Canadian undergraduates","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; General Electric (Canada); University of Toronto; Western University","funders":"Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Audiology; Rhythm; Memory span; Test (biology); Ceiling effect; Musical; Developmental psychology; Recall; Cognitive psychology; Cognition; Working memory; Medicine","score_opus":0.3206795973799662,"score_gpt":0.5131249007507384,"score_spread":0.19244530337077215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135341785","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":[0.9969549,0.000062494255,0.0005855988,0.0013406056,0.00026526998,0.0002321109,0.00017101824,0.000016107064,0.00037185833],"genre_scores_gemma":[0.99255544,0.0006398901,0.0056379274,0.00023830419,0.00005149879,0.000063317035,0.000006937115,0.000017286877,0.0007894107],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99667186,0.0013667642,0.00020689832,0.0005160679,0.00057784235,0.0006605914],"domain_scores_gemma":[0.9918424,0.007207619,0.00003750532,0.00046286147,0.00011960815,0.00032999527],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002291361,0.00010339998,0.00015243278,0.0002644893,0.00084983086,0.00018869575,0.0003568323,0.000075592965,0.0001424264],"category_scores_gemma":[0.014905454,0.00007366159,0.00005322546,0.0014698103,0.0007275349,0.00014987492,0.0002600491,0.0004949102,0.000017466136],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052274722,0.00009332399,0.0096634785,0.0000025264553,6.948033e-7,0.00006147637,0.00035804664,1.6197187e-7,0.9641965,0.0020979808,0.00025043153,0.02327016],"study_design_scores_gemma":[0.00036455426,0.00014682734,0.40310264,0.00002563164,0.000016419262,0.00004600129,0.0010273573,0.00045200824,0.53376156,0.007465438,0.05341174,0.00017985865],"about_ca_topic_score_codex":0.031846985,"about_ca_topic_score_gemma":0.028296882,"teacher_disagreement_score":0.43043497,"about_ca_system_score_codex":0.000051617804,"about_ca_system_score_gemma":0.00044070234,"threshold_uncertainty_score":0.9933924},"labels":[],"label_agreement":null},{"id":"W3140486864","doi":"10.3758/s13428-021-01556-y","title":"Is the author recognition test a useful metric for native and non-native English speakers? An item response theory analysis","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","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":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Hebrew University of Jerusalem","keywords":"Test (biology); Psychology; Reading (process); Item response theory; Neuroscience of multilingualism; First language; Foreign language; Language assessment; Linguistics; Cognitive psychology; Mathematics education; Psychometrics; Developmental psychology","score_opus":0.3218624457308632,"score_gpt":0.5860858601608735,"score_spread":0.2642234144300103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140486864","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":[0.97423977,0.0004304345,0.020086035,0.00060461863,0.000360655,0.0014691162,0.00035799365,0.000056288576,0.0023950895],"genre_scores_gemma":[0.756636,0.00005958248,0.19050187,0.00034542233,0.00035646564,0.004057063,0.0002470374,0.00010543698,0.047691103],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.977493,0.019824127,0.00048465692,0.00092217943,0.0005905509,0.0006855259],"domain_scores_gemma":[0.95186186,0.044576243,0.00014921554,0.0007398776,0.002425712,0.00024710718],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041031912,0.0002321468,0.0004427644,0.0014861559,0.00067500945,0.0002372183,0.00035001762,0.00022151055,0.0012318082],"category_scores_gemma":[0.028636174,0.00017495616,0.00022394699,0.004851569,0.00033670422,0.00021372954,0.00017955551,0.0008588145,0.000021604523],"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":[0.0030641593,0.001212601,0.0621883,0.000040802122,0.0015937809,0.00019336757,0.3249421,5.181274e-7,0.004185782,0.00057883083,0.0037279327,0.5982718],"study_design_scores_gemma":[0.0011807618,0.0006572417,0.8890801,0.00004431789,0.00074876536,0.00001638387,0.07272237,0.00014443212,0.011148616,0.0021682659,0.021730144,0.00035859444],"about_ca_topic_score_codex":0.000083130246,"about_ca_topic_score_gemma":0.00002231643,"teacher_disagreement_score":0.8268918,"about_ca_system_score_codex":0.0002096671,"about_ca_system_score_gemma":0.0002570988,"threshold_uncertainty_score":0.9996812},"labels":[],"label_agreement":null},{"id":"W3150425792","doi":"10.3758/s13428-021-01592-8","title":"The good and the bad: Are some attribute words better than others in the Implicit Association Test?","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":15,"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":"Psychology; Implicit-association test; Cognitive psychology; Set (abstract data type); Test (biology); Quality (philosophy); Selection (genetic algorithm); Association (psychology); Social psychology; Artificial intelligence; Computer science","score_opus":0.19250705590750736,"score_gpt":0.5669183079270538,"score_spread":0.3744112520195464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150425792","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":[0.8277771,0.0014470348,0.00008786854,0.16182509,0.000601268,0.00095849304,0.000019212957,0.000029847331,0.00725412],"genre_scores_gemma":[0.9800214,0.001756424,0.0009979005,0.0026444143,0.0013439398,0.0012676484,0.0000054524544,0.00003510518,0.011927719],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9827784,0.015051502,0.00024612545,0.00029481473,0.0008869379,0.0007422276],"domain_scores_gemma":[0.98615366,0.013042425,0.00010849529,0.0003659721,0.0002555772,0.000073886076],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.032440048,0.00010278508,0.00020118107,0.000057745456,0.0017662689,0.00046046474,0.00073481223,0.00019945473,0.00009125215],"category_scores_gemma":[0.006443675,0.0000533109,0.00011746405,0.0009357802,0.00095652486,0.00014183704,0.00017269432,0.0009360116,0.00001685838],"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":[0.000051218114,0.00022461599,0.7757518,0.0000037181712,0.00004231143,0.00003106332,0.05481441,5.0396523e-8,0.0019957486,0.022035215,0.008601987,0.13644783],"study_design_scores_gemma":[0.00062159775,0.000043817607,0.81880903,0.000014345121,0.000021698012,0.0000026952482,0.06806695,0.000002519957,0.00017503455,0.017440831,0.09469868,0.00010282417],"about_ca_topic_score_codex":0.0029991516,"about_ca_topic_score_gemma":0.006618229,"teacher_disagreement_score":0.15918067,"about_ca_system_score_codex":0.0002574078,"about_ca_system_score_gemma":0.00014156698,"threshold_uncertainty_score":0.9995333},"labels":[],"label_agreement":null},{"id":"W3152214984","doi":"10.3758/s13428-021-01558-w","title":"Evaluating the predication model of metaphor comprehension: Using word2vec to model best/worst quality judgments of 622 novel metaphors","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaphor; Comprehension; Set (abstract data type); Quality (philosophy); Computer science; Cognitive psychology; Cognition; Word2vec; Space (punctuation); Natural language processing; Psychology; Artificial intelligence; Linguistics; Epistemology; Philosophy","score_opus":0.7789337434495036,"score_gpt":0.6764091439089269,"score_spread":0.10252459954057669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152214984","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":[0.73803395,0.0007039263,0.2588158,0.00010993481,0.00019438386,0.0011259136,0.0001421568,0.000021589382,0.0008523779],"genre_scores_gemma":[0.52849364,0.00001962681,0.46962932,0.00006972605,0.000040646406,0.00051046675,0.00003866828,0.00004604587,0.0011518939],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9882201,0.007072538,0.0012093046,0.0008206454,0.0020079056,0.0006695017],"domain_scores_gemma":[0.9943011,0.0013855661,0.00040009586,0.0015566684,0.0021224637,0.00023412655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01943448,0.0002642205,0.00070374284,0.000428415,0.00032820826,0.000046648973,0.00066615175,0.0002250782,0.00042972158],"category_scores_gemma":[0.0019482124,0.00021053139,0.00032974395,0.0016403832,0.00033968754,0.00015260205,0.00048978097,0.00070821244,0.000012540905],"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":[0.0002937036,0.0014080887,0.00030908824,0.00007737612,0.00017325068,0.0000037020818,0.007908138,0.007574301,0.90625787,0.002069695,0.000039199545,0.07388556],"study_design_scores_gemma":[0.0027268508,0.00070114614,0.0077322945,0.00029389295,0.0015301092,0.000033883058,0.02601898,0.49827057,0.45562217,0.0063590095,0.000050608407,0.000660511],"about_ca_topic_score_codex":0.0009966753,"about_ca_topic_score_gemma":0.00004754074,"teacher_disagreement_score":0.49069625,"about_ca_system_score_codex":0.00012868755,"about_ca_system_score_gemma":0.00049449323,"threshold_uncertainty_score":0.85852206},"labels":[],"label_agreement":null},{"id":"W3156228691","doi":"10.3758/s13428-021-01570-0","title":"Calculating semantic relatedness of lists of nouns using WordNet path length","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"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","funders":"","keywords":"WordNet; Computer science; Noun; Natural language processing; Path (computing); Artificial intelligence; Semantic similarity; Information retrieval; Programming language","score_opus":0.25866170950767636,"score_gpt":0.5705119817345476,"score_spread":0.3118502722268713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156228691","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":[0.3526398,0.0026664638,0.64406973,0.00005428474,0.00012498483,0.00022063879,0.0000040120126,0.0001176926,0.00010239271],"genre_scores_gemma":[0.35291627,0.000016146934,0.6469321,0.0000049833498,0.000015242195,0.000011774791,0.0000020053055,0.000014497856,0.000086928885],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9954407,0.002149951,0.00052146096,0.00048764213,0.0009228326,0.00047737596],"domain_scores_gemma":[0.99669486,0.0007671233,0.00020641122,0.0009718465,0.0012484493,0.00011132889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006136796,0.00014195987,0.00038046486,0.00034641474,0.00014831779,0.000097376695,0.0010432916,0.00016689415,0.000022624938],"category_scores_gemma":[0.0020046283,0.00013101628,0.00011215151,0.0022051602,0.00021149291,0.0003591776,0.0010573373,0.0007120937,8.721511e-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":[0.000006285995,0.00019570267,0.0029971914,0.00021525189,0.000013288123,0.00024987484,0.0014191177,0.000008607741,0.7805595,0.0061973887,0.00001695641,0.20812085],"study_design_scores_gemma":[0.00020854331,0.00009179151,0.0020267256,0.0005979954,0.000025701973,0.00010907546,0.00021090891,0.020563873,0.97002643,0.005853678,0.000062446255,0.00022284142],"about_ca_topic_score_codex":0.0004305799,"about_ca_topic_score_gemma":0.000008851735,"teacher_disagreement_score":0.207898,"about_ca_system_score_codex":0.000099612684,"about_ca_system_score_gemma":0.00048020994,"threshold_uncertainty_score":0.53426886},"labels":[],"label_agreement":null},{"id":"W3161204446","doi":"10.3758/s13428-021-01583-9","title":"Introducing BITTSy: The Behavioral Infant &amp; Toddler Testing System","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","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":"McGill University; University of Toronto","funders":"Graduate School, University of Maryland; National Science Foundation","keywords":"Toddler; Computer science; Software; Set (abstract data type); Fixation (population genetics); Human–computer interaction; Embedded system; Operating system; Programming language; Psychology; Medicine","score_opus":0.4514430033162071,"score_gpt":0.6074659095288819,"score_spread":0.15602290621267478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161204446","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":[0.9576013,0.002058559,0.0051360345,0.0005844819,0.0017573567,0.00092979125,0.000013283239,0.00027367956,0.031645518],"genre_scores_gemma":[0.5173447,0.000011744773,0.43405724,0.00020509475,0.00094791286,0.0022212034,0.00010616795,0.00017538464,0.044930525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99224186,0.0046284213,0.00048495433,0.00077496626,0.00079588627,0.0010739233],"domain_scores_gemma":[0.9960594,0.0016044024,0.00008785757,0.0013269327,0.0007179672,0.00020345194],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00936603,0.00023212354,0.00032984017,0.00036414957,0.0006737996,0.00025749573,0.0006102572,0.0001889586,0.0025408103],"category_scores_gemma":[0.0015944828,0.00016816788,0.0001252759,0.002309759,0.00025571912,0.00010933461,0.0005330011,0.0010899013,0.0005582767],"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":[0.000086348744,0.0009078432,0.18118721,0.00009115433,0.00010088131,0.0014035244,0.023218324,0.00000487815,0.07330589,0.0049627423,0.016039096,0.6986921],"study_design_scores_gemma":[0.0031745029,0.00035298252,0.56530106,0.00035122797,0.00036670518,0.0015104262,0.1309248,0.00006369978,0.018186934,0.00033327096,0.2776973,0.0017371104],"about_ca_topic_score_codex":0.001560915,"about_ca_topic_score_gemma":0.00023715888,"teacher_disagreement_score":0.696955,"about_ca_system_score_codex":0.00018489333,"about_ca_system_score_gemma":0.0003481285,"threshold_uncertainty_score":0.998371},"labels":[],"label_agreement":null},{"id":"W3165834552","doi":"10.3758/s13428-021-01664-9","title":"OpenMaze: An open-source toolbox for creating virtual navigation experiments","year":2021,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Spatial Cognition and Navigation","field":"Engineering","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":"Regional Municipality of Waterloo; University of Toronto","funders":"","keywords":"Toolbox; Bespoke; Computer science; Human–computer interaction; Coding (social sciences); Variety (cybernetics); Task (project management); Software; Process (computing); Software engineering; Artificial intelligence; Systems engineering","score_opus":0.5711997562062917,"score_gpt":0.6509840627283027,"score_spread":0.07978430652201096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165834552","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":[0.00016401417,0.92299926,0.0683706,0.0000030753758,0.0006120539,0.005849102,0.00017163465,0.00029070076,0.0015395728],"genre_scores_gemma":[0.00002469413,0.8047112,0.17252046,0.00001013211,0.00055810134,0.014327717,0.005505587,0.0004190363,0.001923059],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939795,0.003157625,0.00085787167,0.0007449198,0.0005958415,0.0006642236],"domain_scores_gemma":[0.9969932,0.0012287727,0.000134357,0.0007368442,0.0005784483,0.0003283669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006256979,0.00045629073,0.0013212059,0.00036985552,0.00046338091,0.0009462262,0.0010644384,0.0005175226,0.00044616772],"category_scores_gemma":[0.0008075303,0.00046307704,0.00027801667,0.0009922162,0.000079809426,0.0006096037,0.00036933192,0.0010739621,0.000048211426],"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":[0.0000060515185,0.000115469134,6.0420115e-7,0.0013669512,0.000043989767,0.0000088092065,0.00024035272,0.000008741409,0.000638856,0.00015374148,0.00031576803,0.99710065],"study_design_scores_gemma":[0.00044495187,0.0003054443,0.000002771372,0.0066771405,0.00024149191,0.000027358881,0.0005698203,0.00068088423,0.0025582723,0.00002012395,0.9878954,0.0005762853],"about_ca_topic_score_codex":0.000107470776,"about_ca_topic_score_gemma":0.0000057197435,"teacher_disagreement_score":0.9965244,"about_ca_system_score_codex":0.00048804996,"about_ca_system_score_gemma":0.00032708302,"threshold_uncertainty_score":0.9997821},"labels":[],"label_agreement":null},{"id":"W3166385395","doi":"10.3758/s13428-021-01628-z","title":"The Early Social Cognition Inventory (ESCI): An examination of its psychometric properties from birth to 47 months","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":8,"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; Psychology; Cognitive test; Developmental psychology; Social cognition; Test (biology); Social cognitive theory; Clinical psychology; Pediatrics; Medicine; Psychiatry","score_opus":0.3798399237008766,"score_gpt":0.5371560630070777,"score_spread":0.15731613930620114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166385395","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":[0.9938002,0.0012687497,0.00025559342,0.00032983086,0.00037563295,0.0005799214,0.000025804333,0.00004216957,0.0033221028],"genre_scores_gemma":[0.98877424,0.000054626464,0.0055818916,0.00003465275,0.00023379546,0.000398812,0.000029166082,0.00003370827,0.0048591266],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9926164,0.0053217667,0.00034485201,0.00048550765,0.00078873185,0.00044273477],"domain_scores_gemma":[0.9981915,0.0004445857,0.00008324627,0.0003224164,0.0008033839,0.0001548832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056586047,0.00012852254,0.00021090345,0.0004237271,0.0005222106,0.00013066854,0.00034074273,0.00013040724,0.00061087863],"category_scores_gemma":[0.0012350009,0.000100421355,0.0000772944,0.0015303119,0.00015689469,0.00011278671,0.0001569072,0.00052678573,0.00011996752],"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":[0.00018499188,0.00059774995,0.008277877,0.000015318146,0.000043117816,0.00001739788,0.012568188,1.715297e-7,0.14140499,0.0007642679,0.0004070502,0.83571887],"study_design_scores_gemma":[0.00039461366,0.00033646458,0.9622823,0.00003652197,0.000018677458,0.0000019697434,0.003694157,0.0000055539003,0.02240167,0.000107778425,0.010589406,0.00013087565],"about_ca_topic_score_codex":0.00017457048,"about_ca_topic_score_gemma":0.000059500682,"teacher_disagreement_score":0.9540044,"about_ca_system_score_codex":0.000086794185,"about_ca_system_score_gemma":0.00014294505,"threshold_uncertainty_score":0.66886926},"labels":[],"label_agreement":null},{"id":"W3166958512","doi":"10.3758/s13428-021-01602-9","title":"Building an intelligent recommendation system for personalized test scheduling in computerized assessments: A reinforcement learning approach","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":23,"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":"Formative assessment; Pace; Computer science; Test (biology); Scheduling (production processes); Reinforcement learning; Machine learning; Mathematics education; Psychology; Engineering; Operations management","score_opus":0.3273825167922156,"score_gpt":0.5494179913574728,"score_spread":0.22203547456525724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166958512","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":[0.019999169,0.00009618171,0.97759825,0.000072959054,0.00048875384,0.0011517176,0.0000014704775,0.00019665186,0.00039481878],"genre_scores_gemma":[0.13670252,0.000013637643,0.8605668,0.0000134060365,0.00016376795,0.0008780063,0.000045408025,0.00003764549,0.0015788048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921859,0.0043117073,0.00079550507,0.0010451034,0.00075383997,0.0009079316],"domain_scores_gemma":[0.9964983,0.0015575606,0.00022003017,0.00054889295,0.00094967545,0.0002255654],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.016743304,0.00026383865,0.0004926869,0.0005751604,0.0006368817,0.00087357813,0.00083233207,0.00014584062,0.000020618167],"category_scores_gemma":[0.0011131269,0.00027182858,0.00016097359,0.0011449447,0.00005103762,0.00071808184,0.0006046314,0.001005369,0.0000059450203],"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":[0.000067176166,0.00075302215,0.0031942348,0.00054820953,0.000053190623,0.00008443303,0.0030571169,0.032872554,0.15689519,0.3114054,0.000009705252,0.49105978],"study_design_scores_gemma":[0.0010524826,0.0005195944,0.00037938688,0.0004683323,0.000012972787,0.000062584426,0.0054021617,0.93571883,0.03133292,0.000104040366,0.024538057,0.00040864764],"about_ca_topic_score_codex":0.0001473651,"about_ca_topic_score_gemma":0.0000025682507,"teacher_disagreement_score":0.9028463,"about_ca_system_score_codex":0.0009789624,"about_ca_system_score_gemma":0.00033525738,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W3170480231","doi":"10.3758/s13428-021-01564-y","title":"The RK processor: A program for analysing metaphor and word feature-listing data","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":12,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaphor; Computer science; Feature (linguistics); Ambiguity; Natural language processing; Word (group theory); Coding (social sciences); Artificial intelligence; Consistency (knowledge bases); Similarity (geometry); Information retrieval; Linguistics; Programming language","score_opus":0.4311475053656623,"score_gpt":0.6309512869748113,"score_spread":0.19980378160914897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170480231","genre_codex":"empirical","genre_gemma":"methods","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":[0.74052656,0.11553769,0.09502703,0.006639003,0.0027411382,0.014212649,0.0008203233,0.00089848496,0.023597145],"genre_scores_gemma":[0.096880324,0.00036442987,0.8712628,0.00012703596,0.00081905385,0.0064200214,0.0007906849,0.00013836125,0.02319729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99407756,0.003353379,0.00030896868,0.0008965159,0.0005324586,0.0008311394],"domain_scores_gemma":[0.99483913,0.002757354,0.000100454825,0.0013506616,0.0007743705,0.00017805258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013468823,0.00018066334,0.0003155734,0.00017020047,0.00099687,0.00059668714,0.00067687733,0.00016218357,0.00009989615],"category_scores_gemma":[0.004542462,0.00012539388,0.00011015707,0.0012216086,0.00031202775,0.0001730919,0.00047890897,0.00071876467,0.000008378429],"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":[0.00011168163,0.0002724954,0.0006939762,0.0000492731,0.00013541605,0.00007618757,0.0010441089,2.0514946e-8,0.005023247,0.0007799879,0.0019564263,0.9898572],"study_design_scores_gemma":[0.004410878,0.00091352453,0.061589543,0.000248714,0.0028050416,0.00061352865,0.07211926,0.0013325822,0.02812154,0.011222578,0.815238,0.0013847871],"about_ca_topic_score_codex":0.00012262684,"about_ca_topic_score_gemma":0.00022568683,"teacher_disagreement_score":0.9884724,"about_ca_system_score_codex":0.000035922127,"about_ca_system_score_gemma":0.00017161475,"threshold_uncertainty_score":0.7667219},"labels":[],"label_agreement":null},{"id":"W3173672466","doi":"10.3758/s13428-021-01604-7","title":"Troubled past: A critical psychometric assessment of the self-report Survey of Autobiographical Memory (SAM)","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Douglas Mental Health University Institute; McGill University; McGill Genome Centre; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute on Aging; National Institutes of Health","keywords":"Autobiographical memory; Episodic memory; Psychology; Recall; Semantic memory; Childhood memory; Cognitive psychology; Association (psychology); Developmental psychology; Cognition; Psychiatry","score_opus":0.35808866813911666,"score_gpt":0.6406066858722068,"score_spread":0.28251801773309015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173672466","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":[0.981349,0.0009509014,0.0042607626,0.000604375,0.0028590267,0.00091919414,0.000066940396,0.000057741716,0.008932092],"genre_scores_gemma":[0.9523759,0.00007885717,0.044926446,0.000033163185,0.00014319117,0.0003271358,0.00002225455,0.000058084024,0.0020350039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9762644,0.019413076,0.0010258727,0.0007524738,0.00172543,0.00081872934],"domain_scores_gemma":[0.99078184,0.0043546758,0.00021057691,0.0019880217,0.0024148459,0.00025002894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027448054,0.00022931528,0.00072066806,0.0010952315,0.00023663307,0.000064575725,0.0009239321,0.00034473854,0.0023051137],"category_scores_gemma":[0.0032041427,0.00018084758,0.00049341924,0.0066386503,0.00084628456,0.00008008711,0.0003239992,0.0012864103,0.000010476938],"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":[0.00013522158,0.006800333,0.9298944,0.00011839897,0.00033976568,0.0005226128,0.00046663688,3.1670925e-7,0.02365343,0.0051846677,0.0019236421,0.030960603],"study_design_scores_gemma":[0.001108114,0.00027208836,0.98921114,0.000026792353,0.00010637305,0.00021464296,0.00038557756,0.000008393484,0.0072015356,0.0005910648,0.0007100275,0.0001642476],"about_ca_topic_score_codex":0.0018585988,"about_ca_topic_score_gemma":0.00022645225,"teacher_disagreement_score":0.059316773,"about_ca_system_score_codex":0.00009667705,"about_ca_system_score_gemma":0.00076165964,"threshold_uncertainty_score":0.9986069},"labels":[],"label_agreement":null},{"id":"W3174949916","doi":"10.3758/s13428-021-01636-z","title":"Challenging response latencies in faking detection: The case of few items and no warnings","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Deception detection and forensic psychology","field":"Psychology","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":"Queen's University","funders":"","keywords":"Psychology; Lie detection; Computer science; Deception; Cognitive psychology; Applied psychology; Social psychology","score_opus":0.32414565031786513,"score_gpt":0.6050252207614508,"score_spread":0.2808795704435857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174949916","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":[0.99074465,0.00087880035,0.0017686649,0.00044780303,0.0009087607,0.00034516765,0.0000032606968,0.000037674537,0.00486521],"genre_scores_gemma":[0.99195105,0.00007051797,0.00282491,0.00004663672,0.000071036666,0.00026786537,6.7264966e-7,0.000022767697,0.004744531],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99094975,0.007618845,0.0003683074,0.00042504322,0.00020887532,0.00042917108],"domain_scores_gemma":[0.99680305,0.0021264262,0.00008197238,0.00053356873,0.00036125415,0.00009373351],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012344892,0.00011597968,0.0002305439,0.00048142552,0.0002739964,0.00004006684,0.00014013684,0.00018514671,0.0010272387],"category_scores_gemma":[0.0016389448,0.00009582493,0.00007179126,0.0010064035,0.0004947286,0.00006442334,0.00015108119,0.0009041917,0.000052474807],"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":[0.00095687725,0.00021497585,0.0026708331,0.000025169027,0.00003311522,0.0035107762,0.017613266,0.0000014280371,0.17299005,0.00055360317,0.0002950739,0.8011348],"study_design_scores_gemma":[0.0046023857,0.0016066774,0.6576006,0.00018852709,0.00006794085,0.04100574,0.114849836,0.00068458257,0.039890468,0.0011230543,0.1376448,0.00073542754],"about_ca_topic_score_codex":0.00036580785,"about_ca_topic_score_gemma":0.00021768389,"teacher_disagreement_score":0.8003994,"about_ca_system_score_codex":0.00005849594,"about_ca_system_score_gemma":0.00004462019,"threshold_uncertainty_score":0.999886},"labels":[],"label_agreement":null},{"id":"W3178744861","doi":"10.3758/s13428-021-01630-5","title":"Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus space","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aesthetic Perception and Analysis","field":"Neuroscience","cited_by":21,"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":"Perception; Mnemonic; Computer science; Artificial intelligence; Visual perception; Computer vision; Stimulus (psychology); Visual memory; Psychology; Cognitive psychology; Cognition","score_opus":0.3031626478333489,"score_gpt":0.5148994585921086,"score_spread":0.21173681075875972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178744861","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":[0.9911627,0.000103557555,0.0044054403,0.0004111339,0.000036288613,0.00027921257,0.0000071720146,0.000057823618,0.00353667],"genre_scores_gemma":[0.9105543,0.000574291,0.08085829,0.000038169645,0.00003743106,0.00006774392,0.0000022443908,0.00003291538,0.007834619],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99429476,0.003341683,0.0002886295,0.0006418502,0.0009773033,0.00045574782],"domain_scores_gemma":[0.9984094,0.00029081135,0.000085383916,0.0005151936,0.00046112345,0.00023810798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034501886,0.00016224493,0.0003858377,0.00042645232,0.00029504503,0.0001096382,0.00021655235,0.00006788819,0.00058894913],"category_scores_gemma":[0.0010010151,0.00013581646,0.00009004561,0.0013285617,0.00067885814,0.00016109389,0.00020679683,0.00041075438,0.000013653694],"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":[0.000049102895,0.00016946965,0.0071868715,0.00002925363,0.0000023231582,0.000102905025,0.00061966345,0.00000748653,0.80396116,0.000104382525,0.000019320154,0.18774806],"study_design_scores_gemma":[0.0012562508,0.00034271003,0.19713336,0.00024708812,0.00013604239,0.00021281364,0.0060272687,0.0014990638,0.7915604,0.00013278068,0.00103825,0.0004139786],"about_ca_topic_score_codex":0.00056749955,"about_ca_topic_score_gemma":0.0002997324,"teacher_disagreement_score":0.18994649,"about_ca_system_score_codex":0.000092409384,"about_ca_system_score_gemma":0.00018020235,"threshold_uncertainty_score":0.644858},"labels":[],"label_agreement":null},{"id":"W3195351601","doi":"10.3758/s13428-021-01679-2","title":"The Multiple Object Avoidance (MOA) task measures attention for action: Evidence from driving and sport","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":21,"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":"Trent University; Nottingham Trent University","keywords":"Task (project management); Psychology; Cognitive psychology; Action (physics); Object (grammar); Computer science; Artificial intelligence","score_opus":0.48095421207596134,"score_gpt":0.6343246860396539,"score_spread":0.15337047396369252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195351601","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":[0.9076641,0.0019978452,0.08455973,0.0015490032,0.0022358277,0.00096141483,0.00002572191,0.000124789,0.0008815382],"genre_scores_gemma":[0.9449514,0.00037513717,0.03682957,0.000047873495,0.00039930886,0.001580254,0.000029592813,0.000037619826,0.01574923],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99572414,0.0024033098,0.00038413628,0.0005431713,0.00052701216,0.0004182075],"domain_scores_gemma":[0.99337864,0.0050180973,0.000112598194,0.00060446566,0.00075163925,0.00013457752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067836046,0.00013062527,0.00019809895,0.000110365036,0.0010517635,0.00025598423,0.00023688318,0.0001275823,0.0008310495],"category_scores_gemma":[0.003195489,0.000108008826,0.00013085245,0.0002919827,0.00018975716,0.00026167536,0.00010688405,0.0005774988,0.00007194479],"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":[0.00027346303,0.0001841405,0.1281777,0.000021162725,0.000081171514,0.00003650203,0.0020446174,0.000002140105,0.21612954,0.0007151922,0.005099016,0.64723533],"study_design_scores_gemma":[0.000504125,0.000068155925,0.87593764,0.00009422074,0.000028596773,0.000034553024,0.003753725,0.00032495207,0.010816449,0.00027522937,0.108016916,0.0001454099],"about_ca_topic_score_codex":0.0003521244,"about_ca_topic_score_gemma":0.0008146716,"teacher_disagreement_score":0.74776,"about_ca_system_score_codex":0.00012134598,"about_ca_system_score_gemma":0.00011188735,"threshold_uncertainty_score":0.90994096},"labels":[],"label_agreement":null},{"id":"W3196590458","doi":"10.3758/s13428-022-01919-z","title":"Reliability of the empathy selection task, a novel behavioral measure of empathy avoidance","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","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 Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Empathy; Psychology; Task (project management); Reliability (semiconductor); Selection (genetic algorithm); Cognitive psychology; Stroop effect; Social psychology; Computer science; Cognition; Artificial intelligence","score_opus":0.3840022036709241,"score_gpt":0.6043703302202744,"score_spread":0.22036812654935034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196590458","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":[0.99413955,0.00033958943,0.0010896019,0.00015183348,0.0014520297,0.0017426132,0.0004215422,0.00004658343,0.00061664334],"genre_scores_gemma":[0.98446476,0.000003061714,0.010512602,0.000022091397,0.00005460201,0.0023271728,0.00001436522,0.00004616997,0.0025551587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98772556,0.008343047,0.0010180525,0.0006401767,0.0014705147,0.0008026359],"domain_scores_gemma":[0.9967202,0.0003711972,0.000389635,0.0012849348,0.0010228425,0.00021117693],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014494696,0.00020716847,0.00046334526,0.0003865357,0.0008043072,0.00001562781,0.0010716218,0.00021126553,0.0031556154],"category_scores_gemma":[0.00045080137,0.00017465888,0.00051158975,0.0022582046,0.00062225026,0.0001181404,0.00059999625,0.0024237796,0.0000111824165],"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":[0.0012368462,0.020970061,0.37094074,0.00015618558,0.00003881191,0.000013716035,0.01631653,0.00002682514,0.36950356,0.002241933,0.0064551695,0.2120996],"study_design_scores_gemma":[0.0011390641,0.0023682646,0.9665458,0.000052774292,0.000110788686,0.00005206809,0.0083474135,0.000025247551,0.016333634,0.00016901085,0.0046318504,0.00022407166],"about_ca_topic_score_codex":0.00610103,"about_ca_topic_score_gemma":0.00020114126,"teacher_disagreement_score":0.5956051,"about_ca_system_score_codex":0.0003996039,"about_ca_system_score_gemma":0.0004439213,"threshold_uncertainty_score":0.9998777},"labels":[],"label_agreement":null},{"id":"W3200105746","doi":"10.3758/s13428-021-01704-4","title":"The Early Humor Survey (EHS): A reliable parent-report measure of humor development for 1- to 47-month-olds","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Humor Studies and Applications","field":"Psychology","cited_by":11,"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":"Psychology; Developmental psychology; Exploratory factor analysis; Clinical psychology; Psychometrics","score_opus":0.49298477628125853,"score_gpt":0.6242857224602868,"score_spread":0.13130094617902827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200105746","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":[0.9626097,0.0022547955,0.016964577,0.0019294046,0.0009872784,0.0048730313,0.00023878184,0.00008920138,0.01005321],"genre_scores_gemma":[0.6389471,0.00005755147,0.26564574,0.00006716796,0.000240375,0.02378568,0.00015235684,0.00014578358,0.0709582],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99459124,0.001942944,0.00081448146,0.000759675,0.000862332,0.0010293092],"domain_scores_gemma":[0.9939365,0.0024128598,0.00015393921,0.0014067654,0.0017980163,0.00029196948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018359665,0.00021143482,0.00045001358,0.00013613014,0.0011533219,0.00010197384,0.0006747116,0.0001236037,0.00034815344],"category_scores_gemma":[0.0027164698,0.00016546996,0.00016304353,0.0010821419,0.00022581607,0.000024678542,0.00044450187,0.0004376886,0.00007910527],"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":[0.00096482283,0.003479214,0.26181206,0.00013629287,0.00085022376,0.00044147973,0.024563562,0.0000042048136,0.0535637,0.012978351,0.11637885,0.52482724],"study_design_scores_gemma":[0.00045564893,0.00018520126,0.6317342,0.000027433876,0.000037565052,0.000024619329,0.0040079094,0.0000011522927,0.013445654,0.00010712371,0.34977376,0.00019970346],"about_ca_topic_score_codex":0.0015426074,"about_ca_topic_score_gemma":0.0017234687,"teacher_disagreement_score":0.5246275,"about_ca_system_score_codex":0.00014674856,"about_ca_system_score_gemma":0.0005716011,"threshold_uncertainty_score":0.88705367},"labels":[],"label_agreement":null},{"id":"W3200635405","doi":"10.3758/s13428-021-01624-3","title":"Best research practices for using the Implicit Association Test","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":182,"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; McGill University","funders":"Economic and Social Research Council","keywords":"Implicit-association test; Psychology; Association (psychology); Test (biology); Implicit attitude; Social psychology; Selection (genetic algorithm); Cognitive psychology; Applied psychology; Computer science","score_opus":0.8389178653384918,"score_gpt":0.783184058779802,"score_spread":0.05573380655868976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200635405","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":[0.7871206,0.0020913393,0.0069184825,0.062234312,0.0033267175,0.0047884574,0.00009047467,0.00014868601,0.13328096],"genre_scores_gemma":[0.45775422,0.0017683738,0.28642336,0.0008738479,0.011484203,0.0055973954,0.00004467762,0.00021298481,0.23584093],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.98092407,0.01548976,0.00028838732,0.00047642228,0.0015886454,0.0012326877],"domain_scores_gemma":[0.9664055,0.028857421,0.00021804574,0.00042280275,0.0039126715,0.0001835196],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062443584,0.00009482015,0.00020114746,0.0001807924,0.0038899195,0.0005418629,0.0007231757,0.00033278397,0.00046428136],"category_scores_gemma":[0.09847862,0.00007810378,0.0001417845,0.0019524595,0.00068480655,0.00029673218,0.00025671147,0.0012006027,0.000054298867],"study_design_candidate":"not_applicable","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":[0.00009959848,0.0020602131,0.09131938,0.000041008883,0.00010369786,0.00005428095,0.03337426,5.001431e-7,0.43133643,0.06537629,0.036560144,0.3396742],"study_design_scores_gemma":[0.0003869294,0.0003046288,0.013195693,0.000034029068,0.000055672277,0.0000072403614,0.1045388,0.00003968798,0.009424293,0.012644969,0.859166,0.00020200222],"about_ca_topic_score_codex":0.011207193,"about_ca_topic_score_gemma":0.0040094126,"teacher_disagreement_score":0.8226059,"about_ca_system_score_codex":0.0009576843,"about_ca_system_score_gemma":0.0011150991,"threshold_uncertainty_score":0.9974069},"labels":[],"label_agreement":null},{"id":"W3204429926","doi":"10.3758/s13428-021-01659-6","title":"LIVE-streaming 3D images: A neuroscience approach to full-body illusions","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Transcranial Magnetic Stimulation Studies","field":"Neuroscience","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":"Queensland University of Technology; Fonds De La Recherche Scientifique - FNRS; Universität Siegen; Canadian Institute for Advanced Research","keywords":"Illusion; Computer science; Transcranial magnetic stimulation; Set (abstract data type); Neuroscience; Psychology; Stimulation","score_opus":0.4231347299909947,"score_gpt":0.5608453545288526,"score_spread":0.13771062453785793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204429926","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":[0.5902193,0.00035013398,0.37255445,0.0017642393,0.00092669,0.0027489231,0.00013452185,0.0004799799,0.030821757],"genre_scores_gemma":[0.5154797,0.00009072934,0.47870907,0.00043078655,0.00011439675,0.00070912845,0.000002440697,0.000058577254,0.0044051744],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99179524,0.0036510075,0.00042172207,0.00143963,0.0016107459,0.0010816365],"domain_scores_gemma":[0.9953739,0.0026551886,0.000049114988,0.0008994361,0.0005285462,0.0004938055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027935612,0.00025550957,0.0003526047,0.00045688043,0.0011996084,0.00031537985,0.0008352118,0.0000906007,0.00028507528],"category_scores_gemma":[0.012113695,0.00024285713,0.00012992592,0.0034479662,0.0007400085,0.00022680877,0.0010276973,0.00072308205,0.00016556629],"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":[0.00002877835,0.00050519046,0.00036398653,0.00001573354,9.57852e-7,0.00015417827,0.001089446,0.00009373443,0.9464361,0.00044930886,0.000162125,0.050700482],"study_design_scores_gemma":[0.0022042813,0.0013261946,0.44400263,0.00012644658,0.00010596719,0.00065168034,0.0038108467,0.007895052,0.4818514,0.00046296476,0.056108575,0.0014539579],"about_ca_topic_score_codex":0.000080944665,"about_ca_topic_score_gemma":0.000005030121,"teacher_disagreement_score":0.46458468,"about_ca_system_score_codex":0.00009102145,"about_ca_system_score_gemma":0.00025820878,"threshold_uncertainty_score":0.9962077},"labels":[],"label_agreement":null},{"id":"W360559091","doi":"10.3758/s13428-015-0602-3","title":"Norms for name agreement, familiarity, subjective frequency, and imageability for 348 object names in Tunisian Arabic","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":45,"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 Laval; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Orthography; Word lists by frequency; Reading (process); Age of Acquisition; Arabic; Linguistics; Normative; Computer science; Word (group theory); Semantics (computer science); Phonology; Word recognition; Natural language processing; Psychology; Artificial intelligence; Cognition","score_opus":0.3438291449843307,"score_gpt":0.5920910447842678,"score_spread":0.24826189979993707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W360559091","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":[0.9698132,0.00079986936,0.01838396,0.0004294032,0.00064434984,0.0046412996,0.00014909805,0.000060467388,0.005078345],"genre_scores_gemma":[0.6000676,0.000025486139,0.38619763,0.000055904668,0.00013278164,0.008166808,0.000074740245,0.00006531407,0.005213729],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99441546,0.0025004048,0.000578553,0.0009557864,0.0004782157,0.0010715512],"domain_scores_gemma":[0.9958216,0.0022857415,0.00009296511,0.0006779669,0.00073968724,0.00038204074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02076522,0.00026749683,0.00050638424,0.00054998265,0.00022278672,0.00013894559,0.00043028916,0.00023516317,0.000094426134],"category_scores_gemma":[0.0027435364,0.0002341999,0.00012599639,0.000556055,0.00041700198,0.00022195686,0.00019031766,0.0006161473,0.000020510135],"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":[0.00072125683,0.0009590745,0.59818476,0.00014242592,0.00006678191,0.000041344578,0.0224444,3.8628352e-7,0.004286899,0.0031023244,0.0018572602,0.3681931],"study_design_scores_gemma":[0.0042755413,0.0015126895,0.9293894,0.00007516571,0.000038645434,0.00003391476,0.0091390135,0.00011268068,0.0027479974,0.039573707,0.0125625385,0.00053868815],"about_ca_topic_score_codex":0.0033432012,"about_ca_topic_score_gemma":0.00040953688,"teacher_disagreement_score":0.3697456,"about_ca_system_score_codex":0.00053355884,"about_ca_system_score_gemma":0.00037026036,"threshold_uncertainty_score":0.9550395},"labels":[],"label_agreement":null},{"id":"W36973636","doi":"10.3758/s13428-023-02088-3","title":"Obesity among Pff-reserve First Nations, Métis, and Inuit Peoples in Canada’s Provinces: Associated Factors and Secular Trends","year":2012,"lang":"en","type":"dissertation","venue":"Behavior Research Methods","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":2,"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":"Metis; Obesity; Overweight; Demography; Socioeconomic status; Ethnic group; Body mass index; Geography; Odds; Medicine; Gerontology; Population; Political science; Logistic regression; Sociology","score_opus":0.08402551226420661,"score_gpt":0.4493321402713333,"score_spread":0.36530662800712665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36973636","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":[0.9964083,0.0010338086,0.0000010753575,0.00007725701,0.00015578316,0.0013831011,0.0003403007,0.000042600514,0.0005577824],"genre_scores_gemma":[0.99409294,0.0003158643,0.00058671215,0.0000034973107,0.000079005695,0.0003951836,0.0017218413,0.000092230264,0.0027127068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938198,0.0020887502,0.0005226029,0.00081809465,0.0016909587,0.0010598433],"domain_scores_gemma":[0.9953478,0.0027219953,0.00024163144,0.00050104805,0.0005200104,0.0006675081],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003337125,0.0005026242,0.0011072041,0.0011326928,0.00051204325,0.00011562651,0.0002923082,0.00055596646,0.00016308331],"category_scores_gemma":[0.0042789415,0.0004536698,0.0001276323,0.0012187433,0.00021798491,0.0003387421,0.00027746122,0.001990399,0.0000010986942],"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":[0.00004221526,0.002259254,0.98904926,0.0008179875,0.00008426899,0.00007908613,0.002045389,1.2734164e-7,0.0004836948,0.000071108145,0.00017579136,0.004891848],"study_design_scores_gemma":[0.0006693645,0.00018017375,0.991953,0.0005365255,0.00026004852,0.0000038886533,0.003568252,0.00002743492,0.0022106976,0.00005156499,0.00014922948,0.00038982087],"about_ca_topic_score_codex":0.95122695,"about_ca_topic_score_gemma":0.9993877,"teacher_disagreement_score":0.048160724,"about_ca_system_score_codex":0.0027201085,"about_ca_system_score_gemma":0.0031453914,"threshold_uncertainty_score":0.9997915},"labels":[],"label_agreement":null},{"id":"W4200273859","doi":"10.3758/s13428-021-01738-8","title":"Video playback versus live stimuli to assess quantity discrimination in angelfish (Pterophyllum scalare)","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Animal Behavior and Reproduction","field":"Agricultural and Biological Sciences","cited_by":4,"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; Universidad de Oviedo; Ministerio de Economía y Competitividad","keywords":"Stimulus (psychology); Shoal; Communication; Psychology; Cognitive psychology","score_opus":0.5557374849731176,"score_gpt":0.5590784985018049,"score_spread":0.00334101352868732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200273859","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":[0.9974044,0.00012804514,0.00013036252,0.0009088558,0.00051456445,0.0005336603,0.000033762426,0.000050124207,0.0002962522],"genre_scores_gemma":[0.9850506,0.00006517191,0.013595747,0.000022548496,0.00027905806,0.00020231774,0.00008590923,0.0000035570997,0.00069507945],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9955487,0.002035111,0.0003047216,0.00081158266,0.0007230888,0.0005767691],"domain_scores_gemma":[0.9982953,0.00064932177,0.00004174241,0.00019162794,0.0005764468,0.00024555554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003323584,0.0001632157,0.00025458078,0.00007495385,0.00031523575,0.00020077807,0.00033816855,0.00017422234,0.00085722655],"category_scores_gemma":[0.0013341793,0.00007968054,0.00011322443,0.0014178118,0.00012621853,0.00027045087,0.00035748392,0.0005502724,0.00011712248],"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":[0.00014645568,0.00041795927,0.06031576,0.0000075462904,0.0000027884591,0.00007617336,0.00020997532,0.0000016886656,0.69711626,0.00006465933,0.00020680926,0.24143392],"study_design_scores_gemma":[0.00022171359,0.0006040533,0.91748285,0.000029261046,0.00001692806,0.00000829392,0.0028149493,0.000010930225,0.07622008,0.000049228056,0.002347886,0.00019381315],"about_ca_topic_score_codex":0.0020240718,"about_ca_topic_score_gemma":0.0053315754,"teacher_disagreement_score":0.8571671,"about_ca_system_score_codex":0.00019314748,"about_ca_system_score_gemma":0.000042956523,"threshold_uncertainty_score":0.9386029},"labels":[],"label_agreement":null},{"id":"W4200330936","doi":"10.3758/s13428-021-01717-z","title":"PuPl: an open-source tool for processing pupillometry data","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Research Foundation; McMaster University","keywords":"Pupillometry; Open source; Computer science; Human–computer interaction; Psychology; Pupil; Programming language; Neuroscience","score_opus":0.7890012828901644,"score_gpt":0.6870658849593866,"score_spread":0.10193539793077777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200330936","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":[0.25068134,0.00026619493,0.7419556,0.0009847454,0.00060364907,0.002525366,0.00026102547,0.0004268082,0.0022952827],"genre_scores_gemma":[0.15873624,0.000065875785,0.82059294,0.0010699587,0.00033150727,0.0008354731,0.00020529793,0.0001683403,0.01799436],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99267656,0.0035654688,0.00038771183,0.0015547414,0.00096612866,0.00084942003],"domain_scores_gemma":[0.9963477,0.00095300586,0.00008917994,0.0017184797,0.00055761647,0.00033396488],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012386681,0.00020095852,0.00031082018,0.0002803336,0.0012601536,0.0021036202,0.003105812,0.00016717712,0.0008300283],"category_scores_gemma":[0.010213526,0.00019070903,0.00004765342,0.0017806814,0.00024100562,0.0017294895,0.0025817098,0.0006626646,0.000053829423],"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":[0.00003429225,0.0003227347,0.000036624682,0.00004750794,6.967783e-7,0.000018505809,0.0001673808,5.82182e-7,0.5400791,0.000266225,0.0003628727,0.45866346],"study_design_scores_gemma":[0.0008153876,0.00041685335,0.00059510476,0.000073817726,0.0000242672,0.0001190581,0.0010331162,0.006005194,0.85038084,0.0019493956,0.13817269,0.00041429498],"about_ca_topic_score_codex":0.000022608641,"about_ca_topic_score_gemma":0.000008243903,"teacher_disagreement_score":0.45824915,"about_ca_system_score_codex":0.000078168014,"about_ca_system_score_gemma":0.00072733173,"threshold_uncertainty_score":0.9989323},"labels":[],"label_agreement":null},{"id":"W4200424524","doi":"10.3758/s13428-021-01735-x","title":"Evaluating the efficacy of an iPad® app in determining a single bout of exercise benefit to executive function","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Smartphone app; Physical medicine and rehabilitation; Session (web analytics); Equivalence (formal languages); Stroop effect; Physical therapy; Audiology; Cognition; Medicine; Computer science; Neuroscience; Mathematics","score_opus":0.7331761601180892,"score_gpt":0.6604872587517003,"score_spread":0.07268890136638884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200424524","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":[0.9984383,0.0001079046,0.000117304924,0.0001397607,0.00021105987,0.00076859805,0.000010548735,0.000021417283,0.00018509066],"genre_scores_gemma":[0.9828934,0.000016227694,0.016098859,0.00004073514,0.000025348072,0.0002828406,0.0000014146156,0.000020966934,0.000620209],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99498427,0.0026063726,0.00047411214,0.0006491507,0.0007391227,0.00054699497],"domain_scores_gemma":[0.99697185,0.0018859707,0.00011542997,0.0005720471,0.0003524995,0.00010223351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046108146,0.00014699427,0.00035843556,0.00027341826,0.00023803205,0.000033196884,0.000425544,0.00007930249,0.000040712304],"category_scores_gemma":[0.0033007346,0.000108866945,0.00009567563,0.0015581881,0.00041401034,0.0001465414,0.00044871034,0.00050805835,0.000005018326],"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":[0.00021825508,0.0005411198,0.0029069826,0.000010275757,0.0000011385212,0.00002972524,0.0010332018,0.000013191792,0.6691397,0.00001729584,0.0000046832183,0.32608443],"study_design_scores_gemma":[0.0004985429,0.0014695995,0.10627238,0.00011692582,0.000036014237,0.0000143450325,0.0017611206,0.000046697533,0.88936424,0.0002867765,0.000028284026,0.00010509029],"about_ca_topic_score_codex":0.00011170474,"about_ca_topic_score_gemma":0.00005552169,"teacher_disagreement_score":0.32597932,"about_ca_system_score_codex":0.000055395303,"about_ca_system_score_gemma":0.00007707486,"threshold_uncertainty_score":0.4439465},"labels":[],"label_agreement":null},{"id":"W4200504981","doi":"10.3758/s13428-021-01753-9","title":"The Tapping Assay: A Simple Method to Induce Fear Responses in Zebrafish","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","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":"Canadian Celiac Association; University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Zebrafish; Anxiety; Stimulus (psychology); Neuroscience; Psychology; Computer science; Cognitive psychology; Biology; Psychiatry","score_opus":0.17854596067763234,"score_gpt":0.5785484567686334,"score_spread":0.4000024960910011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200504981","genre_codex":"empirical","genre_gemma":"methods","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":[0.729047,0.001769168,0.23982541,0.022756852,0.00015926691,0.0029569103,0.00011559932,0.00006274356,0.0033070534],"genre_scores_gemma":[0.20902708,0.00043937546,0.77168643,0.0010764063,0.0005485275,0.006084658,0.00020442181,0.00015256344,0.010780512],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9861196,0.010370281,0.00042430373,0.0008703747,0.001030334,0.0011850738],"domain_scores_gemma":[0.9945622,0.0027449327,0.00004380973,0.0013089068,0.0007593962,0.000580734],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026332181,0.00017701711,0.00023051388,0.0002745365,0.0005287172,0.00023762787,0.000968735,0.00026247435,0.000097325654],"category_scores_gemma":[0.026635284,0.0001479801,0.000119295786,0.0021017278,0.0003309059,0.000008310566,0.0014596594,0.0009318162,0.000052751137],"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":[0.000095663294,0.0001376016,0.0006074177,0.0000064847395,0.000013872863,0.000047236208,0.000055829783,0.0000011167286,0.7829066,0.00028670696,0.0075812885,0.20826018],"study_design_scores_gemma":[0.00027511836,0.00014673645,0.01857656,0.000013142784,0.0000043171813,0.000024025778,0.0006489621,0.000032579013,0.51312286,0.00066511123,0.4663448,0.00014580549],"about_ca_topic_score_codex":0.00025295463,"about_ca_topic_score_gemma":0.00053569366,"teacher_disagreement_score":0.53186107,"about_ca_system_score_codex":0.0001348214,"about_ca_system_score_gemma":0.0011543015,"threshold_uncertainty_score":0.9815638},"labels":[],"label_agreement":null},{"id":"W4200624835","doi":"10.3758/s13428-021-01740-0","title":"Valence norms for 3,600 English words collected during the COVID-19 pandemic: Effects of age and the pandemic","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aging and Gerontology Research","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Valence (chemistry); Pandemic; Emotional valence; Psychology; Coronavirus disease 2019 (COVID-19); Young adult; Stressor; Developmental psychology; Cognition; Demography; Clinical psychology; Medicine; Psychiatry; Disease; Sociology; Infectious disease (medical specialty)","score_opus":0.31449635730409486,"score_gpt":0.59901345804642,"score_spread":0.28451710074232517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200624835","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":[0.9828225,0.0056349193,0.006791674,0.00066772144,0.0004789979,0.0025310735,0.000037036036,0.000100385376,0.0009357392],"genre_scores_gemma":[0.9452946,0.0006430211,0.008157065,0.0002396929,0.00030564042,0.005992702,0.000020794141,0.00007566208,0.03927079],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9847728,0.012529765,0.00041454713,0.0006704045,0.00060361496,0.0010088814],"domain_scores_gemma":[0.9698236,0.028134763,0.000101723286,0.001029416,0.0006279113,0.0002825974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017406253,0.00020180021,0.00052481296,0.00021105992,0.0009533585,0.00008686737,0.0007900886,0.00028964016,0.00023083686],"category_scores_gemma":[0.01892478,0.00011880449,0.00017429635,0.0010668247,0.002401868,0.00005493775,0.0004895673,0.0014419025,0.000004618942],"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":[0.0047555896,0.00078649685,0.73376137,0.0014564035,0.00056006794,0.000993877,0.10278448,0.0000027541146,0.034001958,0.0044525987,0.006517763,0.109926656],"study_design_scores_gemma":[0.026935462,0.00092313206,0.88329,0.0001933577,0.00044544227,0.0010717111,0.030720651,0.00010575454,0.010737366,0.0055138753,0.039248575,0.0008146808],"about_ca_topic_score_codex":0.00055570266,"about_ca_topic_score_gemma":0.00039313338,"teacher_disagreement_score":0.14952864,"about_ca_system_score_codex":0.00015661916,"about_ca_system_score_gemma":0.00044879664,"threshold_uncertainty_score":0.98933923},"labels":[],"label_agreement":null},{"id":"W4210525855","doi":"10.3758/s13428-021-01774-4","title":"Contrasting domain-general and domain-specific accounts in cognitive neuropsychology: An outline of a new approach with developmental prosopagnosia as a case","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","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":"University of British Columbia","funders":"Danmarks Frie Forskningsfond","keywords":"Neuropsychology; Psychology; Cognitive psychology; Cognition; Cognitive neuropsychology; Context (archaeology); Domain (mathematical analysis); Developmental psychology; Mechanism (biology); Cognitive science; Neuroscience; Epistemology","score_opus":0.4460085892567069,"score_gpt":0.549792555383548,"score_spread":0.1037839661268411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210525855","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":[0.99474674,0.000019522366,0.0021830422,0.000074131254,0.000044137385,0.0017109773,0.00007103706,0.000032034393,0.0011183597],"genre_scores_gemma":[0.86722535,0.000020081588,0.13142614,0.00014689613,0.00003661732,0.00082680513,0.000025144413,0.000037756374,0.00025519734],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9928183,0.004810213,0.00034630092,0.0008126497,0.00068897335,0.00052354776],"domain_scores_gemma":[0.9987865,0.00058500015,0.00009366964,0.00017199092,0.00011443442,0.000248392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039204163,0.00018290742,0.0002729817,0.0005112769,0.00048419932,0.00008303808,0.00021133758,0.00006362954,0.0006715246],"category_scores_gemma":[0.0002531786,0.0001699206,0.000030654002,0.0010634254,0.00046263993,0.00022019635,0.0002222511,0.0008954031,0.000007407879],"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":[0.0014982875,0.0015042879,0.017144771,0.000022587372,0.000004528533,0.004032811,0.008757357,0.0000042587117,0.8207422,0.00028967526,0.00005170264,0.14594753],"study_design_scores_gemma":[0.033457596,0.009637683,0.53499335,0.0002814612,0.00007306002,0.1289733,0.16786063,0.0006678418,0.110031255,0.002445146,0.009248014,0.002330648],"about_ca_topic_score_codex":0.00022181476,"about_ca_topic_score_gemma":0.00004698422,"teacher_disagreement_score":0.71071094,"about_ca_system_score_codex":0.00012510887,"about_ca_system_score_gemma":0.00023895237,"threshold_uncertainty_score":0.73527235},"labels":[],"label_agreement":null},{"id":"W4210535774","doi":"10.3758/s13428-021-01771-7","title":"A Novel Approach for Developing Efficient and Convenient Short Assessments to Approximate a Long Assessment","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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 Toronto","funders":"","keywords":"Computer science; Statistics; Mathematics","score_opus":0.6484728603350225,"score_gpt":0.7123271134612921,"score_spread":0.06385425312626958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210535774","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":[0.22716157,0.0001678998,0.76052547,0.00042945077,0.0004957061,0.008365999,0.0001471033,0.00006522739,0.002641586],"genre_scores_gemma":[0.111790635,0.000006140253,0.84722537,0.00020114028,0.000078689,0.038256433,0.000103797836,0.00008612318,0.0022516784],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9905655,0.003797945,0.00063815893,0.001255032,0.0019233369,0.0018200427],"domain_scores_gemma":[0.9970295,0.0010672504,0.00007383183,0.00080739224,0.00034871363,0.0006733245],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.025649978,0.00027270737,0.0004601449,0.0008235885,0.0014193585,0.00015105943,0.0007896144,0.00010755742,0.00036738542],"category_scores_gemma":[0.00023204724,0.0002783136,0.00009815225,0.001151523,0.00019233559,0.000055139182,0.0019926103,0.0013225193,0.0000060199436],"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":[0.0012209411,0.007634428,0.024871493,0.0010418826,0.00020029281,0.00016498743,0.005136277,0.00022741708,0.033019047,0.04147242,0.002725711,0.8822851],"study_design_scores_gemma":[0.01488484,0.013925121,0.69537675,0.00022328387,0.00023746378,0.0011495065,0.054293275,0.08729896,0.009134689,0.00075903436,0.11920148,0.0035156074],"about_ca_topic_score_codex":0.00028112158,"about_ca_topic_score_gemma":0.0000063305115,"teacher_disagreement_score":0.8787695,"about_ca_system_score_codex":0.0017381612,"about_ca_system_score_gemma":0.00062875135,"threshold_uncertainty_score":0.9999669},"labels":[],"label_agreement":null},{"id":"W4210546055","doi":"10.3758/s13428-022-01798-4","title":"Quantifying children’s sensorimotor experience: Child body–object interaction ratings for 3359 English words","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":19,"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":"Referent; Psychology; Embodied cognition; Cognitive psychology; Age of Acquisition; Perspective (graphical); Cognition; Object (grammar); Valence (chemistry); Developmental psychology; Linguistics; Computer science; Artificial intelligence","score_opus":0.36302458373415386,"score_gpt":0.6036297274374163,"score_spread":0.24060514370326241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210546055","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":[0.95137924,0.00012121562,0.03728207,0.00033649264,0.0046429634,0.0026830514,0.000071338305,0.00031997354,0.0031636818],"genre_scores_gemma":[0.9618177,0.000011499363,0.024407858,0.00018613772,0.00086260674,0.0076673343,0.0002724618,0.00009475266,0.004679679],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99321395,0.0040056487,0.0005519699,0.00074262597,0.0008179031,0.0006679196],"domain_scores_gemma":[0.997512,0.0009311022,0.0002133124,0.00058897265,0.000592898,0.00016174164],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061655124,0.00020637634,0.00027231962,0.00058327796,0.0019732793,0.00016995861,0.0004265188,0.00013680782,0.008045381],"category_scores_gemma":[0.0019093575,0.00022599376,0.00017392657,0.0010993282,0.0001242669,0.0003465718,0.00022497553,0.0012366158,0.000032131913],"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":[0.0015552659,0.0028372183,0.3830872,0.00006647823,0.00019193106,0.000033689543,0.11211669,0.00014890824,0.04855285,0.008431089,0.029328614,0.41365007],"study_design_scores_gemma":[0.004989942,0.0016265797,0.47979885,0.000045349316,0.00007361118,0.00019698631,0.108207405,0.0023110732,0.024362797,0.000103045306,0.37720352,0.0010808249],"about_ca_topic_score_codex":0.00031382055,"about_ca_topic_score_gemma":0.000011761022,"teacher_disagreement_score":0.41256925,"about_ca_system_score_codex":0.00052589894,"about_ca_system_score_gemma":0.00009749263,"threshold_uncertainty_score":0.999326},"labels":[],"label_agreement":null},{"id":"W4210746747","doi":"10.3758/s13428-021-01732-0","title":"Visual and semantic similarity norms for a photographic image stimulus set containing recognizable objects, animals and scenes","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":9,"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":"National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Multidimensional scaling; Semantic similarity; Similarity (geometry); Artificial intelligence; Computer science; Pattern recognition (psychology); Set (abstract data type); Categorization; Stimulus (psychology); Visual perception; Cognitive psychology; Natural language processing; Psychology; Image (mathematics); Perception; Machine learning","score_opus":0.22452910133432574,"score_gpt":0.5455105804287299,"score_spread":0.32098147909440417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210746747","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":[0.7658197,0.00035990402,0.23204023,0.0001869546,0.0002025365,0.0011713743,0.000025071962,0.00013467117,0.000059511167],"genre_scores_gemma":[0.8377677,0.000056434328,0.16105808,0.000057061196,0.000026782454,0.00086956244,0.0000072404596,0.000021011334,0.00013608045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99577093,0.0020062784,0.0002949376,0.0007227042,0.000597817,0.00060734863],"domain_scores_gemma":[0.9983499,0.0007527481,0.00007755986,0.00029450277,0.00030745438,0.00021784443],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010252196,0.0001627708,0.00027700397,0.0005637918,0.0014928726,0.00045318762,0.00039537204,0.00006427114,0.00004836096],"category_scores_gemma":[0.0005162165,0.00015943412,0.000080628466,0.0011745351,0.00020048165,0.0003815971,0.00095451786,0.00053055614,0.0000014150799],"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":[0.00038861902,0.0006361789,0.02919573,0.00028173384,0.000049655715,0.00011347647,0.0038784936,0.000007330712,0.4564365,0.0013287098,0.00024477014,0.5074388],"study_design_scores_gemma":[0.008512967,0.019716293,0.21797721,0.00015045241,0.00019649377,0.0009833947,0.016767588,0.5802059,0.12693217,0.018338244,0.007946252,0.0022730092],"about_ca_topic_score_codex":0.00028269747,"about_ca_topic_score_gemma":0.000044680142,"teacher_disagreement_score":0.5801986,"about_ca_system_score_codex":0.00006507765,"about_ca_system_score_gemma":0.0001032828,"threshold_uncertainty_score":0.99980706},"labels":[],"label_agreement":null},{"id":"W4210813972","doi":"10.3758/s13428-021-01772-6","title":"Expanding horizons of cross-linguistic research on reading: The Multilingual Eye-movement Corpus (MECO)","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":149,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit Gent; Saint Petersburg State University; Israel Science Foundation; Fonds Wetenschappelijk Onderzoek; Eesti Teadusagentuur","keywords":"Reading (process); Eye movement; Computer science; Linguistics; Contrast (vision); Eye tracking; Word (group theory); Cognitive psychology; Empirical research; Diversity (politics); Psychology; Artificial intelligence; Sociology","score_opus":0.42039436511020484,"score_gpt":0.6630701278381799,"score_spread":0.24267576272797503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210813972","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":[0.97445124,0.00041067618,0.0002456634,0.00022607474,0.0022747624,0.0016019603,0.00007697617,0.00007441071,0.02063825],"genre_scores_gemma":[0.9568652,0.000020509051,0.00862473,0.000053748772,0.0003090437,0.0032823405,0.00003254063,0.00008815447,0.030723758],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9806746,0.012936928,0.0008973368,0.001011994,0.002855756,0.0016233433],"domain_scores_gemma":[0.98943204,0.0075311107,0.00018549382,0.001538994,0.0010346258,0.0002777511],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.039212998,0.00026604297,0.0004312651,0.001214162,0.0024842757,0.00022823019,0.0015537795,0.00012821378,0.002796064],"category_scores_gemma":[0.003635402,0.0002115334,0.00018881922,0.00195361,0.00089390326,0.000051685132,0.0011549745,0.0032327098,0.00010760986],"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":[0.0022154807,0.004371646,0.18517356,0.00011104489,0.00025574892,0.0011151866,0.08762323,0.00011830684,0.09506823,0.0436998,0.008205941,0.5720418],"study_design_scores_gemma":[0.0044348757,0.007457343,0.53197706,0.00028583806,0.00009421816,0.00008804435,0.053301513,0.00020580199,0.10676156,0.006724412,0.28740028,0.0012690441],"about_ca_topic_score_codex":0.00088447524,"about_ca_topic_score_gemma":0.000007915012,"teacher_disagreement_score":0.57077277,"about_ca_system_score_codex":0.00076446234,"about_ca_system_score_gemma":0.00036553104,"threshold_uncertainty_score":0.9990669},"labels":[],"label_agreement":null},{"id":"W4212782570","doi":"10.3758/s13428-020-01506-0","title":"Correction to: Editorial: Into a new decade","year":2022,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Academic Publishing and Open Access","field":"Decision Sciences","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":"Computer science; Information retrieval; Data science","score_opus":0.44132939814837524,"score_gpt":0.6685985257114079,"score_spread":0.22726912756303264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212782570","genre_codex":"editorial","genre_gemma":"other","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":[0.000051898474,0.0013611404,0.012390226,0.0035214657,0.9152198,0.0014952414,0.00005460113,0.0001927329,0.06571289],"genre_scores_gemma":[0.000009260454,0.0001485917,0.03366682,0.00021685126,0.14410506,0.00094802125,0.00014119694,0.00013253975,0.8206316],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9537238,0.019322075,0.0019502408,0.002996882,0.020219896,0.0017871036],"domain_scores_gemma":[0.9675397,0.022121383,0.000776039,0.003820868,0.0033944305,0.0023475573],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.13689633,0.00055402867,0.0012295994,0.00423806,0.001682899,0.0059582265,0.014649903,0.0016417812,0.010479308],"category_scores_gemma":[0.2622026,0.00046553125,0.00047972234,0.010283158,0.0002795491,0.0015706184,0.0077369437,0.018997913,0.001075446],"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":[0.00004773831,0.000048853904,0.00014160362,0.0000038016815,0.000008457819,0.000020121885,0.0007415478,0.0000036116674,0.00011270997,0.000023142316,0.6148106,0.38403782],"study_design_scores_gemma":[0.00019303049,0.00024767747,0.0010971152,0.0000741865,0.000032514803,0.000017825869,0.0015955775,0.00006184143,0.00017297942,0.0066682873,0.9893351,0.0005038173],"about_ca_topic_score_codex":0.015148556,"about_ca_topic_score_gemma":0.000537979,"teacher_disagreement_score":0.7711147,"about_ca_system_score_codex":0.0016842519,"about_ca_system_score_gemma":0.0071372055,"threshold_uncertainty_score":0.99977964},"labels":[],"label_agreement":null},{"id":"W4213112533","doi":"10.3758/s13428-022-01801-y","title":"Machine learning to detect invalid text responses: Validation and comparison to existing detection methods","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text and Document Classification Technologies","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Coding (social sciences); Word (group theory); Machine learning; Code (set theory); Quality (philosophy); Information retrieval; Linguistics; Statistics","score_opus":0.421437191862916,"score_gpt":0.5856823952146699,"score_spread":0.1642452033517539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213112533","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":[0.11762687,0.00022184236,0.87911755,0.0011783997,0.00019457252,0.00089472247,0.0000032327853,0.00057422306,0.00018858953],"genre_scores_gemma":[0.3259832,0.0000086726495,0.67180336,0.00003296527,0.000014233938,0.0011677729,0.0000027276924,0.00001921232,0.0009678506],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98662406,0.0105249155,0.00047195688,0.00087304873,0.00090858527,0.00059740845],"domain_scores_gemma":[0.9960991,0.0024801071,0.0001304137,0.00081301614,0.00023128538,0.0002460471],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.022758607,0.00018515177,0.00028483922,0.0015162235,0.0016540632,0.0005400796,0.001253708,0.000079806916,0.00007271101],"category_scores_gemma":[0.0065024476,0.00019430261,0.000056872355,0.0031227013,0.00008473345,0.0003389998,0.0029649267,0.0011505609,0.000025611334],"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":[0.000046855792,0.000032360185,0.0010421448,0.000006853205,0.0000034235234,0.0000036520003,0.0010968142,0.00012470201,0.27026817,0.0007376681,0.000046255413,0.7265911],"study_design_scores_gemma":[0.00037417686,0.0017904832,0.013482491,0.000017407137,0.000015007157,0.000054232885,0.0031304164,0.020734888,0.8468761,0.0029430813,0.11010959,0.00047215473],"about_ca_topic_score_codex":0.0002259169,"about_ca_topic_score_gemma":0.000011922558,"teacher_disagreement_score":0.7261189,"about_ca_system_score_codex":0.0003834141,"about_ca_system_score_gemma":0.00008714058,"threshold_uncertainty_score":0.99964565},"labels":[],"label_agreement":null},{"id":"W4220858191","doi":"10.3758/s13428-022-01803-w","title":"Audio-Tokens: A toolbox for rating, sorting and comparing audio samples in the browser","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","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":"Centre for Research on Brain Language and Music; McGill University; Montreal Neurological Institute and Hospital","funders":"Canada First Research Excellence Fund; Centre for Research on Brain, Language and Music; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Toolbox; Computer science; JavaScript; Feature (linguistics); Plug-in; Categorical variable; Speech recognition; Artificial intelligence; Machine learning; World Wide Web","score_opus":0.6559392404991495,"score_gpt":0.5947403805143804,"score_spread":0.06119885998476915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220858191","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":[0.99473834,0.000026594333,0.0025808762,0.00047970054,0.00019749414,0.0013241207,0.000012092507,0.00003833932,0.00060243736],"genre_scores_gemma":[0.9854759,0.000017282826,0.011353882,0.00056959887,0.00007524547,0.002127377,0.0000025891204,0.000020078032,0.00035804507],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9933837,0.004051071,0.00031787675,0.0006534858,0.00088371674,0.00071016373],"domain_scores_gemma":[0.9972133,0.002202558,0.00008108557,0.00037867358,0.000047250844,0.00007713148],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0127406,0.00012127744,0.00019285608,0.00029175123,0.0017019669,0.00024802278,0.00067209004,0.000029727655,0.000074469004],"category_scores_gemma":[0.0041931705,0.00009779494,0.00006388291,0.0009586249,0.00034301047,0.0002512611,0.00047735305,0.0007663903,0.0000022490271],"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":[0.00003411865,0.000119513206,0.0052921055,0.00001455287,3.2310936e-7,0.000023296643,0.0028623575,0.000025890067,0.9509806,0.0010148388,0.00046134368,0.03917108],"study_design_scores_gemma":[0.004506177,0.0026026494,0.5341905,0.00011487214,0.00006671568,0.00087332557,0.03999537,0.021149496,0.2757827,0.008788831,0.11046636,0.001462995],"about_ca_topic_score_codex":0.00019621107,"about_ca_topic_score_gemma":0.000057152753,"teacher_disagreement_score":0.6751979,"about_ca_system_score_codex":0.00009672021,"about_ca_system_score_gemma":0.00010027222,"threshold_uncertainty_score":0.99959767},"labels":[],"label_agreement":null},{"id":"W4221022654","doi":"10.3758/s13428-022-01810-x","title":"Quantifying social semantics: An inclusive definition of socialness and ratings for 8388 English words","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":70,"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":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Mitacs; British Psychological Society; UK Research and Innovation","keywords":"Concreteness; Noun; Psychology; Cognitive psychology; Semantics (computer science); Meaning (existential); Computer science; Natural language processing; Linguistics","score_opus":0.5543549710857866,"score_gpt":0.6303453224183189,"score_spread":0.07599035133253229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221022654","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":[0.92588186,0.0000655535,0.07052936,0.0004437384,0.0007692877,0.0010748922,0.00009756264,0.00007158834,0.0010661416],"genre_scores_gemma":[0.9445464,0.0000053343333,0.053265236,0.00006176478,0.00029171482,0.0013090988,0.0001832111,0.000039516446,0.0002977493],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99489444,0.0036246951,0.00035256485,0.00033073494,0.0004881239,0.0003094144],"domain_scores_gemma":[0.9979435,0.0008312539,0.0001884318,0.00017323134,0.00079683744,0.00006674053],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073947916,0.00009803993,0.00022335588,0.00029893877,0.0015448241,0.00005088829,0.00018195936,0.00011571374,0.0010160211],"category_scores_gemma":[0.00086954475,0.00011445825,0.000064064276,0.0006005135,0.00018904188,0.00018215746,0.00021000052,0.0004298153,0.0000013317621],"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":[0.0006448962,0.0014993008,0.051541235,0.00016343949,0.00007742399,0.0000105356985,0.18695198,0.000006827384,0.04490285,0.3022763,0.0024726107,0.4094526],"study_design_scores_gemma":[0.00817755,0.0029068426,0.391905,0.000042734708,0.00027012842,0.000031382206,0.5126026,0.0021770447,0.010496011,0.03160951,0.038605936,0.0011752173],"about_ca_topic_score_codex":0.00014676213,"about_ca_topic_score_gemma":0.00002802353,"teacher_disagreement_score":0.4082774,"about_ca_system_score_codex":0.00015619383,"about_ca_system_score_gemma":0.00013285132,"threshold_uncertainty_score":0.9998972},"labels":[],"label_agreement":null},{"id":"W4224263986","doi":"10.3758/s13428-022-01845-0","title":"IAT faking indices revisited: Aspects of replicability and differential validity","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":13,"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":"Psychology; Context (archaeology); Block (permutation group theory); Task (project management); Cognitive psychology; Social psychology; Mathematics","score_opus":0.5770403301936822,"score_gpt":0.6674394156831788,"score_spread":0.0903990854894966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224263986","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":[0.9928244,0.0006685185,0.00044477452,0.00014227425,0.00041580255,0.0009581499,0.00015601575,0.000052270454,0.004337818],"genre_scores_gemma":[0.9937936,0.00001553893,0.0043169213,0.000017914546,0.00006219498,0.0009826714,0.000029921384,0.000025662632,0.00075558433],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9884724,0.008904747,0.00060684566,0.0006704624,0.00071182975,0.00063368765],"domain_scores_gemma":[0.9976967,0.00073533005,0.00019030704,0.00092065043,0.00019034678,0.00026669534],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010310573,0.00014170879,0.00037714455,0.00041673804,0.0006918269,0.000035978035,0.00044584816,0.0001108214,0.011800964],"category_scores_gemma":[0.00039058216,0.00014038917,0.00017949492,0.00072594313,0.00036276018,0.00008353072,0.00075976114,0.0013274266,0.000011070055],"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":[0.0003885037,0.0029428778,0.3441054,0.00016043366,0.000030343872,0.00006720273,0.0019443925,1.06833696e-7,0.01885657,0.017877579,0.0014781392,0.61214846],"study_design_scores_gemma":[0.0005836378,0.0013508408,0.982882,0.000027493501,0.0000577998,0.000041963915,0.0015286788,0.0000054271186,0.002132367,0.0013681239,0.00986217,0.0001594682],"about_ca_topic_score_codex":0.0016932766,"about_ca_topic_score_gemma":0.000029629522,"teacher_disagreement_score":0.63877666,"about_ca_system_score_codex":0.00015393308,"about_ca_system_score_gemma":0.0000880648,"threshold_uncertainty_score":0.98910236},"labels":[],"label_agreement":null},{"id":"W4225015069","doi":"10.3758/s13428-022-01861-0","title":"Accuracy of paper-and-pencil systematic observation versus computer-aided systems","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","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":"Brock University","funders":"Universidad Autónoma de Madrid; University of Auckland","keywords":"Pencil (optics); Computer science; Computer-aided; Computer graphics (images); Artificial intelligence; Programming language; Engineering","score_opus":0.8223134969967072,"score_gpt":0.6146735580251322,"score_spread":0.20763993897157496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225015069","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":[0.98160595,0.008158593,0.0012122316,0.00026880702,0.0034218202,0.0030489746,0.00006361832,0.000115667855,0.0021043168],"genre_scores_gemma":[0.977938,0.00009881136,0.013672267,0.000048696424,0.0001454807,0.0061712773,0.000026499298,0.00004058298,0.0018583905],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9877293,0.009330288,0.00077926234,0.000578702,0.0009989707,0.00058343814],"domain_scores_gemma":[0.9952277,0.0033054324,0.0002800875,0.00070226757,0.00032968904,0.00015480992],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0103460485,0.00020689277,0.00068184925,0.00021567062,0.00062525633,0.000059117057,0.0006050377,0.000118092925,0.0016501973],"category_scores_gemma":[0.0005231645,0.00016650482,0.00013257483,0.00088786456,0.00027889368,0.00010875928,0.0006593769,0.0008127484,0.0000402308],"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":[0.0028489917,0.0058868225,0.034085795,0.0073788296,0.00060071563,0.00053160416,0.01446068,0.000042794276,0.04735267,0.037909564,0.009913368,0.8389882],"study_design_scores_gemma":[0.0066795223,0.008877145,0.92509407,0.0008291426,0.0005658651,0.00023278249,0.032747805,0.00026605217,0.00030874045,0.0005383539,0.022742381,0.001118167],"about_ca_topic_score_codex":0.0019227043,"about_ca_topic_score_gemma":0.00000695771,"teacher_disagreement_score":0.89100826,"about_ca_system_score_codex":0.00015448702,"about_ca_system_score_gemma":0.00003534409,"threshold_uncertainty_score":0.99926245},"labels":[],"label_agreement":null},{"id":"W4225749806","doi":"10.3758/s13428-021-01762-8","title":"RETRACTED ARTICLE: Eye tracking: empirical foundations for a minimal reporting guideline","year":2022,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":163,"is_retracted":true,"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; SR Research (Canada)","funders":"National Eye Institute; National Cancer Institute; National Institute for Health and Care Research","keywords":"Guideline; Eye tracking; Foundation (evidence); Empirical research; Computer science; Empirical evidence; Quality (philosophy); Gaze; Tracking (education); Eye movement; Artificial intelligence; Psychology; Medicine; Statistics; Political science; Mathematics","score_opus":0.7737194927129117,"score_gpt":0.7106257387479584,"score_spread":0.06309375396495331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225749806","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":[0.000060055296,0.49598783,0.49885815,0.0007186715,0.0006407332,0.0026434108,0.000041608248,0.0007505485,0.00029899616],"genre_scores_gemma":[0.0000109869,0.23412877,0.7603918,0.000023562072,0.00022744697,0.0043065306,0.00013968424,0.00008970567,0.00068157417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874944,0.0046117553,0.0035880415,0.0016928335,0.0012599286,0.0013530483],"domain_scores_gemma":[0.98905987,0.0055762124,0.0019909365,0.002129938,0.00095525896,0.0002878018],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038080726,0.0004710818,0.0017750757,0.0013138835,0.0011271426,0.0005156105,0.0028799612,0.000715978,0.00023050871],"category_scores_gemma":[0.035214268,0.0004239097,0.00089134305,0.003730249,0.00032388672,0.0002770353,0.0014883527,0.0039396994,0.00002400337],"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":[0.0000031692257,0.00030610905,0.00005932039,0.0005429137,0.000038275655,0.00016153975,0.00007337592,1.888087e-7,0.000056319197,0.00091925095,0.0026747917,0.99516475],"study_design_scores_gemma":[0.0001611763,0.00028035403,0.00029018582,0.0004113384,0.00019225178,0.00020156657,0.00005110646,0.0005668189,0.000048333015,0.00059896114,0.9967848,0.00041309162],"about_ca_topic_score_codex":0.000026560827,"about_ca_topic_score_gemma":0.000004294611,"teacher_disagreement_score":0.99475163,"about_ca_system_score_codex":0.0006152037,"about_ca_system_score_gemma":0.0017123179,"threshold_uncertainty_score":0.99982125},"labels":[],"label_agreement":null},{"id":"W4226366257","doi":"10.3758/s13428-022-01858-9","title":"Waiting for baseline stability in single-case designs: Is it worth the time and effort?","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","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":"Institut universitaire en santé mentale de Montréal; Université de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"","keywords":"Baseline (sea); Computer science; Classifier (UML); Stability (learning theory); Machine learning; Support vector machine; Multiple baseline design; Monte Carlo method; Artificial intelligence; Graph; Statistics; Mathematics; Psychology; Theoretical computer science","score_opus":0.872368813169848,"score_gpt":0.6139927190547214,"score_spread":0.25837609411512663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226366257","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":[0.9912104,0.0010937519,0.0006670975,0.0032897773,0.00020011837,0.002214102,0.00019630035,0.000042387554,0.0010860929],"genre_scores_gemma":[0.9646951,0.000019121453,0.023056576,0.00066675904,0.00013031362,0.0075900643,0.000025113746,0.00005019478,0.0037667819],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9913763,0.006081388,0.00050273153,0.0007493855,0.00043315135,0.0008570656],"domain_scores_gemma":[0.994687,0.004386977,0.00007981452,0.00055092655,0.00015310386,0.00014218657],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02498,0.0001983757,0.00034708192,0.0001557413,0.0011484061,0.00006297535,0.00038079594,0.00010369947,0.010402135],"category_scores_gemma":[0.0005959888,0.00013811105,0.0001225698,0.0007765032,0.00046767632,0.000053352924,0.00054469437,0.0010807309,0.000021917676],"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":[0.00070639944,0.0021507384,0.05801959,0.000020355255,0.000028845212,0.000821947,0.0072086006,0.0000010680656,0.00788283,0.00023619333,0.008135989,0.9147875],"study_design_scores_gemma":[0.01076363,0.011582694,0.4670018,0.00009181414,0.00047775308,0.0032266206,0.098547496,0.001531893,0.006106921,0.0069580926,0.39113894,0.0025723514],"about_ca_topic_score_codex":0.00070197723,"about_ca_topic_score_gemma":0.00010021999,"teacher_disagreement_score":0.9122151,"about_ca_system_score_codex":0.000106661726,"about_ca_system_score_gemma":0.00002679763,"threshold_uncertainty_score":0.9905025},"labels":[],"label_agreement":null},{"id":"W4226435591","doi":"10.3758/s13428-022-02029-6","title":"Shennong: A Python toolbox for audio speech features extraction","year":2023,"lang":"en","type":"preprint","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","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":"Agence Nationale de la Recherche; Institut national de recherche en informatique et en automatique (INRIA); Canadian Institute for Advanced Research; Facebook","keywords":"Computer science; Python (programming language); Speech recognition; Toolbox; Normalization (sociology); Software; Scripting language; Mel-frequency cepstrum; Speech processing; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction; Programming language","score_opus":0.4835932963510312,"score_gpt":0.6236894237901746,"score_spread":0.14009612743914335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226435591","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":[0.0069643892,0.0010511251,0.98157877,0.0020584753,0.0034735603,0.0026784933,0.000045897417,0.0011263497,0.0010229383],"genre_scores_gemma":[0.0018385708,0.00015302234,0.9804587,0.00005135575,0.0009346813,0.0029765102,0.00006354227,0.00013127351,0.013392369],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99213064,0.001926893,0.00064633787,0.0020403082,0.0017157417,0.0015400994],"domain_scores_gemma":[0.9936434,0.0022490637,0.00029330992,0.002191597,0.0012142477,0.00040840465],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016809605,0.00050559227,0.0006870389,0.001290686,0.0007346637,0.002109948,0.0034091945,0.00082680705,0.000032551256],"category_scores_gemma":[0.0027320706,0.0004887731,0.00046677413,0.0014469393,0.0001966139,0.0005971703,0.0029448604,0.0032656216,0.00008845948],"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":[0.000041519907,0.0001783822,0.0002292898,0.0003659393,0.00003480497,0.00020482267,0.00044091608,0.000020529136,0.06622407,0.0004739895,0.012585652,0.91920006],"study_design_scores_gemma":[0.00086773874,0.00042834808,0.017417176,0.0007357719,0.00010140688,0.00021768392,0.00033076905,0.002445356,0.8618824,0.077857964,0.03623515,0.00148026],"about_ca_topic_score_codex":0.00024553578,"about_ca_topic_score_gemma":0.00004339414,"teacher_disagreement_score":0.91771984,"about_ca_system_score_codex":0.00047192443,"about_ca_system_score_gemma":0.0011430223,"threshold_uncertainty_score":0.9997564},"labels":[],"label_agreement":null},{"id":"W4229037496","doi":"10.3758/s13428-021-01641-2","title":"Can musical ability be tested online?","year":2021,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","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 Toronto","funders":"","keywords":"Psychology; Sophistication; Melody; Musical; Test (biology); Construct validity; Session (web analytics); Openness to experience; Rhythm; Cognition; Cognitive psychology; Cognitive test; Audiology; Developmental psychology; Psychometrics; Social psychology; Computer science; Medicine","score_opus":0.6179878787281432,"score_gpt":0.6237240557554887,"score_spread":0.005736177027345524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229037496","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":[0.9942413,0.000005845348,0.00042363987,0.003132433,0.0004915483,0.00042016635,0.00007774323,0.00011849469,0.0010888606],"genre_scores_gemma":[0.9695964,0.000044651784,0.025625696,0.0016852674,0.00019543078,0.00017695613,0.000013414124,0.000031430125,0.0026307523],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9914743,0.0049823117,0.0002991922,0.0011410619,0.0012588543,0.00084430084],"domain_scores_gemma":[0.9966885,0.001573436,0.000037794634,0.0009871766,0.00032534884,0.0003877833],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034698555,0.00015842832,0.00022792938,0.00020428137,0.000509473,0.00018615791,0.00057682913,0.00011780723,0.0008174018],"category_scores_gemma":[0.0141655,0.00014482356,0.00012172556,0.00199325,0.00088448013,0.0002122983,0.0005210557,0.0009787022,0.00003822027],"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":[0.000008641357,0.0006518795,0.00052207854,0.000007718001,2.7892256e-7,0.00026798272,0.00024232568,4.6960102e-7,0.9035206,0.00029427276,0.00039648544,0.09408728],"study_design_scores_gemma":[0.0002996114,0.00016585395,0.20279245,0.000012821335,0.000009638973,0.0001678093,0.00043545032,0.00016815703,0.77390546,0.00079309853,0.021033235,0.00021641472],"about_ca_topic_score_codex":0.0001462727,"about_ca_topic_score_gemma":0.00013509227,"teacher_disagreement_score":0.20227037,"about_ca_system_score_codex":0.00015627961,"about_ca_system_score_gemma":0.00056845974,"threshold_uncertainty_score":0.9941386},"labels":[],"label_agreement":null},{"id":"W4281285907","doi":"10.3758/s13428-022-01817-4","title":"Planning, conducting, and analyzing a psychophysiological experiment on challenge and threat: A comprehensive tutorial","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","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":"Baycrest Hospital; University of Toronto","funders":"University of Toronto; Social Sciences and Humanities Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"Biopsychosocial model; Task (project management); Computer science; Data science; Data collection; Psychology; Cognitive psychology; Applied psychology; Engineering","score_opus":0.7294798079183736,"score_gpt":0.6851642411720622,"score_spread":0.04431556674631143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281285907","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":[0.990786,0.0053291507,0.00004210038,0.0002961012,0.0012478963,0.00088262605,0.000036182297,0.00006248867,0.0013174465],"genre_scores_gemma":[0.98855263,0.00007617611,0.0068607596,0.00009492024,0.00032973164,0.003043173,0.000021833714,0.000037597296,0.00098319],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934034,0.0043488587,0.00035776335,0.00074384914,0.00042701204,0.00071915507],"domain_scores_gemma":[0.99846274,0.0005883864,0.00008809823,0.0004177741,0.00010724042,0.00033575922],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002467302,0.00019467853,0.00035914363,0.000339944,0.0011380321,0.000050464918,0.00022821696,0.00012469442,0.0024549214],"category_scores_gemma":[0.00006853767,0.00017772045,0.000097894845,0.0002948284,0.00034559658,0.000054662913,0.00042905996,0.0014230132,0.000015298463],"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":[0.0032714547,0.005968561,0.014608647,0.000060301325,0.00012327784,0.0006559191,0.022566285,0.0000027385274,0.089230366,0.01868258,0.011821137,0.8330087],"study_design_scores_gemma":[0.0116803255,0.045087107,0.5930975,0.00023297785,0.00019512264,0.0004670896,0.091841035,0.000069058435,0.0031797104,0.0030295707,0.24940075,0.0017197339],"about_ca_topic_score_codex":0.00046867103,"about_ca_topic_score_gemma":0.0000022799616,"teacher_disagreement_score":0.831289,"about_ca_system_score_codex":0.00011684472,"about_ca_system_score_gemma":0.000037401234,"threshold_uncertainty_score":0.99845695},"labels":[],"label_agreement":null},{"id":"W4283690849","doi":"10.3758/s13428-022-01873-w","title":"Evaluating validity properties of 25 race-related scales","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","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":"McGill University","funders":"","keywords":"Nomological network; Prejudice (legal term); Scale (ratio); Psychology; Social psychology; Ceiling (cloud); Construct validity; Race (biology); Construct (python library); External validity; Cognitive psychology; Structural equation modeling; Psychometrics; Computer science; Statistics; Mathematics; Developmental psychology; Sociology; Engineering","score_opus":0.7966474623532196,"score_gpt":0.7045809873738367,"score_spread":0.09206647497938292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283690849","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":[0.9848107,0.0005087007,0.0000719278,0.0010133884,0.0007525435,0.0006980097,0.0000074719887,0.00006160166,0.01207567],"genre_scores_gemma":[0.9833755,0.000042844327,0.009201406,0.000021896465,0.0001115528,0.00067415513,0.000002459204,0.000017740686,0.006552464],"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","domain_scores_codex":[0.97466195,0.022590894,0.00036862807,0.00032101115,0.0014874358,0.0005700807],"domain_scores_gemma":[0.99827677,0.0007674627,0.00011080157,0.00026732567,0.000453885,0.00012374338],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035740048,0.00008520837,0.00024611462,0.00022781451,0.0018836706,0.000038982165,0.00069162896,0.00010289641,0.0029486523],"category_scores_gemma":[0.0038412672,0.000079956175,0.00013470127,0.0011003914,0.0012597787,0.00011496787,0.0004430382,0.0007841567,0.000014879286],"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":[0.00012258251,0.0007990331,0.018135922,0.000022927796,0.000031066596,0.00001236857,0.054874223,0.000005219756,0.5041456,0.0101764565,0.0019631798,0.40971142],"study_design_scores_gemma":[0.003553649,0.005802471,0.2285323,0.00016558962,0.00020423999,0.000030663778,0.40032017,0.00047822026,0.10268675,0.042267986,0.21444649,0.0015114628],"about_ca_topic_score_codex":0.004106029,"about_ca_topic_score_gemma":0.00015376961,"teacher_disagreement_score":0.40819994,"about_ca_system_score_codex":0.00027139168,"about_ca_system_score_gemma":0.00032600987,"threshold_uncertainty_score":0.99941576},"labels":[],"label_agreement":null},{"id":"W4283825839","doi":"10.3758/s13428-022-01907-3","title":"Head-mounted mobile eye-tracking in the domestic dog: A new method","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Human-Animal Interaction Studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Eye tracking; Gaze; Computer science; Tracking (education); Computer vision; Eye movement; Artificial intelligence; Task (project management); Human–computer interaction; Psychology; Engineering","score_opus":0.20730988493526833,"score_gpt":0.6956001090152925,"score_spread":0.4882902240800241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283825839","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":[0.9826675,0.0023043454,0.011060808,0.0005370615,0.00029455358,0.0013757582,0.000021497579,0.00002865947,0.0017097859],"genre_scores_gemma":[0.9206536,0.00008086151,0.0699089,0.00023413182,0.00026514023,0.0031050933,0.00004195318,0.000052700834,0.005657621],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917047,0.0061960616,0.0003325312,0.0005440572,0.00065854186,0.0005641302],"domain_scores_gemma":[0.99843043,0.0006102107,0.000067054214,0.0006110265,0.00018478512,0.00009649489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00950259,0.00016809219,0.00022634323,0.00025132994,0.0005547699,0.00009587965,0.0006904614,0.00007652629,0.0005197783],"category_scores_gemma":[0.0010323398,0.00013783401,0.00013432799,0.00069083815,0.00012862563,0.000008195328,0.0008307395,0.0010156189,0.000017631664],"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":[0.00014720396,0.0003626086,0.0037994613,0.000011305988,0.000035932426,0.00010418508,0.002116011,0.00014928484,0.9314994,0.00010127309,0.005337608,0.056335725],"study_design_scores_gemma":[0.0012469814,0.0021269573,0.06167452,0.000020298748,0.000055947177,0.00029580886,0.020258043,0.0001992506,0.09226157,0.0003621083,0.82101256,0.00048598467],"about_ca_topic_score_codex":0.0007227784,"about_ca_topic_score_gemma":0.00018023675,"teacher_disagreement_score":0.8392378,"about_ca_system_score_codex":0.00012836962,"about_ca_system_score_gemma":0.00019634563,"threshold_uncertainty_score":0.56912076},"labels":[],"label_agreement":null},{"id":"W4284888443","doi":"10.3758/s13428-022-01841-4","title":"r2mlm: An R package calculating R-squared measures for multilevel models","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","cited_by":69,"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; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Association for Psychological Science","keywords":"Multilevel model; Computer science; Graphics; Variance (accounting); R package; Mean squared error; Code (set theory); Computation; Theoretical computer science; Data mining; Statistics; Machine learning; Algorithm; Mathematics; Computational science; Set (abstract data type); Programming language; Computer graphics (images)","score_opus":0.832282820153713,"score_gpt":0.7304257606942206,"score_spread":0.10185705945949242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284888443","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":[0.5872063,0.001255338,0.38442418,0.00075877825,0.0020432735,0.012987544,0.0011148556,0.0004271079,0.009782649],"genre_scores_gemma":[0.59949034,0.000011423142,0.35959727,0.00016948163,0.0003802633,0.025562562,0.00021311344,0.00021516252,0.014360372],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.979103,0.015051828,0.00066228554,0.0010516751,0.0021132915,0.0020178966],"domain_scores_gemma":[0.9947661,0.0023678814,0.00011315368,0.0014229823,0.0005342892,0.00079555635],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02991639,0.00025771555,0.00042767898,0.00066722697,0.0020925305,0.000104785606,0.0011947617,0.00017585221,0.003511322],"category_scores_gemma":[0.0010601549,0.0002686837,0.00018860916,0.0007344735,0.00026398955,0.00024544512,0.0007710449,0.0019137565,0.00003933684],"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":[0.0006241756,0.0014961374,0.0019642478,0.000101875055,0.000034747125,0.0001288426,0.0066966764,0.00010227501,0.015908476,0.010968163,0.0029363672,0.959038],"study_design_scores_gemma":[0.026094837,0.022634024,0.16995439,0.00018535333,0.000222733,0.00058798643,0.11733947,0.16966659,0.030033259,0.0796737,0.37883732,0.0047703376],"about_ca_topic_score_codex":0.0025897264,"about_ca_topic_score_gemma":0.00008409379,"teacher_disagreement_score":0.9542677,"about_ca_system_score_codex":0.0007911496,"about_ca_system_score_gemma":0.00038421495,"threshold_uncertainty_score":0.9999765},"labels":[],"label_agreement":null},{"id":"W4286560902","doi":"10.3758/s13428-022-01912-6","title":"Concreteness ratings for 62,000 English multiword expressions","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":34,"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 Calgary","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Psychology; Word (group theory); Meaning (existential); Linguistics; Cognitive psychology; Natural language processing","score_opus":0.23104756777532953,"score_gpt":0.5707877905792769,"score_spread":0.33974022280394733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286560902","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":[0.01238763,0.0015449087,0.98188984,0.00038907767,0.000635451,0.0017526329,0.000055008128,0.001081798,0.00026367063],"genre_scores_gemma":[0.04782943,0.000005631445,0.944747,0.00010209436,0.000121063524,0.00599053,0.00001416215,0.00003678479,0.001153304],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99420214,0.0028150259,0.00033697105,0.0007721513,0.0010689996,0.0008047048],"domain_scores_gemma":[0.9954814,0.0022548253,0.00011094486,0.0010429639,0.0009002182,0.00020965033],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011023095,0.00018126974,0.00027199203,0.00042923776,0.001536504,0.00037017307,0.0030265201,0.000096201715,0.00014794047],"category_scores_gemma":[0.0034345936,0.00016744589,0.00013005253,0.001264595,0.00016037482,0.00050569745,0.0028297086,0.0011957012,0.0000016097608],"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":[0.000048841535,0.00016885225,0.00030222983,0.000049932936,0.000008523426,0.000066879504,0.004631413,0.0000041989615,0.3903663,0.020147676,0.0055696275,0.5786356],"study_design_scores_gemma":[0.0013476149,0.0008986215,0.0003299443,0.00008411613,0.000023920025,0.000057008794,0.0017033307,0.01045496,0.78731734,0.026485492,0.1703919,0.00090572605],"about_ca_topic_score_codex":0.00011601374,"about_ca_topic_score_gemma":0.0000015100261,"teacher_disagreement_score":0.5777298,"about_ca_system_score_codex":0.00021401461,"about_ca_system_score_gemma":0.00025720696,"threshold_uncertainty_score":0.99976337},"labels":[],"label_agreement":null},{"id":"W4289262412","doi":"10.3758/s13428-022-01892-7","title":"Multilevel multivariate meta-analysis made easy: An introduction to MLMVmeta","year":2022,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","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":"Kellogg's (Canada)","funders":"","keywords":"Multivariate statistics; Computer science; Multilevel model; Multivariate analysis; Meta-analysis; Data mining; Machine learning; Artificial intelligence","score_opus":0.9002596806621552,"score_gpt":0.757045118444534,"score_spread":0.1432145622176212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289262412","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":[0.000018144456,0.9814272,0.007111125,0.00032019409,0.002368965,0.0063668597,0.001635228,0.00023164587,0.00052064785],"genre_scores_gemma":[0.0000050117947,0.6267817,0.19033544,0.00010006479,0.0016895377,0.06382742,0.003006912,0.00051279203,0.11374111],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9445448,0.046478968,0.0023733403,0.0029496779,0.0016462769,0.0020069317],"domain_scores_gemma":[0.9911861,0.0016375056,0.00063718564,0.0044601085,0.0005520958,0.0015269922],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.030114878,0.0009746769,0.0060078218,0.0057976446,0.0010405495,0.00024224479,0.0023681824,0.00083417713,0.17333698],"category_scores_gemma":[0.0010832292,0.000815522,0.0073886304,0.007300844,0.00023634004,0.0002708173,0.0010594503,0.004860537,0.0013080373],"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":[0.00004169847,0.0019121256,0.000004054987,0.00047917242,0.02128329,0.000074488606,0.0003145272,0.000001124987,0.000007879769,0.0007678905,0.0038905432,0.97122324],"study_design_scores_gemma":[0.00014889133,0.00057212973,0.00031711397,0.000026150878,0.20224679,0.000035538673,0.00020148314,0.000004074538,0.0000020742812,0.000015420423,0.7958818,0.00054853177],"about_ca_topic_score_codex":0.0056646634,"about_ca_topic_score_gemma":0.00018670541,"teacher_disagreement_score":0.9706747,"about_ca_system_score_codex":0.0008994779,"about_ca_system_score_gemma":0.00048327312,"threshold_uncertainty_score":0.9994696},"labels":[],"label_agreement":null},{"id":"W4293101458","doi":"10.3758/s13428-022-01926-0","title":"Cognitive and social well-being in older adulthood: The CoSoWELL corpus of written life stories","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","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":"McMaster University","funders":"","keywords":"Timeline; Narrative; Yesterday; Psychology; Autobiographical memory; Cognition; Cognitive psychology; History; Linguistics","score_opus":0.18600255127345042,"score_gpt":0.5530519446984792,"score_spread":0.36704939342502874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293101458","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":[0.9908278,0.0010933178,0.00024913755,0.000585348,0.00069503934,0.0010333895,0.000036043522,0.000021444737,0.005458461],"genre_scores_gemma":[0.9950965,0.000054054435,0.00077408354,0.00014113342,0.00018500329,0.0009058759,0.000012853088,0.00004085244,0.0027896522],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892626,0.008794166,0.00033252867,0.00038283668,0.0006890476,0.0005388413],"domain_scores_gemma":[0.99774444,0.0015581032,0.00010308691,0.00026815347,0.00024462765,0.00008160038],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009393933,0.00013622105,0.00030829298,0.0003540183,0.00072151114,0.000048028578,0.00040376568,0.00009748105,0.0019980946],"category_scores_gemma":[0.00024847715,0.00012033538,0.000084203086,0.00064563873,0.00059590454,0.00006619015,0.00034573505,0.0011849755,0.000014620498],"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":[0.0018539402,0.0025589615,0.34770194,0.00010678108,0.00019165652,0.00036263556,0.22895569,6.1861317e-7,0.005183429,0.025884865,0.0036585086,0.383541],"study_design_scores_gemma":[0.0035357499,0.00059336063,0.8477393,0.000022302902,0.00006856674,0.000059265814,0.13407883,0.0000064358846,0.0018254765,0.003905033,0.007888421,0.00027729364],"about_ca_topic_score_codex":0.0016133791,"about_ca_topic_score_gemma":0.00013402449,"teacher_disagreement_score":0.5000373,"about_ca_system_score_codex":0.000084732594,"about_ca_system_score_gemma":0.00013269625,"threshold_uncertainty_score":0.99891424},"labels":[],"label_agreement":null},{"id":"W4294146859","doi":"10.3758/s13428-022-01913-5","title":"d$$^{\\prime }_{o}$$: Sensitivity at the optimal criterion location","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Distributed Sensor Networks and Detection Algorithms","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 Winnipeg","funders":"","keywords":"Prime (order theory); Observer (physics); Set (abstract data type); Noise (video); Detection theory; Mathematics; Variance (accounting); Base (topology); Algorithm; Prime number; Range (aeronautics); Statistics; Computer science; SIGNAL (programming language); Artificial intelligence; Discrete mathematics; Combinatorics; Physics; Telecommunications; Mathematical analysis","score_opus":0.16766907625360186,"score_gpt":0.500187781777576,"score_spread":0.3325187055239741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294146859","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":[0.02418685,0.00025380024,0.9721837,0.0017030587,0.00070537586,0.0004778278,0.000013878351,0.00019011619,0.00028540086],"genre_scores_gemma":[0.4788682,0.000038168022,0.5143629,0.00028017414,0.00022693817,0.000984878,0.000042068612,0.000037422404,0.0051592984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.989996,0.007422397,0.00023642024,0.00057944504,0.0011764511,0.0005892662],"domain_scores_gemma":[0.99727196,0.00092936796,0.00007079081,0.0012049858,0.00036349118,0.00015943729],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.012831997,0.0001325507,0.00015165734,0.00019761139,0.0021326023,0.00035841827,0.0009871344,0.000055422603,0.00017718629],"category_scores_gemma":[0.00024932178,0.00011008828,0.00009717658,0.0020135397,0.00015896348,0.0002880929,0.002755275,0.0008957728,0.000050810304],"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":[0.000029383169,0.0002533828,0.00011015185,0.0000043950095,0.000011601358,0.00015254132,0.0004587311,0.0032737702,0.030140199,0.0024978872,0.0051606903,0.95790726],"study_design_scores_gemma":[0.0006747084,0.0007207449,0.016650805,0.000009828879,0.000019319943,0.0009849234,0.0007362317,0.6352603,0.0640626,0.0007224487,0.27955103,0.0006070733],"about_ca_topic_score_codex":0.00015422433,"about_ca_topic_score_gemma":0.000009852554,"teacher_disagreement_score":0.9573002,"about_ca_system_score_codex":0.00049109635,"about_ca_system_score_gemma":0.00013405288,"threshold_uncertainty_score":0.9991665},"labels":[],"label_agreement":null},{"id":"W4295067019","doi":"10.3758/s13428-022-01958-6","title":"Generating accurate 3D gaze vectors using synchronized eye tracking and motion capture","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","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":"Women and Children’s Health Research Institute; University of Alberta","funders":"Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer vision; Computer science; Artificial intelligence; Gaze; Eye tracking; Monocular; Motion capture; Motion (physics)","score_opus":0.25227002656806086,"score_gpt":0.5296659863595778,"score_spread":0.277395959791517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295067019","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":[0.5312739,0.00040141348,0.46747634,0.00017776366,0.00021406442,0.00024003415,0.0000034191382,0.00018375399,0.00002931459],"genre_scores_gemma":[0.57238185,0.000006239333,0.42735663,0.000016539514,0.00003674997,0.0001173096,0.0000025254799,0.000017204498,0.00006494323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942128,0.0034088278,0.00028855877,0.0007183012,0.0006744713,0.00069703767],"domain_scores_gemma":[0.9985466,0.00042325057,0.00010930025,0.00058275607,0.00021389761,0.00012420355],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007013314,0.00017844942,0.00025877057,0.000515182,0.0014984182,0.00032415276,0.000856672,0.000104365245,0.000054866665],"category_scores_gemma":[0.0005311446,0.00017952622,0.00006164364,0.0012397263,0.0001948249,0.0003293748,0.0012331854,0.0013381784,0.0000020514829],"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":[0.0000071972604,0.0001193754,0.0066943346,0.000018364413,0.000011663046,0.00015596917,0.0010406844,0.0010261671,0.38535732,0.0012223275,0.000028841217,0.6043177],"study_design_scores_gemma":[0.0014885622,0.00044941777,0.06649519,0.00007402037,0.000061146144,0.0004729153,0.0021104293,0.8752515,0.048937604,0.0011729344,0.0025108599,0.00097548176],"about_ca_topic_score_codex":0.00025006564,"about_ca_topic_score_gemma":0.0000072373427,"teacher_disagreement_score":0.87422526,"about_ca_system_score_codex":0.00032834703,"about_ca_system_score_gemma":0.00015111748,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W4306655083","doi":"10.3758/s13428-022-01988-0","title":"Questions of value, questions of magnitude: An exploration and application of methods for comparing indirect effects in multiple mediator models","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":88,"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":"Operationalization; Mediation; Computer science; Mechanism (biology); Magnitude (astronomy); Value (mathematics); Psychology; Cognitive psychology; Epistemology; Machine learning; Physics","score_opus":0.48291823368261927,"score_gpt":0.6283255401611992,"score_spread":0.14540730647857997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306655083","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":[0.8272719,0.00088950695,0.16843885,0.00008265211,0.00010729018,0.002918031,0.000059550795,0.000027513535,0.00020473199],"genre_scores_gemma":[0.60964483,0.00008841407,0.38691804,0.0000011631041,0.000010411133,0.0033016792,0.000015120517,0.000011888895,0.000008453202],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9931031,0.0054946276,0.0005062025,0.00030829167,0.00031502135,0.00027278124],"domain_scores_gemma":[0.996796,0.0023240682,0.00021969904,0.0002499423,0.00030936772,0.000100937075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012823009,0.00009924634,0.0004232327,0.00048913085,0.0005153509,0.000015445961,0.00029428527,0.00006914413,0.000005880411],"category_scores_gemma":[0.0011389457,0.00011701417,0.0000622267,0.0006509989,0.0005764955,0.0004655033,0.00027965673,0.0002429396,1.068036e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016973646,0.0019462587,0.11586798,0.00017961032,0.000026738107,5.335103e-7,0.04293209,0.0022768504,0.52946764,0.09295397,0.000008131958,0.21417046],"study_design_scores_gemma":[0.003947789,0.0027360388,0.11283579,0.00016677035,0.00028148928,0.0000018401266,0.09898831,0.1140727,0.55436754,0.111092746,0.00066196866,0.00084701466],"about_ca_topic_score_codex":0.010113737,"about_ca_topic_score_gemma":0.0017504754,"teacher_disagreement_score":0.21847919,"about_ca_system_score_codex":0.0002891625,"about_ca_system_score_gemma":0.00018018695,"threshold_uncertainty_score":0.996478},"labels":[],"label_agreement":null},{"id":"W4307426877","doi":"10.3758/s13428-022-02002-3","title":"The underwood project: A virtual environment for eliciting ambiguous threat","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Media Influence and Health","field":"Arts and Humanities","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 British Columbia","funders":"","keywords":"Narrative; Cognitive psychology; Psychology; Cognition; Naturalism; Social psychology; Computer science","score_opus":0.5894848696925414,"score_gpt":0.5837338777687398,"score_spread":0.005750991923801685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307426877","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":[0.95601374,0.0023099575,0.0036643175,0.0059656715,0.0021931084,0.012016416,0.00048919115,0.0002633472,0.017084228],"genre_scores_gemma":[0.65696394,0.0017176402,0.06620843,0.0024547847,0.006568025,0.11917474,0.00027687076,0.0005104434,0.14612514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958775,0.0017048436,0.00033258527,0.0003449913,0.0008942179,0.0008458478],"domain_scores_gemma":[0.9978166,0.0014547248,0.000077337514,0.00043350147,0.00010377103,0.00011402395],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010256758,0.00013256425,0.00018495182,0.00016579354,0.006052287,0.00025950448,0.0005220971,0.000030880205,0.0013051943],"category_scores_gemma":[0.00028566588,0.00009534092,0.000114045055,0.000084909785,0.00052770565,0.00009266324,0.00037415518,0.00073869777,0.000029956029],"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":[0.00013045527,0.00030495643,0.00015087878,0.00003346886,0.000022307198,0.000015750302,0.031656455,0.000008373604,0.0011659567,0.18562117,0.0050439676,0.77584624],"study_design_scores_gemma":[0.0003828701,0.001110917,0.000254594,0.0000068891973,0.000019154055,0.000006447444,0.049861107,0.000086356304,0.00028772184,0.0036489377,0.94419056,0.00014442658],"about_ca_topic_score_codex":0.0016203529,"about_ca_topic_score_gemma":0.00023198724,"teacher_disagreement_score":0.93914664,"about_ca_system_score_codex":0.00028446043,"about_ca_system_score_gemma":0.0003032963,"threshold_uncertainty_score":0.99960774},"labels":[],"label_agreement":null},{"id":"W4308017781","doi":"10.3758/s13428-022-01999-x","title":"Evaluating CloudResearch’s Approved Group as a solution for problematic data quality on MTurk","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":227,"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":"Vetting; Data quality; Psychology; Quality (philosophy); Sample (material); Applied psychology; Computer science; Computer security; Operations management","score_opus":0.8107478869005017,"score_gpt":0.6970883390979823,"score_spread":0.11365954780251941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308017781","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":[0.086212896,0.00014877119,0.90607506,0.0019734437,0.00045481342,0.004231249,0.000056152458,0.00028991213,0.00055770896],"genre_scores_gemma":[0.14699349,0.0000031756315,0.8476409,0.00010031878,0.00013293575,0.003915411,0.000102812075,0.000050188562,0.0010608045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97731763,0.016015312,0.0006908594,0.001602242,0.0030499813,0.0013239936],"domain_scores_gemma":[0.98940283,0.005648254,0.00020780657,0.003932821,0.000506647,0.00030161388],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.10430951,0.00022861814,0.0003895946,0.00047390437,0.0026118597,0.00060455216,0.0039782617,0.000085619584,0.00006778041],"category_scores_gemma":[0.008200325,0.00022347388,0.00013847505,0.001415976,0.00019487122,0.00041570613,0.005341304,0.0014336073,0.000023706763],"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":[0.00015829006,0.00073192146,0.00006027553,0.00018887933,0.000021736412,0.000017952258,0.0014507659,0.0003025257,0.18538615,0.017803907,0.0017451652,0.79213244],"study_design_scores_gemma":[0.0018377611,0.0032549119,0.0013962206,0.000110421,0.000033071752,0.000070803406,0.0012016344,0.9497103,0.008023578,0.021653004,0.012090358,0.00061792077],"about_ca_topic_score_codex":0.0006246304,"about_ca_topic_score_gemma":0.00001685032,"teacher_disagreement_score":0.9494078,"about_ca_system_score_codex":0.0004965728,"about_ca_system_score_gemma":0.0005813192,"threshold_uncertainty_score":0.9986866},"labels":[],"label_agreement":null},{"id":"W4313453623","doi":"10.3758/s13428-022-02050-9","title":"The timing database: An open-access, live repository for interval timing studies","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":15,"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 Laval; The Scarborough Hospital; University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database; Task (project management); Interval (graph theory); Range (aeronautics); Data mining","score_opus":0.8729870524749542,"score_gpt":0.720222263704515,"score_spread":0.1527647887704392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313453623","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":[0.9921799,0.00006458164,0.0019471464,0.0007419147,0.0019638953,0.0023205222,0.000047831905,0.00022201988,0.000512236],"genre_scores_gemma":[0.8532197,0.0034893786,0.07562417,0.0014659967,0.0017768751,0.015156525,0.00006237247,0.00029891232,0.048906084],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99418855,0.0029365015,0.00032835596,0.0009387952,0.00076284865,0.0008449338],"domain_scores_gemma":[0.9945891,0.003978634,0.000089641384,0.00091355544,0.00025402138,0.00017504685],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012031349,0.00015223998,0.00020788521,0.00025531257,0.0031831376,0.0017829072,0.0031949622,0.000048099428,0.000020111747],"category_scores_gemma":[0.008498159,0.000108335844,0.00006317851,0.0012033266,0.00087923947,0.002054001,0.003886373,0.0004557991,0.000044560788],"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":[0.00005323784,0.0000704965,0.000058576163,0.000019003977,0.0000015390674,0.000059295882,0.0010341804,0.0000022659,0.8979538,0.00023959155,0.0056708567,0.09483714],"study_design_scores_gemma":[0.00050707755,0.0008976823,0.0076588504,0.00014008995,0.000033914923,0.000071417846,0.0084446175,0.0036035366,0.93565774,0.001127459,0.041471057,0.00038657238],"about_ca_topic_score_codex":0.00015472183,"about_ca_topic_score_gemma":0.000046452682,"teacher_disagreement_score":0.13896017,"about_ca_system_score_codex":0.00011562969,"about_ca_system_score_gemma":0.00018511077,"threshold_uncertainty_score":0.9998537},"labels":[],"label_agreement":null},{"id":"W4317952720","doi":"10.3758/s13428-022-02044-7","title":"Visualization of latent components assessed in O*Net occupations (VOLCANO): A robust method for standardized conversion of occupational labels to ratio scale format","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Delphi Technique in Research","field":"Social Sciences","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":"Baycrest Hospital; Centre for Addiction and Mental Health","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Institutes of Health Research","keywords":"Standardization; Dimension (graph theory); Visualization; Psychology; Scale (ratio); Cognition; Sample (material); Computer science; Space (punctuation); Mathematics education; Data science; Applied psychology; Artificial intelligence; Mathematics; Geography; Cartography","score_opus":0.6037485672332248,"score_gpt":0.6851678499988348,"score_spread":0.08141928276561006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317952720","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":[0.30705562,0.00001134664,0.68764436,0.00035230187,0.00012342303,0.004134445,0.00034692773,0.00009093572,0.00024063417],"genre_scores_gemma":[0.3849749,0.00006555385,0.61204976,0.0000149246835,0.00003870137,0.0020441243,0.00027922835,0.000038425143,0.00049439166],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9903545,0.005512668,0.00076268124,0.0003766412,0.0023098844,0.00068361964],"domain_scores_gemma":[0.9927162,0.004078809,0.0001787895,0.0003463568,0.0024593724,0.0002204695],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.035461422,0.00012719564,0.00041915211,0.0017186779,0.00040157526,0.00007082431,0.00060303946,0.0002024834,0.00015291317],"category_scores_gemma":[0.0049256296,0.00013367871,0.00012133399,0.0043653706,0.0003309564,0.00032321303,0.00028761156,0.00024741437,0.000007640151],"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":[0.0026566342,0.0015969286,0.19589812,0.0006322501,0.000058755202,0.000012823439,0.017281085,0.0016260883,0.7044971,0.018237123,0.013713439,0.043789625],"study_design_scores_gemma":[0.0044910153,0.00105494,0.45769733,0.000453996,0.0000629863,0.0000014108305,0.009261391,0.03044693,0.48065642,0.0025660296,0.012705042,0.0006025336],"about_ca_topic_score_codex":0.0037153948,"about_ca_topic_score_gemma":0.00084882264,"teacher_disagreement_score":0.2617992,"about_ca_system_score_codex":0.0004877935,"about_ca_system_score_gemma":0.0010429204,"threshold_uncertainty_score":0.9931954},"labels":[],"label_agreement":null},{"id":"W4321168228","doi":"10.3758/s13428-023-02066-9","title":"Characterizing the role of impulsivity in costly, reactive aggression using a novel paradigm","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":9,"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":"Aggression; Psychology; Temptation; Anger; Impulsivity; Self-control; Rage (emotion); Delay of gratification; Social psychology; Trait; Developmental psychology; Computer science","score_opus":0.5368477379161043,"score_gpt":0.6666851532272852,"score_spread":0.12983741531118087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321168228","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":[0.996787,0.00046056986,0.00027435314,0.00024880044,0.00041648533,0.00102563,0.00007401698,0.000046458164,0.0006666467],"genre_scores_gemma":[0.9937683,0.000046129142,0.0050117103,0.000019060653,0.00007836424,0.00069904566,0.000023235649,0.000040406125,0.00031378772],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99414575,0.0035801805,0.0005398289,0.00040720802,0.00046392414,0.00086313696],"domain_scores_gemma":[0.99793035,0.00091183285,0.00018700515,0.00064033497,0.00015890891,0.00017154557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010424231,0.00014188609,0.0003062015,0.0006487367,0.00027771638,0.000029438395,0.0004373893,0.00019012093,0.00042288186],"category_scores_gemma":[0.0003530054,0.00010923115,0.00015793389,0.001787037,0.00028569286,0.00014675398,0.00027878414,0.0011216291,0.00006738394],"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":[0.00015871585,0.00069805095,0.04337438,0.000012451921,0.000007638918,0.000025449865,0.0022357618,3.5823942e-7,0.51046044,0.0009706702,0.000047968326,0.44200814],"study_design_scores_gemma":[0.00064956135,0.00028271542,0.95994234,0.00040775002,0.00002380752,0.000030775867,0.0045612073,0.00025677198,0.028667323,0.00077529927,0.004244516,0.00015795373],"about_ca_topic_score_codex":0.006615544,"about_ca_topic_score_gemma":0.000117291405,"teacher_disagreement_score":0.9165679,"about_ca_system_score_codex":0.00017988644,"about_ca_system_score_gemma":0.00013357807,"threshold_uncertainty_score":0.99999946},"labels":[],"label_agreement":null},{"id":"W4321490378","doi":"10.3758/s13428-023-02079-4","title":"Multilevel mediation analysis in R: A comparison of bootstrap and Bayesian approaches","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":34,"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":"Resampling; Bayesian probability; Statistics; Computer science; Mediation; Random effects model; Context (archaeology); Type I and type II errors; Econometrics; Estimator; Multilevel model; Mathematics; Meta-analysis","score_opus":0.7501815697635115,"score_gpt":0.663230774126511,"score_spread":0.08695079563700048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321490378","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":[0.1669331,0.00004915093,0.8320837,0.000072810915,0.000025630094,0.00044732835,0.00003589057,0.00003967774,0.00031268367],"genre_scores_gemma":[0.3905006,0.0000119981205,0.6092714,7.6487885e-7,0.000010433587,0.00014549657,0.000008060046,0.000011447081,0.00003980059],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949655,0.0030091957,0.00059762393,0.00036844343,0.00062739954,0.0004318248],"domain_scores_gemma":[0.9902751,0.008984213,0.00010781864,0.00035012394,0.00013692824,0.00014581121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011031904,0.00012789218,0.00060461106,0.0012912716,0.00007881244,0.000038226506,0.00021290744,0.00013905377,0.000105689025],"category_scores_gemma":[0.0069232583,0.000112203925,0.00008409527,0.0027790363,0.00028234042,0.00006410782,0.00014920518,0.00043929767,0.0000027997646],"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":[0.000026972622,0.00033299887,0.21909113,0.00017058542,0.00006557195,0.000012871847,0.0023039507,0.0000030011279,0.0034930166,0.059751563,0.00006824677,0.7146801],"study_design_scores_gemma":[0.00036725024,0.000117328316,0.6633063,0.000032635337,0.00015931808,9.798043e-7,0.0020875323,0.09879301,0.0051145656,0.22982731,0.000020654585,0.00017313645],"about_ca_topic_score_codex":0.00013365361,"about_ca_topic_score_gemma":0.000105314815,"teacher_disagreement_score":0.714507,"about_ca_system_score_codex":0.00004191691,"about_ca_system_score_gemma":0.000055778317,"threshold_uncertainty_score":0.8288287},"labels":[],"label_agreement":null},{"id":"W4321491505","doi":"10.3758/s13428-023-02076-7","title":"A simple semi-automated home-tank method and procedure to explore classical associative learning in adult zebrafish","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","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":"Canadian Celiac Association; University of Toronto","funders":"Göteborgs Universitet","keywords":"Zebrafish; Computer science; Mnemonic; Task (project management); Associative learning; Simple (philosophy); Associative property; Artificial intelligence; Animal cognition; Cognition; Cognitive science; Human–computer interaction; Psychology; Cognitive psychology; Neuroscience; Biology","score_opus":0.13491756394403476,"score_gpt":0.5471398362654555,"score_spread":0.4122222723214207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321491505","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":[0.98364216,0.00007761244,0.010488096,0.003318567,0.000032602202,0.0017232076,0.000046425077,0.00031360588,0.0003577254],"genre_scores_gemma":[0.9265175,0.00035648208,0.062028013,0.00032715354,0.00026345384,0.0068689487,0.00059617724,0.00015843078,0.0028838438],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9931747,0.0032026335,0.00039424995,0.001001719,0.0009886975,0.0012380241],"domain_scores_gemma":[0.9971463,0.000979828,0.000061733546,0.0004569362,0.00062495016,0.0007302457],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007833319,0.00023094968,0.00035057755,0.0006289202,0.00029875178,0.000121525234,0.0005222625,0.00041382186,0.00003813288],"category_scores_gemma":[0.016320907,0.00022246278,0.00008717187,0.0029855845,0.0002923706,0.000013710737,0.0010785123,0.0011193675,0.00006529372],"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":[0.00011424126,0.0002243372,0.016712008,0.000053691314,0.000036396883,0.000050795377,0.00068365666,0.000017779392,0.8933391,0.00010988299,0.02325166,0.06540646],"study_design_scores_gemma":[0.0027778703,0.0021502133,0.5932229,0.00014748954,0.0000375938,0.000034589557,0.006971817,0.016633207,0.2862199,0.0019896526,0.08873024,0.0010844881],"about_ca_topic_score_codex":0.000095208634,"about_ca_topic_score_gemma":0.00011990817,"teacher_disagreement_score":0.6071192,"about_ca_system_score_codex":0.00015322113,"about_ca_system_score_gemma":0.00041645052,"threshold_uncertainty_score":0.99196506},"labels":[],"label_agreement":null},{"id":"W4328051526","doi":"10.3758/s13428-023-02080-x","title":"Taking stock of the past: A psychometric evaluation of the Autobiographical Interview","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Concordia University; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autobiographical memory; Psychology; Recall; Episodic memory; Cognitive psychology; Internal consistency; Reliability (semiconductor); Confirmatory factor analysis; Trait; Psychometrics; Developmental psychology; Clinical psychology; Cognition; Computer science; Structural equation modeling","score_opus":0.6968204307330096,"score_gpt":0.6741826402348429,"score_spread":0.02263779049816672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328051526","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":[0.9903979,0.0011675778,0.0004841411,0.00069614645,0.0020082816,0.0016136188,0.000013811957,0.00003344289,0.0035850937],"genre_scores_gemma":[0.9968345,0.00006418558,0.0008043457,0.000022536658,0.00010405764,0.00055679376,0.0000020345096,0.000030542025,0.0015809922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9800348,0.016962767,0.00047490236,0.00033626097,0.0017425882,0.00044864375],"domain_scores_gemma":[0.9968315,0.0007862369,0.00026018475,0.0012760119,0.0007878488,0.000058263835],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03735946,0.00012056384,0.00026714103,0.0011967126,0.00022267066,0.00002845225,0.0012114749,0.00015662579,0.0014138967],"category_scores_gemma":[0.0013529396,0.000072270144,0.00040183173,0.009315754,0.0005056135,0.00004524796,0.00031451444,0.00068875303,0.000031217227],"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":[0.000032408047,0.00045197995,0.19074689,0.000054773584,0.00007616027,9.782535e-7,0.0017469696,0.0000016916423,0.011573768,0.0010299518,0.0021051876,0.7921792],"study_design_scores_gemma":[0.0006212686,0.000120106335,0.99311525,0.00006959117,0.000099527315,0.0000050274825,0.00063388044,0.0000731879,0.0019572687,0.0017864571,0.0014478568,0.000070553455],"about_ca_topic_score_codex":0.0003906636,"about_ca_topic_score_gemma":0.000057262663,"teacher_disagreement_score":0.8023684,"about_ca_system_score_codex":0.000059130063,"about_ca_system_score_gemma":0.00012605073,"threshold_uncertainty_score":0.99949896},"labels":[],"label_agreement":null},{"id":"W4380870481","doi":"10.3758/s13428-023-02123-3","title":"Simultaneous estimation of the intermediate correlation matrix for arbitrary marginal densities","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods and Inference","field":"Mathematics","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 British Columbia","funders":"","keywords":"Multivariate normal distribution; Correlation; Multivariate statistics; Matrix (chemical analysis); Covariance matrix; Multivariate t-distribution; Distribution (mathematics); Computer science; Data Matrix; Marginal distribution; Mathematics; Statistics; Algorithm; Random variable; Mathematical analysis; Chemistry","score_opus":0.3626131996223184,"score_gpt":0.6157310743641532,"score_spread":0.2531178747418348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380870481","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":[0.28828526,0.00001966693,0.7099619,0.000112848866,0.00030806134,0.0009824048,0.00008405006,0.00006641859,0.00017942415],"genre_scores_gemma":[0.17182781,0.000008326075,0.82644224,0.000006119664,0.000047378784,0.00030162258,0.000010465983,0.000026976924,0.0013290516],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967441,0.0017262585,0.00040453553,0.00021244251,0.00054515543,0.00036752308],"domain_scores_gemma":[0.9737461,0.025297005,0.00011730199,0.00036378484,0.00040426338,0.000071503906],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069748214,0.00011132079,0.00024592274,0.0002044467,0.00020105048,0.000039070394,0.0002943515,0.000104857616,0.000076926546],"category_scores_gemma":[0.029516041,0.0000790315,0.00010768734,0.00061826804,0.00032037348,0.00005655615,0.00017163978,0.0003661706,0.00001380677],"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":[0.0002036637,0.00017818029,0.0011887174,0.0006285921,0.000027134112,0.000022216003,0.0014431444,0.00036027885,0.013058459,0.24573137,0.0018702056,0.735288],"study_design_scores_gemma":[0.00032693325,0.00022627757,0.013111478,0.0001376908,0.00006470233,0.000009792892,0.00055269356,0.36692056,0.011494636,0.606806,0.00021237545,0.00013686475],"about_ca_topic_score_codex":0.000023543846,"about_ca_topic_score_gemma":0.0000030469405,"teacher_disagreement_score":0.7351512,"about_ca_system_score_codex":0.000059259484,"about_ca_system_score_gemma":0.000114700655,"threshold_uncertainty_score":0.97865874},"labels":[],"label_agreement":null},{"id":"W4381716880","doi":"10.3758/s13428-023-02098-1","title":"From pre-processing to advanced dynamic modeling of pupil data","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":64,"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":"Max-Planck-Gesellschaft; Deutsche Forschungsgemeinschaft","keywords":"Pupillometry; Computer science; Variety (cybernetics); Dynamic time warping; Pupil; Pupil size; Artificial intelligence; Psychology","score_opus":0.5692682817835731,"score_gpt":0.6245009920505697,"score_spread":0.05523271026699661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381716880","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":[0.9213786,0.000034874112,0.07685974,0.0003499133,0.00030743703,0.0005544459,0.00022326542,0.00014463055,0.00014707],"genre_scores_gemma":[0.91130245,0.00006166871,0.08728336,0.000045698645,0.00005551366,0.0001339687,0.00008455926,0.00005016204,0.0009826055],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623704,0.0010697849,0.00033606004,0.00091652235,0.0008788769,0.0005616882],"domain_scores_gemma":[0.9974943,0.0009694056,0.00005736843,0.001143135,0.00015986797,0.00017591967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036539189,0.00013057259,0.00022329137,0.0004415987,0.0002628984,0.000102726255,0.0012136301,0.00007121164,0.000040081562],"category_scores_gemma":[0.003861872,0.000119924036,0.0000436459,0.0020441809,0.00010291783,0.00040903842,0.001351265,0.00044171404,0.00004560842],"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":[0.00004519603,0.00003714301,0.000036054505,0.00001382825,6.983019e-7,0.0000133089,0.00012980404,0.0017542905,0.6571992,0.000018727034,0.000034533263,0.34071723],"study_design_scores_gemma":[0.00019049541,0.0001063157,0.0015329871,0.000059970287,0.00000866172,0.0000023690798,0.00023718565,0.92375916,0.07188261,0.0016366094,0.00044164827,0.00014195412],"about_ca_topic_score_codex":0.00025827566,"about_ca_topic_score_gemma":0.000026679556,"teacher_disagreement_score":0.9220049,"about_ca_system_score_codex":0.0000637697,"about_ca_system_score_gemma":0.00010378747,"threshold_uncertainty_score":0.48903602},"labels":[],"label_agreement":null},{"id":"W4382317569","doi":"10.3758/s13428-023-02148-8","title":"Measuring vection: a review and critical evaluation of different methods for quantifying illusory self-motion","year":2023,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","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":"Toronto Rehabilitation Institute; Toronto Metropolitan University; University Health Network","funders":"Australian Research Council; Deakin University","keywords":"Psychology; Comparability; Cognitive psychology; Mathematics","score_opus":0.9385699100556464,"score_gpt":0.7526030079243847,"score_spread":0.18596690213126166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382317569","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":[0.000013141139,0.90739715,0.08675666,0.00005911182,0.00059604127,0.0049121086,0.00002886512,0.00017495599,0.000061939805],"genre_scores_gemma":[0.000012164955,0.88155055,0.11367894,0.000019998772,0.00010625649,0.0044025453,0.000015073683,0.00010959285,0.000104903585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9619942,0.033448406,0.001155422,0.0011790076,0.0015836502,0.00063932146],"domain_scores_gemma":[0.9893609,0.008321034,0.000330019,0.0005794022,0.0011609606,0.00024766204],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05893263,0.00041329372,0.001803477,0.00085570215,0.0005965949,0.00016022217,0.00044744438,0.0003936759,0.00018663688],"category_scores_gemma":[0.036596913,0.00033753106,0.0004686929,0.0014727934,0.00026237013,0.00018812375,0.00031303716,0.0010434279,0.00001907617],"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":[0.0000041397757,0.0001358557,2.003649e-7,0.08784937,0.000011470849,9.708709e-7,0.00008749832,4.0876138e-8,0.0049699177,0.0005331369,0.00001564571,0.90639174],"study_design_scores_gemma":[0.002259257,0.002461211,0.00010993439,0.26246774,0.030999461,0.0006571923,0.0005189928,0.007149394,0.037467312,0.016402189,0.63580805,0.0036992764],"about_ca_topic_score_codex":0.000005411784,"about_ca_topic_score_gemma":0.0000013877442,"teacher_disagreement_score":0.9026925,"about_ca_system_score_codex":0.00037207323,"about_ca_system_score_gemma":0.0004361316,"threshold_uncertainty_score":0.9999077},"labels":[],"label_agreement":null},{"id":"W4382502700","doi":"10.3758/s13428-023-02124-2","title":"The Misinformation Susceptibility Test (MIST): A psychometrically validated measure of news veracity discernment","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":91,"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; Deutscher Akademischer Austauschdienst; University of Virginia","keywords":"Mist; Misinformation; Psychology; Psychological intervention; Test (biology); Computer science; Social psychology; Computer security","score_opus":0.4256537945364519,"score_gpt":0.6244316175167799,"score_spread":0.19877782298032798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382502700","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":[0.9070686,0.00009059431,0.0056183706,0.005983389,0.000619108,0.0030571988,0.000091200985,0.000346884,0.07712464],"genre_scores_gemma":[0.98600227,0.0005406909,0.007853037,0.00004279699,0.00010110276,0.00007025907,0.000030512885,0.000017243568,0.0053421194],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99280125,0.0029559098,0.00060880964,0.00019266082,0.0027314017,0.00070995535],"domain_scores_gemma":[0.9945461,0.003450781,0.00017603434,0.00057946745,0.0008971979,0.00035039693],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034474194,0.000110846835,0.00018853677,0.0003896973,0.0014412869,0.00034365445,0.0006873588,0.00013526529,0.0003543424],"category_scores_gemma":[0.02735897,0.00007737233,0.00011767903,0.004532106,0.0006554558,0.0005125549,0.00014017512,0.0004288414,0.00014477593],"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":[0.000077389566,0.0002478152,0.010028209,0.00003251615,0.0000124056,0.000001305547,0.026375027,0.0000040375794,0.0072819595,0.0017916039,0.015370653,0.9387771],"study_design_scores_gemma":[0.0011419486,0.00044760204,0.6658236,0.00006549358,0.000032839835,0.0000017673118,0.086832695,0.0005043628,0.013522918,0.0016313668,0.22960204,0.00039338658],"about_ca_topic_score_codex":0.0014136554,"about_ca_topic_score_gemma":0.00055942376,"teacher_disagreement_score":0.9383837,"about_ca_system_score_codex":0.00035831518,"about_ca_system_score_gemma":0.0004782528,"threshold_uncertainty_score":0.9998587},"labels":[],"label_agreement":null},{"id":"W4383711346","doi":"10.3758/s13428-023-02158-6","title":"Reclassifying guesses to increase signal-to-noise ratio in psychological experiments","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","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":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; Noise (video); MATLAB; Speech recognition; Variable (mathematics); Artificial intelligence; Psychology; Statistics; Data mining; Machine learning; Mathematics; Programming language","score_opus":0.8334514151004707,"score_gpt":0.7131823945226864,"score_spread":0.12026902057778432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383711346","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":[0.9940085,0.000027820515,0.0002238585,0.0022410343,0.00043596042,0.0014910393,0.000021018466,0.00024892585,0.0013018835],"genre_scores_gemma":[0.98000604,0.000052604984,0.011921482,0.00097553106,0.00010403282,0.002822382,0.0000039198517,0.000045593566,0.0040684044],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9920752,0.0040389965,0.00046772993,0.0013217373,0.000872015,0.0012243185],"domain_scores_gemma":[0.9973487,0.0013687167,0.000041005842,0.0006017687,0.00012088588,0.0005188695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004302633,0.0002641889,0.00038897354,0.001152279,0.00046651848,0.00012544358,0.0008492998,0.00014725488,0.00032471737],"category_scores_gemma":[0.0030103147,0.00021536338,0.00009009712,0.0045654033,0.0003206667,0.00018772454,0.00088624144,0.0008020813,0.0014017961],"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":[0.00018167244,0.00053463114,0.009320207,0.000005041901,9.877067e-7,0.00067795,0.0004923975,0.0000032104183,0.9142067,0.000036521236,0.0063241627,0.068216525],"study_design_scores_gemma":[0.00052632793,0.0007761509,0.1462802,0.000043296393,0.0000060009543,0.000021891552,0.0006247303,0.000011545181,0.8460779,0.00028797987,0.005016127,0.000327859],"about_ca_topic_score_codex":0.00015292404,"about_ca_topic_score_gemma":0.000019761774,"teacher_disagreement_score":0.13696,"about_ca_system_score_codex":0.000120958975,"about_ca_system_score_gemma":0.000031767315,"threshold_uncertainty_score":0.9993757},"labels":[],"label_agreement":null},{"id":"W4384664207","doi":"10.3758/s13428-023-02170-w","title":"LaDEP: A large database of English pseudo-compounds","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","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":"Yorkville University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database; Programming language; Information retrieval; Natural language processing; World Wide Web","score_opus":0.2067183506943114,"score_gpt":0.5583345911829365,"score_spread":0.35161624048862505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384664207","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":[0.04409974,0.0020263575,0.9457165,0.00042798874,0.00092784426,0.0011475519,0.00010440907,0.003610137,0.001939446],"genre_scores_gemma":[0.051929533,0.000057764562,0.9469455,0.000025507063,0.0001209943,0.00023641034,0.000024885268,0.000026981494,0.0006324043],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9953614,0.0017125183,0.00033992121,0.0005983076,0.001142562,0.0008453279],"domain_scores_gemma":[0.99603367,0.0010354018,0.00008275975,0.0014470035,0.0012139142,0.00018727068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013685312,0.00015569825,0.000273978,0.0009190322,0.00022648118,0.00019513478,0.002574013,0.00013058896,0.00003511561],"category_scores_gemma":[0.0045105293,0.00013815801,0.000096594114,0.0038727415,0.00017479037,0.00067380816,0.0023601751,0.00083975657,0.00003337279],"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":[0.000031308562,0.0006249592,0.0029417933,0.00032117852,0.000023438699,0.0004909197,0.0060102576,4.1468167e-7,0.54679435,0.09850985,0.027748957,0.31650257],"study_design_scores_gemma":[0.00075291516,0.00031552228,0.0025501521,0.0002499681,0.000018779741,0.000023958037,0.0005431329,0.004779736,0.9362215,0.02206536,0.0318995,0.0005794712],"about_ca_topic_score_codex":0.00009146814,"about_ca_topic_score_gemma":0.0000065489044,"teacher_disagreement_score":0.38942713,"about_ca_system_score_codex":0.00007018904,"about_ca_system_score_gemma":0.00019964474,"threshold_uncertainty_score":0.563392},"labels":[],"label_agreement":null},{"id":"W4386047445","doi":"10.3758/s13428-023-02190-6","title":"Deep learning models for webcam eye tracking in online experiments","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":41,"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":"Max-Planck-Gesellschaft","keywords":"Eye tracking; Computer science; Gaze; Fixation (population genetics); Artificial intelligence; Deep learning; Computer vision; Eye movement; Tracking (education); Task (project management); Psychology","score_opus":0.49091216203907995,"score_gpt":0.610252692821539,"score_spread":0.1193405307824591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386047445","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":[0.29047495,0.0001534402,0.7076414,0.00039930057,0.00015034713,0.0004840884,0.0000018319122,0.0005624078,0.00013223161],"genre_scores_gemma":[0.49549913,0.000032151336,0.5031587,0.000009680136,0.0000323226,0.00062139635,0.000010206704,0.000026170792,0.0006102428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962805,0.001211844,0.00032483676,0.000692278,0.00050101714,0.0009895214],"domain_scores_gemma":[0.9980659,0.0009688785,0.000055842127,0.0005505571,0.0002441756,0.00011466586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067506284,0.00015695904,0.00027303144,0.0011014253,0.00030704978,0.00015008805,0.0012683317,0.00016728615,0.000007371305],"category_scores_gemma":[0.0009089773,0.00015625407,0.00009283137,0.0020807425,0.00013520334,0.0003543678,0.0006180576,0.0008973564,0.000022109434],"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":[0.0000122449255,0.00029785567,0.0067818887,0.000018851439,0.0000066236353,0.000079804966,0.0013002094,0.0014625712,0.048722185,0.007089532,0.000055401346,0.9341728],"study_design_scores_gemma":[0.0010656021,0.00041254784,0.08311347,0.00008141559,0.0000059926033,0.0000072307894,0.0018229819,0.8605145,0.035676092,0.01457366,0.0023391466,0.00038735833],"about_ca_topic_score_codex":0.00006532322,"about_ca_topic_score_gemma":0.000020902062,"teacher_disagreement_score":0.9337855,"about_ca_system_score_codex":0.00013791317,"about_ca_system_score_gemma":0.00007427586,"threshold_uncertainty_score":0.63718563},"labels":[],"label_agreement":null},{"id":"W4386485153","doi":"10.3758/s13428-023-02222-1","title":"Validation of scrambling methods for vocal affect bursts","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","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":"Georg-August-Universität Göttingen","keywords":"Scrambling; Affect (linguistics); Computer science; Speech recognition; Psychology; Audiology; Communication; Medicine; Algorithm","score_opus":0.4873390771829146,"score_gpt":0.6633259502545373,"score_spread":0.17598687307162275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386485153","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":[0.08069337,0.00017656959,0.91737276,0.00033455624,0.0003423893,0.00066306995,0.0000029217094,0.00023325409,0.00018111606],"genre_scores_gemma":[0.021598257,0.000018839086,0.97745013,0.000012587606,0.000095571,0.0004083146,0.000008358819,0.000025077154,0.00038287402],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949766,0.0027045792,0.0003566303,0.0005615346,0.00064283866,0.00075784716],"domain_scores_gemma":[0.9946429,0.0038141876,0.00010514731,0.00065257377,0.00060857495,0.00017662444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029798023,0.00013905921,0.00029842372,0.00083854026,0.00033143253,0.00025145334,0.0011274572,0.00012335688,0.000012569931],"category_scores_gemma":[0.0038183364,0.00012794847,0.00015511687,0.0030376334,0.00014004819,0.00047264088,0.0005247848,0.00033856614,0.000018306131],"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":[0.0000076134356,0.000034347333,0.00025755828,0.000049106242,0.000004720799,0.0000036556964,0.00018724421,0.000011070058,0.38710663,0.00036619225,0.00016558175,0.6118063],"study_design_scores_gemma":[0.00029613357,0.00019887369,0.0025371823,0.000052737556,0.000010419901,0.0000061549777,0.00008743849,0.008245776,0.97998977,0.007009848,0.0014282252,0.00013742404],"about_ca_topic_score_codex":0.000022787293,"about_ca_topic_score_gemma":5.710251e-7,"teacher_disagreement_score":0.6116688,"about_ca_system_score_codex":0.00007006057,"about_ca_system_score_gemma":0.00024043626,"threshold_uncertainty_score":0.9990271},"labels":[],"label_agreement":null},{"id":"W4387392671","doi":"10.3758/s13428-023-02248-5","title":"Negative affective priming: Reliability and associations with depression symptoms in three samples","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","field":"Psychology","cited_by":1,"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 Calgary","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Nap; Psychology; Reliability (semiconductor); Priming (agriculture); Audiology; Internal consistency; Task (project management); Analysis of variance; Depression (economics); Clinical psychology; Developmental psychology; Psychometrics; Medicine; Social psychology; Internal medicine","score_opus":0.2972621905165959,"score_gpt":0.5732007862776924,"score_spread":0.27593859576109653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387392671","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":[0.98517853,0.0008493197,0.007975483,0.00015786747,0.00027747062,0.0021287159,0.00011353002,0.00022431307,0.0030947896],"genre_scores_gemma":[0.9645316,0.00077141915,0.030296262,0.000014893618,0.000098780474,0.0035436307,0.00005168161,0.000079616475,0.00061212474],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9923674,0.0042417236,0.00036433744,0.0012428673,0.0008394659,0.00094420934],"domain_scores_gemma":[0.9875903,0.010532835,0.0001625435,0.0006492845,0.0008121414,0.0002529016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074660443,0.00029877396,0.00044479425,0.0014663026,0.00049416954,0.00010786156,0.00034426147,0.0002958905,0.00021837659],"category_scores_gemma":[0.008124806,0.00023749245,0.000071765295,0.0047532893,0.00059379183,0.00028541795,0.00037008792,0.000989388,0.0000724975],"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":[0.00016525618,0.00049998483,0.6705043,0.000016754528,0.000046265235,0.000025560212,0.0027272822,0.0000018313655,0.00043439743,0.0001367298,0.00020960151,0.32523206],"study_design_scores_gemma":[0.0016233058,0.00041458796,0.9842801,0.000086644344,0.00005746473,0.00000705037,0.0031534408,0.00002479461,0.0023233609,0.0070569166,0.00072168733,0.00025063968],"about_ca_topic_score_codex":0.0019009735,"about_ca_topic_score_gemma":0.0005333565,"teacher_disagreement_score":0.32498142,"about_ca_system_score_codex":0.00035519275,"about_ca_system_score_gemma":0.00014718363,"threshold_uncertainty_score":0.97267383},"labels":[],"label_agreement":null},{"id":"W4388706574","doi":"10.3758/s13428-023-02280-5","title":"Author Correction: Can musical ability be tested online?","year":2023,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Diverse Music Education Insights","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 Toronto","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Musical; Computer science; Speech recognition; Psychology; Visual arts; Art","score_opus":0.614351461010834,"score_gpt":0.5641746966113369,"score_spread":0.05017676439949714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388706574","genre_codex":"editorial","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":[0.006419272,0.00026238247,0.000044146884,0.013650776,0.61741793,0.004016125,0.0032403218,0.0017890707,0.35315996],"genre_scores_gemma":[0.00016769955,0.000032239554,0.0031355943,0.00019259044,0.014966328,0.0010907486,0.002323259,0.00020760641,0.97788393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902969,0.0043278695,0.0008082074,0.0013035013,0.0021143313,0.0011491623],"domain_scores_gemma":[0.99244815,0.002586747,0.00023356399,0.0016401312,0.002522878,0.00056855066],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006378163,0.0005399915,0.00081057684,0.0012687038,0.0015294759,0.0010379207,0.0011203456,0.00069911417,0.023080735],"category_scores_gemma":[0.005066124,0.0004933004,0.00039015381,0.0007171298,0.0020241363,0.00019219037,0.000639912,0.0051289136,0.00061326445],"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":[0.0000140413185,0.00076042075,0.000037451595,0.00010890776,0.00004529939,0.000071107585,0.020488858,1.4017448e-7,0.00002484417,0.0039086873,0.9450531,0.029487139],"study_design_scores_gemma":[0.00016161444,0.00018628669,0.003646817,0.00016096988,0.00012057143,0.0000075110547,0.017706353,0.000040725576,0.000014497181,0.0005657486,0.97689176,0.00049714633],"about_ca_topic_score_codex":0.009964678,"about_ca_topic_score_gemma":0.018741533,"teacher_disagreement_score":0.624724,"about_ca_system_score_codex":0.0008736154,"about_ca_system_score_gemma":0.0024181202,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W4388725852","doi":"10.3758/s13428-023-02285-0","title":"Retraction Note: Eye tracking: empirical foundations for a minimal reporting guideline","year":2023,"lang":"en","type":"retraction","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":2,"is_retracted":true,"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; SR Research (Canada)","funders":"","keywords":"Guideline; Computer science; Eye tracking; Tracking (education); Artificial intelligence; Optometry; Psychology; Medicine","score_opus":0.6596814002210868,"score_gpt":0.6967781457215364,"score_spread":0.03709674550044961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388725852","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":[0.0006989478,0.00024321643,0.9814091,0.005400933,0.0075952355,0.0018563156,0.00006877553,0.0017020289,0.0010254476],"genre_scores_gemma":[0.0010289494,0.00023476587,0.9745098,0.00004102175,0.0019497534,0.0021544197,0.0005488762,0.00017746461,0.019354999],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.989715,0.002072422,0.0029652063,0.0019661393,0.0018252636,0.0014559688],"domain_scores_gemma":[0.98797923,0.0045651584,0.0021960249,0.0018476521,0.003138062,0.00027388235],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.03915319,0.0004952473,0.0009739667,0.0022724746,0.0011533713,0.00074312487,0.0018127791,0.002300074,0.00004965373],"category_scores_gemma":[0.0434816,0.0004972808,0.0006051852,0.003078166,0.00033196423,0.00056970154,0.0006604783,0.005241739,0.000120942954],"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":[0.000021558635,0.0002879239,0.00041164114,0.0001346046,0.000036805766,0.00015277654,0.00014295364,0.000003650512,0.005430334,0.00043397112,0.14786421,0.8450796],"study_design_scores_gemma":[0.0004198736,0.0006015696,0.0154820345,0.0002639448,0.00013003955,0.00015453938,0.00013850525,0.010479894,0.003967417,0.0025499,0.9650946,0.000717643],"about_ca_topic_score_codex":0.00021712063,"about_ca_topic_score_gemma":0.000055960747,"teacher_disagreement_score":0.84436196,"about_ca_system_score_codex":0.0009972666,"about_ca_system_score_gemma":0.001486592,"threshold_uncertainty_score":0.9997479},"labels":[],"label_agreement":null},{"id":"W4388821770","doi":"10.3758/s13428-023-02246-7","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Type I and type II errors; Null hypothesis; Outlier; Relation (database); Artificial intelligence; Data mining; Machine learning; Statistics; Algorithm; Mathematics","score_opus":0.6771024707565433,"score_gpt":0.6449932992528221,"score_spread":0.03210917150372117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388821770","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":[0.80802524,0.00006503999,0.19059499,0.00005795108,0.00009636611,0.00060107576,0.0000055872206,0.00044678894,0.00010696634],"genre_scores_gemma":[0.7767241,0.000060250193,0.22260605,0.00000276911,0.000015843449,0.00031169684,0.0000069362077,0.000034508448,0.00023783311],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961967,0.0020849698,0.00045555772,0.00028642832,0.0005726946,0.0004036649],"domain_scores_gemma":[0.99613565,0.0026975106,0.000066313994,0.00047193322,0.0005367212,0.000091890885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013750975,0.00012390391,0.0002760208,0.0009540042,0.0001137249,0.00002682461,0.0002465256,0.00017525708,0.000023292461],"category_scores_gemma":[0.014720839,0.00012115338,0.00006504906,0.0021978482,0.00011596441,0.00011282212,0.00012323726,0.000456549,0.000022608228],"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":[0.0002257004,0.0008436152,0.024635455,0.0006968249,0.00002145016,0.000051144132,0.0031904855,0.0011857499,0.48314565,0.0027265109,0.0009191345,0.48235828],"study_design_scores_gemma":[0.0008221921,0.0005605182,0.12079134,0.0008824787,0.000045649005,0.000014898439,0.000411471,0.24546996,0.34924877,0.28118154,0.000084243926,0.00048693453],"about_ca_topic_score_codex":0.00044584772,"about_ca_topic_score_gemma":0.00011931608,"teacher_disagreement_score":0.48187134,"about_ca_system_score_codex":0.000121118755,"about_ca_system_score_gemma":0.00013526356,"threshold_uncertainty_score":0.9935786},"labels":[],"label_agreement":null},{"id":"W4388913253","doi":"10.3758/s13428-023-02238-7","title":"Disaggregating level-specific effects in cross-classified multilevel models","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Conflation; Multilevel model; Computer science; Cluster (spacecraft); Random effects model; Artificial intelligence; Machine learning; Meta-analysis; Linguistics","score_opus":0.8313128540076932,"score_gpt":0.7245869789737178,"score_spread":0.10672587503397535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388913253","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":[0.96736073,0.0007843197,0.013049538,0.00035889522,0.0014590372,0.0039103143,0.00007675069,0.00034358175,0.012656799],"genre_scores_gemma":[0.81486714,0.0002372591,0.12804447,0.00007344388,0.00047822105,0.009497666,0.000094575225,0.00026497807,0.04644223],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98472536,0.008861068,0.00081894046,0.0011754014,0.0016965781,0.0027226505],"domain_scores_gemma":[0.9909369,0.006704678,0.0000960894,0.0012994573,0.00031179358,0.00065113604],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02286048,0.00030935748,0.00051288336,0.0015062918,0.00054097857,0.00020500261,0.0010452762,0.000413492,0.0010246534],"category_scores_gemma":[0.0017417541,0.00030197314,0.00013850133,0.002813573,0.0006401814,0.0003142032,0.0007853027,0.0024653594,0.0016467208],"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":[0.00022895819,0.0005797025,0.027425554,0.00025977017,0.000014124738,0.0011172557,0.0040368605,0.00003182552,0.011715523,0.012485251,0.0027889663,0.9393162],"study_design_scores_gemma":[0.003270454,0.00039760108,0.9627699,0.0002588703,0.00000486455,0.00002435394,0.0017463509,0.008043342,0.005642289,0.010325854,0.0070297243,0.0004863959],"about_ca_topic_score_codex":0.0013077545,"about_ca_topic_score_gemma":0.00009467155,"teacher_disagreement_score":0.93882984,"about_ca_system_score_codex":0.0006818597,"about_ca_system_score_gemma":0.00021798372,"threshold_uncertainty_score":0.99994326},"labels":[],"label_agreement":null},{"id":"W4388927230","doi":"10.3758/s13428-023-02283-2","title":"Denver pain authenticity stimulus set (D-PASS)","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Pain Mechanisms and Treatments","field":"Medicine","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, Okanagan Campus; University of British Columbia","funders":"National Institute on Minority Health and Health Disparities","keywords":"Codebook; Stimulus (psychology); Psychology; Facial expression; Perception; Set (abstract data type); Social psychology; Computer science; Cognitive psychology; Artificial intelligence; Communication; Neuroscience","score_opus":0.4863341374594835,"score_gpt":0.6389944832909215,"score_spread":0.15266034583143795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388927230","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":[0.9717833,0.00012917152,0.02327165,0.0009563132,0.00027684023,0.0017789212,0.000043129887,0.00045985045,0.0013008383],"genre_scores_gemma":[0.7456399,0.00010096555,0.21477717,0.0002353365,0.00022509304,0.001297285,0.00018123462,0.00012927502,0.037413716],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936005,0.0036771179,0.00026136133,0.00048954645,0.0010624886,0.00090898713],"domain_scores_gemma":[0.9972345,0.0013311383,0.00003449848,0.00068360363,0.00025057464,0.00046566917],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019511897,0.00018106679,0.00034480865,0.00053017156,0.00028885945,0.00005130374,0.00020796111,0.00016519759,0.0009917665],"category_scores_gemma":[0.0025767994,0.00014700268,0.00016079735,0.0012716333,0.00014638818,0.000065291504,0.00023616798,0.00058011466,0.0009668899],"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":[0.00023012045,0.001154921,0.09422882,0.00017106508,0.00018257955,0.0040437025,0.0011337735,0.0000022647155,0.17360747,0.0008964016,0.016252242,0.7080966],"study_design_scores_gemma":[0.0052444763,0.002330125,0.8458334,0.0002702204,0.00045384816,0.000118281096,0.0020874767,0.008934715,0.08450895,0.0072890082,0.04229705,0.0006324279],"about_ca_topic_score_codex":0.0002421753,"about_ca_topic_score_gemma":0.0000098846585,"teacher_disagreement_score":0.7516046,"about_ca_system_score_codex":0.00020964514,"about_ca_system_score_gemma":0.00018314217,"threshold_uncertainty_score":0.99992144},"labels":[],"label_agreement":null},{"id":"W4389075303","doi":"10.3758/s13428-023-02273-4","title":"Attention in hindsight: Using stimulated recall to capture dynamic fluctuations in attentional engagement","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recall; Generalizability theory; Psychology; Cognitive psychology; Hindsight bias; CLIPS; Mnemonic; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.5403413114135511,"score_gpt":0.6165809254192173,"score_spread":0.07623961400566615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389075303","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":[0.9867842,0.000012097395,0.011169586,0.00055139227,0.00027150515,0.0009926758,0.000017979812,0.0000883413,0.00011220027],"genre_scores_gemma":[0.98190284,0.000014603077,0.015389622,0.00002949046,0.00002286224,0.00031712226,0.000040295407,0.000031703203,0.0022514758],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99391377,0.0034136847,0.00043302547,0.0006860831,0.0008586961,0.0006947597],"domain_scores_gemma":[0.9987847,0.0006034918,0.000046038633,0.0003152035,0.0001052085,0.00014535179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007247342,0.00014752666,0.00018766668,0.0018929285,0.00031048083,0.00010800934,0.0002968055,0.00012306943,0.00021238408],"category_scores_gemma":[0.0017916594,0.0001504704,0.00007592913,0.0038055389,0.00007763587,0.00018953497,0.00026342322,0.0008016265,0.00015171997],"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":[0.000023829407,0.00019535173,0.006724667,0.000016619693,0.000001357985,0.0001144357,0.00044610124,0.0036749772,0.9708387,0.0001346053,0.000051275096,0.01777805],"study_design_scores_gemma":[0.0010035025,0.000091841684,0.8701339,0.00020405753,0.000011605641,0.000012574142,0.0008146633,0.10940367,0.016695946,0.0008867555,0.00042982132,0.00031166937],"about_ca_topic_score_codex":0.00030855983,"about_ca_topic_score_gemma":0.00016926853,"teacher_disagreement_score":0.9541428,"about_ca_system_score_codex":0.0004391701,"about_ca_system_score_gemma":0.000099523524,"threshold_uncertainty_score":0.6136005},"labels":[],"label_agreement":null},{"id":"W4389129333","doi":"10.3758/s13428-023-02247-6","title":"Does strict invariance matter? Valid group mean comparisons with ordered-categorical items","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":29,"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":"Polytomous Rasch model; Measurement invariance; Categorical variable; Mathematics; Statistics; Scalar (mathematics); Factor analysis; Item response theory; Confirmatory factor analysis; Psychometrics; Structural equation modeling; Geometry","score_opus":0.8548829296835958,"score_gpt":0.6812477469221532,"score_spread":0.17363518276144263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389129333","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":[0.38887933,0.0002535101,0.58921,0.0031131138,0.0018611972,0.0018264223,0.000057569385,0.0006691259,0.014129786],"genre_scores_gemma":[0.41374004,0.000058347705,0.5797751,0.00007162117,0.0002590348,0.0005025362,0.000016059063,0.00006918427,0.005508106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97215366,0.018483132,0.001205803,0.0016462596,0.0048384,0.0016727332],"domain_scores_gemma":[0.8819157,0.114091985,0.00034338192,0.0020086237,0.001058348,0.00058196037],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.09698318,0.00034202213,0.0008706169,0.0026738932,0.0009892049,0.0010611019,0.002867051,0.00022564737,0.001290971],"category_scores_gemma":[0.07725983,0.00017433245,0.00018724558,0.02128239,0.00060349377,0.00041988798,0.0011611275,0.0014174372,0.0010384034],"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":[0.000170274,0.0003349662,0.582754,0.000020244892,0.0000332909,0.00029000203,0.00045738852,0.00003603299,0.0075715184,0.002353738,0.046396047,0.3595825],"study_design_scores_gemma":[0.0007965682,0.0005016102,0.9068286,0.000033122582,0.00003054459,0.000057831563,0.007405352,0.001446115,0.0017707533,0.02315564,0.057449106,0.00052479183],"about_ca_topic_score_codex":0.00064223906,"about_ca_topic_score_gemma":0.00006451687,"teacher_disagreement_score":0.3590577,"about_ca_system_score_codex":0.00013386966,"about_ca_system_score_gemma":0.0001922306,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4389475103","doi":"10.3758/s13428-023-02293-0","title":"Diversity, equity, and inclusivity in observational ambulatory assessment: Recommendations from two decades of Electronically Activated Recorder (EAR) research","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Health Policy Implementation Science","field":"Health Professions","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 Toronto","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Institute on Aging; National Cancer Institute; National Institutes of Health; National Institute of Environmental Health Sciences; Mind and Life Institute","keywords":"Observational study; Psychology; Observational methods in psychology; Experience sampling method; Medical education; Applied psychology; Medicine; Social psychology","score_opus":0.967125737717084,"score_gpt":0.8695035739139877,"score_spread":0.0976221638030963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389475103","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":[0.9740431,0.00001803827,0.00057829183,0.02165283,0.0001697823,0.0019213246,0.00019446657,0.00007407076,0.00134813],"genre_scores_gemma":[0.93014604,0.00035226435,0.06697467,0.0006528925,0.00013675287,0.0009245199,0.000118356205,0.000036935555,0.0006575932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96120423,0.03233629,0.0011405397,0.0007199666,0.0027683387,0.0018306555],"domain_scores_gemma":[0.9600669,0.037097696,0.00023476357,0.0005670876,0.0015927089,0.00044080414],"candidate_categories":["metaresearch","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10187192,0.00014903996,0.00039640014,0.0017398975,0.0044754418,0.000044497083,0.0010399619,0.00023402691,0.0013291547],"category_scores_gemma":[0.012817585,0.00015443229,0.000044225155,0.005472275,0.00060999615,0.000541499,0.021125074,0.0032143423,0.00005343503],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006385012,0.00012335334,0.8481764,0.00008533232,0.00001209893,0.000006427347,0.008490278,0.0000028779907,0.06440215,0.0038010306,0.0046345745,0.07020162],"study_design_scores_gemma":[0.0011758471,0.00012613497,0.9589107,0.00011140338,0.000005678359,3.368069e-7,0.0041274857,0.00030400028,0.0011604184,0.02447757,0.00947619,0.00012422971],"about_ca_topic_score_codex":0.021897206,"about_ca_topic_score_gemma":0.00783543,"teacher_disagreement_score":0.1107343,"about_ca_system_score_codex":0.0014415666,"about_ca_system_score_gemma":0.0040553967,"threshold_uncertainty_score":0.9995838},"labels":[],"label_agreement":null},{"id":"W4389574735","doi":"10.3758/s13428-023-02299-8","title":"Road Hazard Stimuli: Annotated naturalistic road videos for studying hazard detection and scene perception","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Traffic and Road Safety","field":"Engineering","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":"General Electric (Canada); University of Toronto","funders":"","keywords":"Computer science; CLIPS; Perception; Replicate; Set (abstract data type); Hazard; Visual perception; Artificial intelligence; Cognitive psychology; Psychology","score_opus":0.23866927227371765,"score_gpt":0.5051115392190106,"score_spread":0.266442266945293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389574735","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":[0.9492902,0.00031727008,0.046984814,0.00008016412,0.00064987346,0.0014911878,0.00004278233,0.0010725914,0.00007112718],"genre_scores_gemma":[0.9600357,0.00023768914,0.038248044,0.000005532709,0.00017335794,0.0007282403,0.00005016283,0.0000911605,0.0004301145],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972602,0.0006569687,0.0003490926,0.0004609532,0.0004942774,0.00077850284],"domain_scores_gemma":[0.99869776,0.00045609561,0.00002693586,0.00031712544,0.00028379846,0.0002182692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040016794,0.0002356423,0.00031052035,0.0005543709,0.0005275981,0.0001294627,0.00019989315,0.00022324067,0.000034340348],"category_scores_gemma":[0.0005205706,0.00022397157,0.00010114976,0.0010590912,0.00013176525,0.00020697222,0.000116358446,0.00069094775,0.000048369442],"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":[0.0000683668,0.000032265747,0.0008027314,0.0001214685,0.00002749211,0.000016666263,0.0006196778,0.0017219905,0.16157235,0.000005702326,0.00034104637,0.83467025],"study_design_scores_gemma":[0.0009468033,0.00022516648,0.7248561,0.000060615595,0.00006384801,0.000017975506,0.0011881489,0.26653314,0.0040685884,0.000054463526,0.0016394601,0.0003457089],"about_ca_topic_score_codex":0.000089086665,"about_ca_topic_score_gemma":0.00006972543,"teacher_disagreement_score":0.83432454,"about_ca_system_score_codex":0.00022934738,"about_ca_system_score_gemma":0.000037079262,"threshold_uncertainty_score":0.91332954},"labels":[],"label_agreement":null},{"id":"W4390222853","doi":"10.3758/s13428-023-02242-x","title":"Feats: A database of semantic features for early produced noun concepts","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":6,"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":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Institute on Deafness and Other Communication Disorders; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University","keywords":"Computer science; Vocabulary; Natural language processing; Noun; Artificial intelligence; Feature (linguistics); Set (abstract data type); Semantic feature; Semantic network; Linguistics","score_opus":0.35746756208848407,"score_gpt":0.633920496594131,"score_spread":0.2764529345056469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390222853","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":[0.99318194,0.00043827298,0.00069111853,0.0006429281,0.00059028243,0.0020270448,0.00012850513,0.0001858918,0.0021140133],"genre_scores_gemma":[0.86839825,0.000050628325,0.08943781,0.000048454414,0.00039240957,0.002230513,0.00022852057,0.0001183737,0.03909502],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99610937,0.0015238501,0.0003332463,0.000681864,0.0005565664,0.00079511455],"domain_scores_gemma":[0.9972806,0.0014124505,0.000082109924,0.00068674254,0.00037677298,0.00016131636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008032673,0.0001674504,0.00034613063,0.00046882938,0.00024166494,0.000049014936,0.00045658078,0.0001234359,0.0004327061],"category_scores_gemma":[0.0016932697,0.00014654477,0.00013287787,0.0010869807,0.00025114734,0.00006774019,0.00024850597,0.0005726209,0.00021127028],"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":[0.0008942135,0.0008602113,0.06179687,0.00035932125,0.00016724499,0.00020393814,0.014160773,7.896063e-7,0.53279376,0.009159568,0.057241667,0.32236168],"study_design_scores_gemma":[0.0011768626,0.00063750497,0.9325136,0.00013659666,0.00003892699,0.000016926535,0.0017121761,0.000005604977,0.033083938,0.00020906173,0.030220417,0.0002484142],"about_ca_topic_score_codex":0.00027931144,"about_ca_topic_score_gemma":0.000010374614,"teacher_disagreement_score":0.8707167,"about_ca_system_score_codex":0.000045347282,"about_ca_system_score_gemma":0.00015229388,"threshold_uncertainty_score":0.59759223},"labels":[],"label_agreement":null},{"id":"W4390938888","doi":"10.3758/s13428-023-02326-8","title":"What do we manipulate when reminding people of (not) having control? In search of construct validity","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Social and Intergroup Psychology","field":"Social Sciences","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 Toronto","funders":"Narodowa Agencja Wymiany Akademickiej; Narodowe Centrum Nauki; Fundacja na rzecz Nauki Polskiej; Uniwersytet Jagielloński w Krakowie; Narodowym Centrum Nauki; Deutsche Forschungsgemeinschaft","keywords":"Construct (python library); Recall; Control (management); Psychology; Comparability; Construct validity; Social psychology; Cognitive psychology; Sense of control; Locus of control; Emotionality; Developmental psychology; Computer science; Psychometrics; Artificial intelligence","score_opus":0.4821986946205014,"score_gpt":0.6286153137827989,"score_spread":0.14641661916229748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390938888","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":[0.98932165,0.0024622953,0.0011023681,0.001628979,0.0013609013,0.00074735977,0.000017363802,0.000042986652,0.0033161237],"genre_scores_gemma":[0.9899477,0.0021007438,0.006765415,0.000010147577,0.00013765812,0.0000793302,0.0000016289142,0.000023602215,0.00093379064],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9899752,0.007148656,0.00056842674,0.00046071783,0.0010835722,0.00076343614],"domain_scores_gemma":[0.9957129,0.0033909401,0.000072819945,0.00030657218,0.00035384003,0.00016292956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023867,0.00012842572,0.00048741672,0.00067919557,0.00023199811,0.0002144983,0.0006164408,0.00027316282,0.0009946735],"category_scores_gemma":[0.0011976017,0.00012324084,0.00018653089,0.0012381023,0.0011743775,0.0005089773,0.00018899921,0.00085639633,0.000014593633],"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":[0.00016591861,0.00023697238,0.13713352,0.00022481832,0.00004378416,0.00009707167,0.1060829,0.0000012910589,0.1620624,0.036581863,0.0003665069,0.55700296],"study_design_scores_gemma":[0.0031598653,0.0013421044,0.37879595,0.0049616597,0.00019810775,0.000043668057,0.42265427,0.00053669576,0.07491531,0.072038665,0.04014831,0.0012053922],"about_ca_topic_score_codex":0.0085601015,"about_ca_topic_score_gemma":0.0015759158,"teacher_disagreement_score":0.5557976,"about_ca_system_score_codex":0.00028591027,"about_ca_system_score_gemma":0.00042104052,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W4392446616","doi":"10.3758/s13428-024-02352-0","title":"Lightness constancy in reality, in virtual reality, and on flat-panel displays","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Virtual reality; Achromatic lens; Computer science; Perception; Headset; Lightness; Immersion (mathematics); Depth perception; Virtual machine; Display device; Computer vision; Computer graphics (images); Artificial intelligence; Human–computer interaction; Psychology; Mathematics; Optics; Physics","score_opus":0.5964500043183114,"score_gpt":0.621109479030278,"score_spread":0.02465947471196661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392446616","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":[0.98413545,0.00015054546,0.0053218575,0.0022259287,0.0005195649,0.0008319054,0.000058919042,0.0001683652,0.006587464],"genre_scores_gemma":[0.9965635,0.00022533751,0.0012002011,0.0001235728,0.000057671823,0.00019877197,0.0000048183847,0.00003750076,0.001588631],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9926172,0.0046452205,0.00040206366,0.0008982166,0.00080539216,0.0006319424],"domain_scores_gemma":[0.99741983,0.0019359603,0.000025793235,0.000355579,0.000050006955,0.00021283649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0094477795,0.00018894432,0.00027677926,0.0006504794,0.00018029638,0.00037616727,0.00034219451,0.0001882155,0.00019832877],"category_scores_gemma":[0.0017035813,0.00016627586,0.00004532604,0.0015955104,0.00041037353,0.00026415527,0.0002857363,0.0012185848,0.00006966261],"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":[0.00010695017,0.00023921732,0.00037981445,0.000118526325,7.7202543e-7,0.0005813958,0.0017530767,0.000004496153,0.701135,0.051757332,0.00018617805,0.24373727],"study_design_scores_gemma":[0.0023039342,0.001953004,0.05845046,0.0021577151,0.000023965555,0.00029383917,0.0026635667,0.012192079,0.8505076,0.05583269,0.012326311,0.0012947912],"about_ca_topic_score_codex":0.00030909924,"about_ca_topic_score_gemma":0.00023609566,"teacher_disagreement_score":0.24244247,"about_ca_system_score_codex":0.00017235249,"about_ca_system_score_gemma":0.00015553363,"threshold_uncertainty_score":0.6780533},"labels":[],"label_agreement":null},{"id":"W4392583385","doi":"10.3758/s13428-024-02363-x","title":"Mobile version of the Battery for the Assessment of Auditory Sensorimotor and Timing Abilities (BAASTA): Implementation and adult norms","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":16,"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; Université de Montréal; International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music; Bell (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Société d'Accélération du Transfert de Technologies","keywords":"Rhythm; Computer science; Audiology; Finger tapping; Population; Cognitive psychology; Psychology; Normative; Medicine","score_opus":0.25689492300716626,"score_gpt":0.5927734323046927,"score_spread":0.33587850929752644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392583385","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":[0.9953131,0.000028651311,0.0026957954,0.00018623786,0.0005086891,0.0011460818,0.00007211656,0.000010701353,0.000038615035],"genre_scores_gemma":[0.99444646,0.00018653499,0.004647263,0.00003630714,0.000067098204,0.0003695184,9.904123e-7,0.000009763726,0.0002360949],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981797,0.00067549845,0.00018610478,0.0002916201,0.00046808666,0.00019899844],"domain_scores_gemma":[0.9976705,0.0018983693,0.000044107976,0.0002257489,0.00012567324,0.000035657005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025305254,0.00006866808,0.000095566094,0.00010790064,0.00031068368,0.00006669862,0.00017057457,0.000029037961,0.000038888455],"category_scores_gemma":[0.00041433857,0.000038993985,0.0000450146,0.00029567486,0.00066059,0.00019235034,0.00019779672,0.00018163872,3.1923784e-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":[0.000008334306,0.000023162678,0.0009221379,0.00010720545,8.629993e-7,5.1859354e-7,0.0008108278,0.0000017869603,0.9039064,0.00014495416,0.00034594658,0.09372787],"study_design_scores_gemma":[0.0003173256,0.0006848347,0.18119101,0.000075854834,0.00004174765,0.000013411768,0.008585887,0.0034848233,0.8004905,0.00024889756,0.0047700685,0.00009561386],"about_ca_topic_score_codex":0.000075673175,"about_ca_topic_score_gemma":0.0000062394442,"teacher_disagreement_score":0.18026888,"about_ca_system_score_codex":0.00004760974,"about_ca_system_score_gemma":0.00011425797,"threshold_uncertainty_score":0.24339715},"labels":[],"label_agreement":null},{"id":"W4392947175","doi":"10.3758/s13428-024-02378-4","title":"TAT-HUM: Trajectory analysis toolkit for human movements in Python","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Action Observation and Synchronization","field":"Psychology","cited_by":14,"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; St. Michael's Hospital","funders":"University of Toronto","keywords":"Python (programming language); Computer science; Scripting language; Human–computer interaction; Hum; Kinematics; Trajectory; Movement (music); Artificial intelligence; Programming language","score_opus":0.5418191110815244,"score_gpt":0.691732494680939,"score_spread":0.14991338359941464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392947175","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":[0.6290785,0.00056880113,0.36039656,0.00032831976,0.0010368259,0.0017206734,0.00005783527,0.00023715725,0.006575305],"genre_scores_gemma":[0.8800067,0.000023636037,0.042273298,0.00012126775,0.00028727853,0.0033547985,0.00037268375,0.000097861885,0.07346251],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99612904,0.0020042262,0.0004281127,0.0005464837,0.00042640156,0.00046571816],"domain_scores_gemma":[0.99858326,0.0006483591,0.000039509745,0.00041265372,0.00021217325,0.000104066086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007219895,0.00012769728,0.00024370845,0.0016058872,0.00018634234,0.00013674455,0.00023457078,0.00017296431,0.0054994454],"category_scores_gemma":[0.00022315237,0.0001274339,0.00018692901,0.0028379296,0.00008493023,0.00016850674,0.000045700468,0.00035439612,0.00009297044],"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":[0.00014118022,0.0013527406,0.14769538,0.00016668382,0.00069196784,0.00011784014,0.009862225,0.0001043588,0.078357,0.029947514,0.012648979,0.71891415],"study_design_scores_gemma":[0.0012297785,0.00037973182,0.8426104,0.000039016526,0.00021946222,0.0000031175837,0.003604399,0.003644662,0.0035387452,0.002286996,0.1420375,0.00040617856],"about_ca_topic_score_codex":0.00051269797,"about_ca_topic_score_gemma":0.00027717295,"teacher_disagreement_score":0.71850795,"about_ca_system_score_codex":0.00031598858,"about_ca_system_score_gemma":0.00007696278,"threshold_uncertainty_score":0.99540967},"labels":[],"label_agreement":null},{"id":"W4393142761","doi":"10.3758/s13428-024-02356-w","title":"Check your outliers! An introduction to identifying statistical outliers in R with easystats","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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":"Université du Québec à Montréal","funders":"","keywords":"Outlier; Univariate; Computer science; Anomaly detection; Preprint; Transparency (behavior); Software; Data mining; Statistical analysis; Statistical model; R package; Multivariate statistics; Artificial intelligence; Data science; Machine learning; Statistics; Mathematics; World Wide Web; Programming language; Computer security","score_opus":0.628588452955993,"score_gpt":0.6929784310768745,"score_spread":0.06438997812088154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393142761","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":[0.037547983,0.00007433587,0.9595715,0.0006298788,0.00039899623,0.0012626963,0.00008555657,0.00018144162,0.00024760858],"genre_scores_gemma":[0.027387239,0.000009895369,0.9700256,0.00001696768,0.0003484865,0.00069146336,0.0000182704,0.00012091636,0.0013811785],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927728,0.003358365,0.0005937798,0.0011172389,0.0011161146,0.0010416689],"domain_scores_gemma":[0.99570364,0.0025966777,0.000039865663,0.0007138405,0.00031555587,0.00063040893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01311875,0.00028376636,0.00050699187,0.0007930272,0.0001956977,0.00033166463,0.000345025,0.0001419831,0.00024386175],"category_scores_gemma":[0.0060442043,0.00023311596,0.000054257973,0.0012552395,0.000262811,0.0004068593,0.00018246654,0.0012630108,0.00003812612],"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":[0.00033044373,0.0005221084,0.00030747257,0.0004948038,0.00003547202,0.00081620144,0.004645278,0.0000661125,0.020472156,0.3751978,0.0015534362,0.5955587],"study_design_scores_gemma":[0.0012744374,0.0023489574,0.0062255007,0.0005500302,0.00022963942,0.00018374804,0.012694891,0.011750809,0.008037245,0.9391611,0.016150339,0.0013933083],"about_ca_topic_score_codex":0.00010940986,"about_ca_topic_score_gemma":0.00009804629,"teacher_disagreement_score":0.5941654,"about_ca_system_score_codex":0.00045179855,"about_ca_system_score_gemma":0.0002176183,"threshold_uncertainty_score":0.9506193},"labels":[],"label_agreement":null},{"id":"W4393408830","doi":"10.3758/s13428-024-02384-6","title":"Examining the performance of the chi-square difference test when the unrestricted model is slightly misspecified","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Nested set model; Context (archaeology); Statistics; Test (biology); Econometrics; Structural equation modeling; Statistical hypothesis testing; Chi-square test; Mean squared error; Mathematics; Computer science; Data mining","score_opus":0.8815597692413241,"score_gpt":0.6416555860264059,"score_spread":0.23990418321491813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393408830","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":[0.96305823,0.0019346633,0.025688658,0.0028757055,0.0008118467,0.0009710828,0.000047134272,0.000084081126,0.0045286044],"genre_scores_gemma":[0.89907974,0.00020418971,0.089262955,0.0001013746,0.00015837309,0.00022062435,8.196057e-7,0.000034091427,0.01093785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.986015,0.0074625523,0.0009956815,0.0008851916,0.003838476,0.00080307684],"domain_scores_gemma":[0.8402189,0.15528546,0.00028777012,0.003067341,0.0009787536,0.00016177852],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051863663,0.00025534746,0.00041414925,0.00062401406,0.0011876595,0.0008299726,0.005344063,0.00015862416,0.00035238636],"category_scores_gemma":[0.10527421,0.00009607773,0.00023403144,0.007940572,0.0009662933,0.0001932107,0.0014704807,0.0017238782,0.00003188386],"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":[0.000027834789,0.00010109772,0.09642911,0.00003109833,0.000020105283,0.000007722775,0.0042126165,0.00010260327,0.02577219,0.0009793227,0.007926655,0.86438966],"study_design_scores_gemma":[0.00019858785,0.00027640385,0.80728006,0.00019438346,0.000046118632,0.000030649455,0.0034048893,0.15212521,0.016782982,0.010668768,0.008750347,0.00024158112],"about_ca_topic_score_codex":0.00011407566,"about_ca_topic_score_gemma":0.000005797638,"teacher_disagreement_score":0.8641481,"about_ca_system_score_codex":0.000077395394,"about_ca_system_score_gemma":0.00037939675,"threshold_uncertainty_score":0.99306875},"labels":[],"label_agreement":null},{"id":"W4394592969","doi":"10.3758/s13428-024-02401-8","title":"Using virtual reality to induce multi-trial inattentional blindness despite trial-by-trial measures of awareness","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":8,"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":"Tel Aviv University; Milner Foundation; Canadian Institute for Advanced Research","keywords":"Inattentional blindness; Blindness; Virtual reality; Psychology; Computer science; Cognitive psychology; Applied psychology; Human–computer interaction; Perception; Medicine; Optometry; Neuroscience","score_opus":0.9190297617559202,"score_gpt":0.7144993092485171,"score_spread":0.2045304525074031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394592969","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":[0.9825378,0.00013133544,0.0071773515,0.00044852847,0.005201353,0.0041033234,0.00022633439,0.00012997004,0.00004399368],"genre_scores_gemma":[0.9911941,0.000032672495,0.005313733,0.00006531884,0.0006696132,0.0013105678,0.000010150469,0.00006976962,0.0013340472],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.987622,0.0071450216,0.0009550292,0.0014264161,0.0019220219,0.00092946395],"domain_scores_gemma":[0.9964494,0.0019404861,0.0001312723,0.0006473244,0.0004934047,0.0003381276],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010161509,0.00035852552,0.0006763982,0.00080679206,0.0006279933,0.00023820753,0.0009097744,0.00031676778,0.000102972925],"category_scores_gemma":[0.004317203,0.00029525315,0.00033105482,0.0023466225,0.0009445385,0.00035088716,0.0007046291,0.0012284144,0.00003245734],"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":[0.15945734,0.0019057464,0.00015121848,0.0000230898,0.0000126516825,0.00008841668,0.00018183832,0.000004150129,0.7879179,0.000104792845,0.00053213106,0.04962073],"study_design_scores_gemma":[0.20664959,0.0054424633,0.0010051251,0.00013076396,0.000140302,0.000025686923,0.0002465478,0.00008229689,0.7823641,0.00026847242,0.003095315,0.0005493946],"about_ca_topic_score_codex":0.0005228338,"about_ca_topic_score_gemma":0.0000358687,"teacher_disagreement_score":0.049071334,"about_ca_system_score_codex":0.00019941542,"about_ca_system_score_gemma":0.00043072342,"threshold_uncertainty_score":0.99994993},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4396558685","doi":"10.3758/s13428-024-02431-2","title":"Author Correction: r2mlm: An R package calculating R-squared measures for multilevel models","year":2024,"lang":"en","type":"erratum","venue":"Behavior Research Methods","topic":"Data Analysis with R","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; McGill University","funders":"","keywords":"Statistics; R package; Multilevel model; Mean squared error; Computer science; Mathematics; Econometrics","score_opus":0.5097944911348687,"score_gpt":0.5952947699876017,"score_spread":0.08550027885273292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396558685","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":[0.000021934995,0.0012795238,0.9591763,0.00035232434,0.03373974,0.0021534553,0.0004240562,0.00070471474,0.0021479558],"genre_scores_gemma":[0.00034867763,0.000041279854,0.67445815,0.00003303736,0.0018398487,0.0028827304,0.0009035216,0.00022663723,0.3192661],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9840696,0.0062442017,0.0012017271,0.0030743037,0.0035118042,0.0018983586],"domain_scores_gemma":[0.99008,0.0019428111,0.00032035186,0.004467704,0.0023225104,0.00086662924],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.025764193,0.000821661,0.0012872012,0.0022162944,0.0010432575,0.0027889912,0.0053390535,0.0012069361,0.000069978756],"category_scores_gemma":[0.0037571478,0.00075538247,0.0007657692,0.0026763896,0.0003104633,0.0017471511,0.0021916663,0.0047042514,0.00010056522],"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":[0.000014433815,0.00015192058,0.0000057620396,0.00017269106,0.00009607706,0.00010582922,0.0011105697,0.00008258371,0.00062314695,0.0013239805,0.5478676,0.4484454],"study_design_scores_gemma":[0.00023731726,0.00030543815,0.00013052073,0.00036300567,0.00024494165,0.000041287738,0.00028864644,0.7158188,0.0007827913,0.0044517,0.27652365,0.00081188383],"about_ca_topic_score_codex":0.0012430012,"about_ca_topic_score_gemma":0.00039064145,"teacher_disagreement_score":0.71573627,"about_ca_system_score_codex":0.00077846705,"about_ca_system_score_gemma":0.0019279607,"threshold_uncertainty_score":0.9994897},"labels":[],"label_agreement":null},{"id":"W4396558963","doi":"10.3758/s13428-024-02412-5","title":"Measures of angularity in digital images","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Aesthetic Perception and Analysis","field":"Neuroscience","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":"Brandon University","funders":"","keywords":"Computer science; Curvilinear coordinates; Discriminative model; Artificial intelligence; Scripting language; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.5282680905636027,"score_gpt":0.6166722057195967,"score_spread":0.088404115155994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396558963","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":[0.9847829,0.00032585638,0.008425989,0.0003195937,0.00006830466,0.00021294432,0.00003518064,0.00007385141,0.005755387],"genre_scores_gemma":[0.99194163,0.00007601548,0.0055469098,0.000011186068,0.000017493463,0.00004540631,0.0000012167119,0.000013240009,0.002346916],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974779,0.0009815365,0.0002193797,0.00035394114,0.0006758105,0.00029146008],"domain_scores_gemma":[0.999247,0.00030110232,0.000014006472,0.0002699023,0.00007964769,0.00008833095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034580089,0.00007652488,0.00016207327,0.0005448875,0.00005761666,0.00017092077,0.00028600259,0.000054506323,0.00036007777],"category_scores_gemma":[0.0021808285,0.000062821986,0.0001156046,0.0013179078,0.00041068593,0.00022454986,0.00013232075,0.00042328896,0.00006400176],"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":[0.000005127013,0.000107562766,0.0020979976,0.000012818718,4.5130363e-7,0.000087315,0.0002200135,7.785326e-7,0.6210106,0.0006005415,0.00010295867,0.37575382],"study_design_scores_gemma":[0.00030250542,0.0001891886,0.05772328,0.00013488675,0.000026326416,0.00007163949,0.0009578917,0.0011368734,0.91540694,0.0062635057,0.017474158,0.0003128193],"about_ca_topic_score_codex":0.00009121929,"about_ca_topic_score_gemma":0.0000067758765,"teacher_disagreement_score":0.37544098,"about_ca_system_score_codex":0.00005532642,"about_ca_system_score_gemma":0.000095722055,"threshold_uncertainty_score":0.3942599},"labels":[],"label_agreement":null},{"id":"W4396768368","doi":"10.3758/s13428-024-02409-0","title":"Slow and steady: Validating the rhythmic visual response task as a marker for attentional states","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mind wandering and attention","field":"Neuroscience","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":"Queen's University","funders":"","keywords":"Metronome; Cognitive psychology; Mind-wandering; Rhythm; Psychology; Cognition; Task (project management); Stimulus (psychology); Attentional control; Working memory; Neuroscience","score_opus":0.29499827530801165,"score_gpt":0.5895489115772024,"score_spread":0.2945506362691907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396768368","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":[0.98159176,0.00021609604,0.015510541,0.0013556413,0.00026371202,0.00084396166,0.00004978,0.00007924673,0.000089235655],"genre_scores_gemma":[0.9697832,0.00006396429,0.01292302,0.00008021191,0.00016080606,0.0011101809,0.000013100196,0.000053090014,0.015812458],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9939024,0.0041918615,0.00022970822,0.000567894,0.00061764685,0.0004904977],"domain_scores_gemma":[0.9922443,0.0073095905,0.000028775985,0.00021732743,0.00008839021,0.00011163127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0137640685,0.00012792015,0.00012753217,0.000239947,0.0006640658,0.00062812417,0.00018957094,0.00006431611,0.000109528395],"category_scores_gemma":[0.003586374,0.00008896797,0.000098507,0.00045586727,0.00033801387,0.00016427576,0.00019683996,0.00046318417,0.0000341503],"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":[0.0003394623,0.00005002474,0.00017736296,0.000056829533,0.0000052977953,0.00009554844,0.00037495315,0.0000018427771,0.8617372,0.00077224924,0.00055408693,0.13583514],"study_design_scores_gemma":[0.0019059796,0.0021340551,0.06800755,0.0006827328,0.00015559811,0.001066427,0.00441789,0.034013722,0.6811917,0.016213123,0.18927437,0.0009368701],"about_ca_topic_score_codex":0.000028218257,"about_ca_topic_score_gemma":0.0000013690308,"teacher_disagreement_score":0.18872029,"about_ca_system_score_codex":0.0000567291,"about_ca_system_score_gemma":0.00013362963,"threshold_uncertainty_score":0.60570157},"labels":[],"label_agreement":null},{"id":"W4396780632","doi":"10.3758/s13428-024-02376-6","title":"Taboo language across the globe: A multi-lab study","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Swearing, Euphemism, Multilingualism","field":"Social Sciences","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 Alberta","funders":"Agencia Nacional de Investigación y Desarrollo; Ministero dell'Università e della Ricerca; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; Università degli Studi di Milano-Bicocca; Banco Bilbao Vizcaya Argentaria; Deutsche Forschungsgemeinschaft; Comunidad de Madrid; Fundación BBVA","keywords":"Taboo; Globe; Linguistics; Sociocultural evolution; Psychology; Speech community; Valence (chemistry); Social psychology; Sociology; Anthropology; Philosophy","score_opus":0.49207033801001115,"score_gpt":0.7252262250210094,"score_spread":0.23315588701099826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396780632","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":[0.9888782,0.0027699298,0.00081115717,0.0006591071,0.0009483692,0.0022226272,0.000029804523,0.0004699079,0.0032109353],"genre_scores_gemma":[0.93759954,0.000084284766,0.029830003,0.00004799648,0.0010476146,0.0009458512,0.0000035149744,0.00008289769,0.03035828],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9879185,0.007674296,0.00035277475,0.0007446491,0.0019465304,0.0013632798],"domain_scores_gemma":[0.9957138,0.0027094802,0.000043093565,0.00086499995,0.0003604498,0.0003082321],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.040558532,0.00020245221,0.00025513172,0.0001628191,0.0018274169,0.0012018683,0.0014888546,0.00019069927,0.00062762346],"category_scores_gemma":[0.0060015493,0.00014764915,0.00015783185,0.0018725124,0.001103735,0.0002428852,0.0007612167,0.001449674,0.00027231537],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016138954,0.00056095264,0.007484602,0.000021125768,0.00003706947,0.0005568798,0.50489813,6.7373264e-7,0.014772989,0.00057447155,0.00085911836,0.47021785],"study_design_scores_gemma":[0.00083665265,0.00015786647,0.048400193,0.00008078189,0.000074213574,0.000013594061,0.7665995,0.00041014462,0.007823337,0.00015962405,0.17496753,0.00047658646],"about_ca_topic_score_codex":0.029585702,"about_ca_topic_score_gemma":0.0074499333,"teacher_disagreement_score":0.46974126,"about_ca_system_score_codex":0.00039683798,"about_ca_system_score_gemma":0.00058147334,"threshold_uncertainty_score":0.99983495},"labels":[],"label_agreement":null},{"id":"W4399117309","doi":"10.3758/s13428-024-02441-0","title":"Shadows of wisdom: Classifying meta-cognitive and morally grounded narrative content via large language models","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychology of Moral and Emotional Judgment","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; John Templeton Foundation","keywords":"Narrative; Categorization; Humility; Classifier (UML); Psychology; Workflow; Coding (social sciences); Computer science; Social psychology; Artificial intelligence; Sociology; Linguistics; Social science","score_opus":0.7650757583834222,"score_gpt":0.5756139618117823,"score_spread":0.18946179657163997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399117309","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":[0.9503972,0.0031558124,0.040945098,0.0011454333,0.00029008376,0.0010713079,0.0001494032,0.00009953083,0.0027461376],"genre_scores_gemma":[0.98313946,0.00011745064,0.014220334,0.00020404026,0.00004386464,0.00042311876,0.0000078571475,0.000028325856,0.0018155472],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99490494,0.002673082,0.0003435611,0.00073399686,0.00078195997,0.00056247134],"domain_scores_gemma":[0.9978238,0.0015151894,0.000055422915,0.00022198536,0.00019205011,0.00019155059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044518276,0.00020255294,0.00041908832,0.00035843116,0.0002560201,0.000093402494,0.00027800543,0.00011773755,0.00034459637],"category_scores_gemma":[0.00053190463,0.00015101588,0.00019141048,0.0005193656,0.0007301879,0.00041192773,0.00027808239,0.00072261615,0.000021426085],"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":[0.0001637452,0.00044635445,0.0000667477,0.000085028485,0.00014200006,0.00039488875,0.010162968,0.0000021845626,0.9206047,0.011802976,0.00014058317,0.055987842],"study_design_scores_gemma":[0.0030152942,0.0018746794,0.011658747,0.00044215994,0.0010850524,0.00043875392,0.035551567,0.012553331,0.88494855,0.046794455,0.0006870832,0.0009503467],"about_ca_topic_score_codex":0.00015768487,"about_ca_topic_score_gemma":0.00001914144,"teacher_disagreement_score":0.055037495,"about_ca_system_score_codex":0.000063403524,"about_ca_system_score_gemma":0.000071633876,"threshold_uncertainty_score":0.6158249},"labels":[],"label_agreement":null},{"id":"W4400940128","doi":"10.3758/s13428-024-02466-5","title":"Body–object interaction ratings for 3600 French nouns","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"Université Laval; Centre for Interdisciplinary Research in Rehabilitation","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Noun; Object (grammar); Psychology; Computer science; Linguistics; Natural language processing; Cognitive psychology; Artificial intelligence","score_opus":0.2720334576754829,"score_gpt":0.6157969862804322,"score_spread":0.3437635286049493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400940128","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":[0.72187394,0.004906936,0.1925894,0.00071214733,0.009296311,0.0040797982,0.00019738615,0.00078560604,0.06555849],"genre_scores_gemma":[0.7965434,0.00008045431,0.11608264,0.00016731971,0.0022211515,0.008786231,0.0002795963,0.00019857904,0.07564058],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995682,0.002183312,0.0003529985,0.00065846345,0.00045060483,0.000672591],"domain_scores_gemma":[0.9968202,0.0021869563,0.00004295303,0.0004573116,0.00034463243,0.00014790872],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075546475,0.00017828777,0.00023722847,0.0005826948,0.0002589171,0.00028798857,0.0002775798,0.00021141903,0.004398831],"category_scores_gemma":[0.00080474064,0.00015388435,0.00023231404,0.00071151374,0.00012034229,0.00022390978,0.00007555928,0.00088326965,0.00057661027],"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":[0.000110575216,0.0003416205,0.0002480971,0.000105105064,0.00008901783,0.00014316705,0.008816921,9.8894155e-8,0.13596371,0.0042191716,0.027502472,0.82246006],"study_design_scores_gemma":[0.0027427783,0.0033082226,0.031812184,0.0005130577,0.00069424324,0.00048071903,0.030847043,0.00096556084,0.17665298,0.022680389,0.7279119,0.0013909503],"about_ca_topic_score_codex":0.0008645086,"about_ca_topic_score_gemma":0.00006830722,"teacher_disagreement_score":0.8210691,"about_ca_system_score_codex":0.00013418289,"about_ca_system_score_gemma":0.00011482715,"threshold_uncertainty_score":0.9965113},"labels":[],"label_agreement":null},{"id":"W4401411007","doi":"10.3758/s13428-024-02482-5","title":"A tutorial: Analyzing eye and head movements in virtual reality","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Virtual reality; Human–computer interaction; Eye movement; Head (geology); Optical head-mounted display; Computer graphics (images); Artificial intelligence; Computer vision; Cognitive psychology; Psychology","score_opus":0.29592612692404874,"score_gpt":0.5960021332841007,"score_spread":0.30007600636005194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401411007","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":[0.5301912,0.0007698074,0.46576953,0.0012988634,0.0006932396,0.00035275889,0.0000057613124,0.00044992715,0.00046895078],"genre_scores_gemma":[0.88592345,0.000060106162,0.113152735,0.00001318488,0.00007793961,0.00015895136,0.0000016890679,0.000015414264,0.0005965055],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99657,0.0015467517,0.00025560122,0.0006665823,0.00042676588,0.00053431914],"domain_scores_gemma":[0.99862796,0.00062229036,0.000019344157,0.00052557385,0.0000929921,0.0001118663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009565595,0.0001191622,0.00020457654,0.0007477926,0.00012727521,0.00034549515,0.000645635,0.00012256429,0.000009750576],"category_scores_gemma":[0.000508325,0.00010807482,0.000043743803,0.0015675961,0.0002120724,0.00026854145,0.00067135197,0.00081399095,0.000012626698],"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":[0.000005693474,0.00010231023,0.013063265,0.000020869775,0.000007649913,0.00023620183,0.00043834912,0.0000018587338,0.02700294,0.028921844,0.0001353165,0.9300637],"study_design_scores_gemma":[0.001089633,0.0009551333,0.85117006,0.00045883746,0.000016332584,0.000031335738,0.00048679224,0.030531842,0.025749672,0.03675036,0.052012123,0.00074790145],"about_ca_topic_score_codex":0.0006311278,"about_ca_topic_score_gemma":0.00006876843,"teacher_disagreement_score":0.9293158,"about_ca_system_score_codex":0.0001554238,"about_ca_system_score_gemma":0.00012287819,"threshold_uncertainty_score":0.44071633},"labels":[],"label_agreement":null},{"id":"W4402581411","doi":"10.3758/s13428-024-02508-y","title":"A standardized framework to test event-based experiments","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","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":"Canadian Institute for Advanced Research","funders":"Templeton World Charity Foundation","keywords":"Computer science; Protocol (science); Snapshot (computer storage); Replication (statistics); Robustness (evolution); Benchmark (surveying); Medical physics; Data science; Cognitive psychology; Psychology; Medicine","score_opus":0.42660021898052125,"score_gpt":0.6289628346652205,"score_spread":0.20236261568469927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402581411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34127727,0.0013207031,0.6219174,0.022784522,0.0036730932,0.0042238827,0.00035965187,0.0012600617,0.0031833758],"genre_scores_gemma":[0.7571951,0.000015037794,0.23534153,0.0013341845,0.0002897743,0.0031597498,0.0000018423183,0.00009902411,0.002563713],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9938793,0.0024970945,0.00025556423,0.0010373085,0.0015847438,0.0007459787],"domain_scores_gemma":[0.9518988,0.047009412,0.000017810862,0.0005915264,0.0001972038,0.00028523695],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059973635,0.00020486907,0.00025953093,0.0005931311,0.00052675884,0.00037923225,0.00045613156,0.00010601049,0.0005739014],"category_scores_gemma":[0.09652898,0.00018208053,0.0001489658,0.0021498597,0.0002319168,0.00015903938,0.00040976165,0.00086959504,0.00045067992],"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":[0.00011947138,0.0004519324,0.00044164344,0.00003936966,0.0000075950024,0.00025218746,0.0005129089,0.000023958737,0.93366516,0.0027653475,0.0096622305,0.052058216],"study_design_scores_gemma":[0.00022647654,0.00067474274,0.0008935827,0.00015770455,0.000010554658,0.00000906379,0.0001870178,0.0004764728,0.8782618,0.0022047441,0.11667341,0.00022441],"about_ca_topic_score_codex":0.000033680255,"about_ca_topic_score_gemma":0.0000044845965,"teacher_disagreement_score":0.41591787,"about_ca_system_score_codex":0.00042452285,"about_ca_system_score_gemma":0.00037236622,"threshold_uncertainty_score":0.9110813},"labels":[],"label_agreement":null},{"id":"W4402666573","doi":"10.3758/s13428-024-02493-2","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","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 Manitoba","funders":"Social Sciences and Humanities Research Council of Canada; James S. McDonnell Foundation; Academy of Finland; Horizon 2020 Framework Programme; Directorate for Engineering; Grand Équipement National De Calcul Intensif; China Scholarship Council; Economic and Social Research Council; European Commission; National Institutes of Health; National Science Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Computer science; Variation (astronomy); Reliability (semiconductor); Intraclass correlation; Natural language processing; Language acquisition; Identity (music); Artificial intelligence; Psychology; Developmental psychology; Mathematics education; Psychometrics","score_opus":0.2585887042868682,"score_gpt":0.5697168966099126,"score_spread":0.31112819232304445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402666573","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":[0.9669515,0.009892538,0.017866563,0.00091560575,0.00087655376,0.00094269734,0.00003233765,0.00007246181,0.0024497542],"genre_scores_gemma":[0.9092818,0.0005110612,0.08617619,0.000087569206,0.00028462213,0.00025254648,0.00003832267,0.00007956305,0.003288314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99465334,0.0031863018,0.0004980467,0.00050818786,0.00064750505,0.0005066411],"domain_scores_gemma":[0.9870173,0.011794324,0.000084061714,0.0007068301,0.00030106082,0.0000964263],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022854356,0.00016628522,0.00031406523,0.00036077102,0.00030193647,0.0003311561,0.00058752357,0.00017292837,0.0010967469],"category_scores_gemma":[0.0063944138,0.00008877476,0.0001224543,0.0019819087,0.0007451643,0.00029157757,0.00037584713,0.0011076372,0.000011899526],"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":[0.00033466134,0.00015579772,0.023786115,0.000060323797,0.00006453274,0.000063039544,0.015302091,8.6478923e-7,0.0037356939,0.00076668547,0.0026664254,0.9530638],"study_design_scores_gemma":[0.008275556,0.0003485288,0.7809694,0.00069042936,0.0013614012,0.00014245755,0.069258034,0.010535997,0.014902154,0.031431258,0.08045401,0.001630801],"about_ca_topic_score_codex":0.00951278,"about_ca_topic_score_gemma":0.00012730875,"teacher_disagreement_score":0.95143294,"about_ca_system_score_codex":0.00009096744,"about_ca_system_score_gemma":0.00015535484,"threshold_uncertainty_score":0.99981636},"labels":[],"label_agreement":null},{"id":"W4405230022","doi":"10.3758/s13428-024-02565-3","title":"DerLex: An eye-movement database of derived word reading in English","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","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":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Eye movement; Word (group theory); Computer science; Reading (process); Movement (music); Natural language processing; Artificial intelligence; Linguistics; Art","score_opus":0.25296962608578827,"score_gpt":0.5626719829348331,"score_spread":0.30970235684904485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405230022","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":[0.6628756,0.00049287797,0.33458784,0.00028396412,0.00038578906,0.00038206557,0.000008733311,0.00063396036,0.00034918947],"genre_scores_gemma":[0.53848094,0.000032009248,0.46117634,0.00001015417,0.000031765576,0.00014590261,0.000003405853,0.000018374589,0.00010110391],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99626404,0.0015638245,0.00034267298,0.0006906567,0.0005386426,0.0006001735],"domain_scores_gemma":[0.9979304,0.00064147543,0.000034814395,0.0010060244,0.00025442458,0.0001328518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008482085,0.00013638295,0.0002374525,0.0010160614,0.00008908848,0.00017910347,0.0013057676,0.00010779922,0.000029160783],"category_scores_gemma":[0.0007939253,0.00012758939,0.000055920278,0.0018078861,0.00022746583,0.0004971911,0.0007232462,0.0008212205,0.000011004875],"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":[0.000006698679,0.00025937974,0.0061892397,0.000058587157,0.000007275006,0.00026428382,0.001212363,0.000002295152,0.33913374,0.023341918,0.000096925236,0.62942725],"study_design_scores_gemma":[0.00063157786,0.0006293617,0.20165329,0.00071918574,0.000021901573,0.000011342214,0.0015152827,0.011736512,0.7687407,0.008223526,0.0055720513,0.0005452313],"about_ca_topic_score_codex":0.00028169592,"about_ca_topic_score_gemma":0.000055687215,"teacher_disagreement_score":0.62888205,"about_ca_system_score_codex":0.00014124703,"about_ca_system_score_gemma":0.00020482756,"threshold_uncertainty_score":0.5202944},"labels":[],"label_agreement":null},{"id":"W4405273443","doi":"10.3758/s13428-024-02517-x","title":"The PSR corpus: A Persian sentence reading corpus of eye movements","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":17,"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":"Reading (process); Sentence; Eye movement; Persian; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","score_opus":0.19681685782045238,"score_gpt":0.5401224052394038,"score_spread":0.3433055474189514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405273443","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":[0.22349352,0.0039721713,0.7621227,0.0036060503,0.0017257121,0.0009790708,0.000017018698,0.00086663046,0.0032171286],"genre_scores_gemma":[0.7303469,0.00029082116,0.26462802,0.000022789574,0.000050359973,0.0002227968,0.0000015145448,0.000028016413,0.0044087754],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965098,0.00120464,0.00030032083,0.0005553207,0.0007670236,0.00066292397],"domain_scores_gemma":[0.99730045,0.001275555,0.000057807454,0.0009488554,0.00030459376,0.00011276782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073891757,0.00013809747,0.00019275793,0.0003876267,0.00042207414,0.00032304245,0.0018811525,0.00009863045,0.000010936878],"category_scores_gemma":[0.00066145626,0.00009755045,0.00011183354,0.0015157327,0.0006105558,0.0001933968,0.00077530637,0.00078528054,0.000035860463],"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":[0.000006179456,0.00007882542,0.00524155,0.000030483596,0.00002202588,0.00013991327,0.0004695406,6.9524015e-7,0.104202874,0.056900717,0.00038424833,0.8325229],"study_design_scores_gemma":[0.001092867,0.0021009268,0.23727785,0.001345943,0.00009095601,0.0002700853,0.0044034105,0.047099065,0.4799243,0.04920219,0.1759145,0.0012779214],"about_ca_topic_score_codex":0.0001937797,"about_ca_topic_score_gemma":0.0000089386185,"teacher_disagreement_score":0.831245,"about_ca_system_score_codex":0.00012763806,"about_ca_system_score_gemma":0.00017548286,"threshold_uncertainty_score":0.3977992},"labels":[],"label_agreement":null},{"id":"W4406027501","doi":"10.3758/s13428-024-02550-w","title":"Validation of the Emotionally Congruent and Incongruent Face–Body Static Set (ECIFBSS)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face Recognition and Perception","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation and Economic Development Trois Rivières; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada; Université du Québec à Trois-Rivières","keywords":"Sadness; Disgust; Psychology; Facial expression; Anger; Valence (chemistry); Surprise; Cognitive psychology; Happiness; Emotion perception; Perception; Arousal; Emotion classification; Stimulus (psychology); Social psychology; Communication","score_opus":0.3302486855200189,"score_gpt":0.5729854020264431,"score_spread":0.2427367165064242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406027501","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":[0.9917759,0.000016647284,0.003980554,0.0013447937,0.0002676908,0.00089847215,0.00007493431,0.000023831224,0.0016172038],"genre_scores_gemma":[0.993108,0.000099846955,0.0036144704,0.0001725215,0.000012501967,0.00015477663,0.000010282767,0.000010038155,0.002817572],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99471176,0.0037783268,0.00029593243,0.00032836432,0.00063345785,0.0002521539],"domain_scores_gemma":[0.9980706,0.0012334603,0.00006748116,0.00030131076,0.00024880434,0.000078370555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00333981,0.000097899974,0.00014740163,0.00026107157,0.0002808213,0.00008273628,0.0002651531,0.00007373861,0.0004189368],"category_scores_gemma":[0.0023874817,0.000073254836,0.00006120236,0.0006907808,0.00043199144,0.00012835638,0.00022534955,0.00036023982,0.000021044785],"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":[0.000027440357,0.00015737492,0.005780193,0.000057503075,0.0000034281852,0.0000018231858,0.00044039317,0.000010480093,0.941697,0.0017487883,0.0005419589,0.049533587],"study_design_scores_gemma":[0.0004754938,0.000080496655,0.19059977,0.00008395032,0.000020573474,0.000008023639,0.0006156519,0.0006166148,0.8022462,0.0022786031,0.0028814499,0.000093177085],"about_ca_topic_score_codex":0.00008858833,"about_ca_topic_score_gemma":0.000011777106,"teacher_disagreement_score":0.18481956,"about_ca_system_score_codex":0.000094053874,"about_ca_system_score_gemma":0.00019234717,"threshold_uncertainty_score":0.45870644},"labels":[],"label_agreement":null},{"id":"W4406119379","doi":"10.3758/s13428-024-02582-2","title":"Expansion of the SyllabO+ corpus and database: Words, lemmas, and morphology","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","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":"Centre de Recherche Industrielle du Québec; Université de Montréal; Université Laval; McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Morpheme; Transparency (behavior); Computer science; Linguistics; Natural language processing; Agreement; Syllabic verse; Artificial intelligence; Speech recognition","score_opus":0.17109214308246842,"score_gpt":0.5626949910866405,"score_spread":0.391602848004172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406119379","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":[0.9860147,0.0064190044,0.0013359379,0.0005419135,0.00045481275,0.0005850174,0.000022949851,0.000020256526,0.0046053817],"genre_scores_gemma":[0.89342463,0.0007310424,0.073346496,0.00031990677,0.000048280104,0.0005249533,0.000039428658,0.00004226254,0.031523027],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969517,0.0018915477,0.0002191064,0.00035947762,0.00022847681,0.00034967135],"domain_scores_gemma":[0.9984845,0.0007461146,0.000044245542,0.00054848276,0.00010848597,0.00006816421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003231336,0.00010689859,0.00020233414,0.0002540363,0.00017578423,0.000023707624,0.0002765476,0.00012390432,0.00050475047],"category_scores_gemma":[0.0005145012,0.000074524425,0.000028619594,0.0006290235,0.00059604953,0.000047277623,0.0005484353,0.00038384442,0.0000048501115],"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":[0.00018336654,0.0001782233,0.20344873,0.000070223985,0.000041888,0.000060458297,0.0030023505,4.429719e-8,0.12471122,0.011983205,0.008525532,0.6477948],"study_design_scores_gemma":[0.0018237988,0.00011354089,0.93600714,0.00009437198,0.00006642297,0.000049580398,0.007486332,0.000005645784,0.02405539,0.0014325684,0.02865229,0.00021289053],"about_ca_topic_score_codex":0.0007139642,"about_ca_topic_score_gemma":0.000052213985,"teacher_disagreement_score":0.7325584,"about_ca_system_score_codex":0.000018202396,"about_ca_system_score_gemma":0.00011809897,"threshold_uncertainty_score":0.55266637},"labels":[],"label_agreement":null},{"id":"W4406652175","doi":"10.3758/s13428-024-02585-z","title":"Eyewitness Lineup Identity (ELI) database: Crime videos and mugshots for eyewitness identification research","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Memory Processes and Influences","field":"Neuroscience","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":"Simon Fraser University","funders":"Economic and Social Research Council","keywords":"Eyewitness identification; Psychology; Witness; Culprit; Eyewitness memory; Identification (biology); Eyewitness testimony; Crime scene; Social psychology; Recall; Computer science; Cognitive psychology; Criminology; Database","score_opus":0.5907812189468639,"score_gpt":0.6792687532089515,"score_spread":0.08848753426208766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406652175","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":[0.89089483,0.0016603282,0.097970374,0.0016008023,0.0011083813,0.0048124767,0.00026473167,0.00018291043,0.0015051435],"genre_scores_gemma":[0.9447805,0.0011053403,0.033382054,0.00025711217,0.00033048188,0.005668605,0.0000557485,0.00008877998,0.014331343],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.989723,0.0047632325,0.0007526359,0.0016538595,0.0018594079,0.0012478183],"domain_scores_gemma":[0.9898729,0.006316425,0.00012615223,0.0013277183,0.0020444847,0.0003123533],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02984335,0.00025829,0.00040409373,0.0012819223,0.00236131,0.0015030971,0.0017018288,0.00020960454,0.00015726293],"category_scores_gemma":[0.028041907,0.00023733602,0.00009553992,0.003439934,0.0018520278,0.001893632,0.0011665492,0.0011483524,0.000043466986],"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":[0.00014601805,0.00027372624,0.000868795,0.00062099466,0.000005272222,0.000018698298,0.00020889753,0.0000014656757,0.92085093,0.019356363,0.0013823223,0.05626651],"study_design_scores_gemma":[0.00059959956,0.0001452185,0.018286582,0.00018111493,0.000034700206,0.000012295089,0.00061563385,0.00070804224,0.9480598,0.016039386,0.015050936,0.0002666761],"about_ca_topic_score_codex":0.00032708028,"about_ca_topic_score_gemma":0.0000476807,"teacher_disagreement_score":0.064588316,"about_ca_system_score_codex":0.00015495959,"about_ca_system_score_gemma":0.0007220631,"threshold_uncertainty_score":0.9995334},"labels":[],"label_agreement":null},{"id":"W4406853484","doi":"10.3758/s13428-024-02553-7","title":"EmoAtlas: An emotional network analyzer of texts that merges psychological lexicons, artificial intelligence, and network science","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":19,"is_retracted":false,"has_abstract":false,"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; Emotional intelligence; Natural language processing; Psychology; Social psychology","score_opus":0.30727787482703395,"score_gpt":0.593795430617827,"score_spread":0.2865175557907931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406853484","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":[0.5332777,0.0005434802,0.4590599,0.00020585669,0.0002268141,0.000691029,0.000012841605,0.00008522792,0.005897184],"genre_scores_gemma":[0.8047016,0.000030096739,0.19457467,0.000014694591,0.00034974088,0.000107131826,0.000015348716,0.000011822993,0.00019489962],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99540573,0.0017121731,0.0005391359,0.0007765367,0.0007114172,0.0008549973],"domain_scores_gemma":[0.99774855,0.00071200036,0.00012958137,0.0007146528,0.00047180837,0.00022340755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010225519,0.00021288598,0.00047547434,0.0005177629,0.0007131532,0.00020060349,0.0008123179,0.00009195742,0.0007550593],"category_scores_gemma":[0.0000875853,0.00018634487,0.00015754723,0.0034982704,0.0018205165,0.00022509455,0.0006070788,0.00063934445,0.0000032593962],"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":[0.00003973734,0.0004235188,0.1544333,0.000005547128,0.00004147797,0.0000019728334,0.00004212492,0.0004139573,0.002185963,0.18245171,0.0011055745,0.65885514],"study_design_scores_gemma":[0.00012548923,0.00037026135,0.34265417,0.00016562322,0.00015006757,0.0000027242932,0.000575004,0.010520766,0.014165919,0.6281331,0.0026742315,0.000462614],"about_ca_topic_score_codex":0.00014435586,"about_ca_topic_score_gemma":0.00002693825,"teacher_disagreement_score":0.6583925,"about_ca_system_score_codex":0.000046305577,"about_ca_system_score_gemma":0.0001716273,"threshold_uncertainty_score":0.826737},"labels":[],"label_agreement":null},{"id":"W4407688685","doi":"10.3758/s13428-025-02610-9","title":"Open-access network science: Investigating phonological similarity networks based on the SUBTLEX-US lexicon","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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":"Computer science; Lexicon; Python (programming language); Artificial intelligence; Natural language processing; Clustering coefficient; Adjacency list; Similarity (geometry); Cluster analysis","score_opus":0.4133289132249728,"score_gpt":0.6305229576386698,"score_spread":0.21719404441369705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407688685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27749965,0.00017541552,0.5865863,0.0053226743,0.0004227705,0.004461389,0.000016084654,0.0003501598,0.1251656],"genre_scores_gemma":[0.91500115,0.0000029104842,0.08237539,0.0006718652,0.0003241961,0.0012028462,0.000022359336,0.000024692998,0.00037459424],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923108,0.0042208876,0.00048633333,0.00093258254,0.0008075394,0.0012418312],"domain_scores_gemma":[0.99435306,0.0033373816,0.00014794523,0.0014744606,0.00045230144,0.00023484303],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024265287,0.00027998627,0.0004565733,0.0003514839,0.0023724623,0.0030752672,0.0057793767,0.00011290318,0.0013691755],"category_scores_gemma":[0.00061036454,0.00019853123,0.00018577592,0.0053979293,0.0018642724,0.00038521388,0.004959181,0.0019127034,0.000006717854],"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":[0.00006814585,0.0006184711,0.384873,0.000008650112,0.00005245132,0.0000071769227,0.000031385665,0.012651436,0.0023254445,0.2524936,0.02801651,0.31885374],"study_design_scores_gemma":[0.00089172256,0.00034033658,0.22174819,0.0004033303,0.00016183981,6.641136e-7,0.00031154352,0.53815335,0.025553726,0.17942081,0.03210142,0.0009130314],"about_ca_topic_score_codex":0.0009779987,"about_ca_topic_score_gemma":0.000021792566,"teacher_disagreement_score":0.63750154,"about_ca_system_score_codex":0.00020422676,"about_ca_system_score_gemma":0.00095777493,"threshold_uncertainty_score":0.9995998},"labels":[],"label_agreement":null},{"id":"W4408300423","doi":"10.3758/s13428-025-02623-4","title":"The role of individual differences and attitude in willingness to participate in TMS studies","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Transcranial Magnetic Stimulation Studies","field":"Neuroscience","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":"Trent University; Nottingham Trent University","keywords":"Transcranial magnetic stimulation; Psychology; Context (archaeology); Perspective (graphical); Applied psychology; Social psychology","score_opus":0.5495828560905578,"score_gpt":0.6418443354744394,"score_spread":0.09226147938388163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408300423","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":[0.9961813,0.002172321,0.00012504112,0.00055916887,0.00008886261,0.0006822348,0.0000060506313,0.000011066202,0.00017395729],"genre_scores_gemma":[0.9960564,0.0004297058,0.0028071867,0.00002263534,0.0000063574507,0.00056943076,5.2251274e-8,0.0000056514755,0.00010259321],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99623877,0.0021430613,0.00036349162,0.00034125583,0.0005050458,0.00040840099],"domain_scores_gemma":[0.992662,0.006944586,0.000028551214,0.00020817199,0.00010782945,0.0000488265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043942453,0.00010023725,0.0002741716,0.00031291318,0.0002124547,0.000058468904,0.0003702518,0.000037911013,0.0000041189496],"category_scores_gemma":[0.0044901567,0.00006931298,0.000021571992,0.001376942,0.0006939622,0.000051663763,0.0004006727,0.00026657322,0.0000012271295],"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":[0.000098759505,0.00013454768,0.5508916,0.000023675513,0.000005558553,0.0000062890963,0.0059730173,0.000016652935,0.2196785,0.0022900614,0.0000033260117,0.22087805],"study_design_scores_gemma":[0.0003858857,0.000117417105,0.96626693,0.00007158058,0.000009352346,2.8307707e-7,0.002876575,0.000086206084,0.025754947,0.0041651465,0.00020339621,0.00006229524],"about_ca_topic_score_codex":0.00016893154,"about_ca_topic_score_gemma":0.00050169724,"teacher_disagreement_score":0.41537535,"about_ca_system_score_codex":0.00002866633,"about_ca_system_score_gemma":0.000047800728,"threshold_uncertainty_score":0.53754616},"labels":[],"label_agreement":null},{"id":"W4408426509","doi":"10.3758/s13428-025-02636-z","title":"Unraveling other-race face perception with GAN-based image reconstruction","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Face recognition and analysis","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":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Race (biology); Similarity (geometry); Artificial intelligence; Face (sociological concept); Pairwise comparison; Computer science; Perception; Face perception; Basis (linear algebra); Pattern recognition (psychology); Cognitive psychology; Computer vision; Psychology; Image (mathematics); Mathematics; Geology; Geometry","score_opus":0.14810278882505917,"score_gpt":0.52501069815385,"score_spread":0.37690790932879087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408426509","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":[0.059945237,0.000033317625,0.93587196,0.0013617455,0.0001084497,0.00032415867,0.000003727441,0.00016057967,0.0021908034],"genre_scores_gemma":[0.083687134,0.000020208927,0.9138585,0.00011499085,0.000022884142,0.00015862894,0.0000043125874,0.000013661458,0.0021196867],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963533,0.0018552496,0.00024199384,0.0005732415,0.0005426604,0.0004335305],"domain_scores_gemma":[0.9981825,0.00043165352,0.00005806904,0.0006088914,0.0005906383,0.00012825985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042774295,0.0001449021,0.000211007,0.0008033929,0.0004013705,0.00039823382,0.0005690302,0.00009818647,0.00024004228],"category_scores_gemma":[0.00027422857,0.00012333294,0.00010587932,0.002152306,0.00021137577,0.00038873954,0.00006766449,0.0005046751,0.00008168052],"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":[0.000015628633,0.00009787212,0.001546609,0.000022800843,0.000013550489,0.000008642193,0.00016875783,0.000058549653,0.2199491,0.00028530098,0.00007780211,0.7777554],"study_design_scores_gemma":[0.001932517,0.00039298338,0.02711169,0.0005381344,0.00012759684,0.000055878772,0.0047044517,0.31514677,0.6420343,0.0016772471,0.005457935,0.0008205075],"about_ca_topic_score_codex":0.00017906196,"about_ca_topic_score_gemma":0.000032407803,"teacher_disagreement_score":0.77693486,"about_ca_system_score_codex":0.00018075976,"about_ca_system_score_gemma":0.00029123292,"threshold_uncertainty_score":0.50293714},"labels":[],"label_agreement":null},{"id":"W4409147508","doi":"10.3758/s13428-025-02628-z","title":"SingleMALD: Investigating practice effects in auditory lexical decision","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Lexical decision task; Stimulus (psychology); Psychology; Computer science; Lexical access; Task (project management); Cognitive psychology; Audiology; Cognition; Medicine","score_opus":0.2294778276926878,"score_gpt":0.6508911712031178,"score_spread":0.42141334351043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409147508","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":[0.89484966,0.0013050004,0.036548864,0.001278766,0.0040498413,0.0014319388,0.0000018793803,0.00013816771,0.060395885],"genre_scores_gemma":[0.15867072,0.000013996399,0.82947874,0.00041528026,0.00021875472,0.0011685028,0.0000061675423,0.000038587143,0.009989252],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98922735,0.00821605,0.0005250679,0.00064451067,0.0006265427,0.0007604551],"domain_scores_gemma":[0.980876,0.01800397,0.00007109222,0.0005956319,0.00026107082,0.00019218281],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018173836,0.0001698422,0.00030101,0.00096489035,0.00024381108,0.00012928531,0.00041686857,0.00024560865,0.00017895212],"category_scores_gemma":[0.01777536,0.00015752007,0.000065710614,0.0015667471,0.00023292222,0.00018180213,0.00028384323,0.001420327,0.00017241744],"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":[0.00013695232,0.000614677,0.025334815,0.000051942225,0.000022395521,0.00037456883,0.0035150882,0.0000021529715,0.011143798,0.0076388707,0.013063355,0.9381014],"study_design_scores_gemma":[0.0016230902,0.00027623726,0.6883306,0.00093553046,0.000035217607,0.00004622944,0.0020997662,0.000076456956,0.0050944197,0.0063917623,0.29474926,0.0003414739],"about_ca_topic_score_codex":0.0003961933,"about_ca_topic_score_gemma":0.000010119061,"teacher_disagreement_score":0.93775994,"about_ca_system_score_codex":0.00034834177,"about_ca_system_score_gemma":0.00029856502,"threshold_uncertainty_score":0.9904983},"labels":[],"label_agreement":null},{"id":"W4409148165","doi":"10.3758/s13428-025-02656-9","title":"VOC-ADO: A lexical database for French-speaking adolescents","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","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":"Centre for Interdisciplinary Research in Rehabilitation","funders":"Agence Nationale de la Recherche","keywords":"Vocabulary; Computer science; Lemma (botany); Psychology; Linguistics; Lexical database; Mathematics education; Natural language processing","score_opus":0.3489859521934305,"score_gpt":0.6063080813811523,"score_spread":0.25732212918772185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409148165","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":[0.019596986,0.00015510793,0.9772587,0.0009548031,0.00033036165,0.001092391,0.000019259885,0.00013432375,0.00045809336],"genre_scores_gemma":[0.28043914,0.000008863827,0.71796894,0.00008896134,0.000058680165,0.0006787309,0.000016464232,0.000009970508,0.00073025323],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99621236,0.0015070104,0.00033966987,0.00075230765,0.0005494244,0.00063923997],"domain_scores_gemma":[0.99688786,0.0010127848,0.000044604956,0.0014324251,0.00044816223,0.00017414507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008318839,0.00013586243,0.0002083109,0.00038804114,0.00043393503,0.0003175162,0.001635245,0.00012089207,0.000017278471],"category_scores_gemma":[0.0018537225,0.00012584975,0.000117460186,0.0011351104,0.00019106717,0.0004250003,0.0007698452,0.0005228325,0.000019020992],"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":[0.000019557014,0.0004569297,0.007089455,0.00011880736,0.000005963148,0.000006530844,0.0002843317,0.0000012776056,0.0309151,0.04554972,0.0010717028,0.9144806],"study_design_scores_gemma":[0.0022729076,0.00045718392,0.62611103,0.00068707793,0.00006074126,0.000020592703,0.00029769712,0.041833926,0.10057174,0.042381253,0.18443063,0.00087525096],"about_ca_topic_score_codex":0.0002740931,"about_ca_topic_score_gemma":0.00005174779,"teacher_disagreement_score":0.9136054,"about_ca_system_score_codex":0.00016680136,"about_ca_system_score_gemma":0.00032782907,"threshold_uncertainty_score":0.51320034},"labels":[],"label_agreement":null},{"id":"W4409665275","doi":"10.3758/s13428-025-02658-7","title":"Assessing multiple abilities through process data in computer-based assessments: The multidimensional sequential response model (MSRM)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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 Toronto","funders":"Beijing Municipal Social Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.920767338243147,"score_gpt":0.759212213405075,"score_spread":0.161555124838072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409665275","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":[0.4453298,0.0001525013,0.5523787,0.000743724,0.00043063945,0.0006700474,0.000041920175,0.000048709255,0.00020396286],"genre_scores_gemma":[0.35935256,0.000004349949,0.6399703,0.0001332543,0.0000439366,0.00020272905,0.000014619057,0.000016721346,0.00026149934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9544425,0.036956534,0.0015639786,0.0018926047,0.004008024,0.001136342],"domain_scores_gemma":[0.7379035,0.2559777,0.00033323275,0.0040260674,0.0016080029,0.00015152304],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17743869,0.00029508723,0.0006301436,0.0015263046,0.001034844,0.0012393835,0.0044509345,0.00021637703,0.00009794051],"category_scores_gemma":[0.24627991,0.00018954882,0.00013858726,0.006938378,0.0009016287,0.001382144,0.002594382,0.0014432744,0.000008045399],"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":[0.0013396555,0.001418917,0.20468552,0.000065638975,0.000034123044,0.00006830843,0.0011326793,0.026800703,0.017795844,0.0006226175,0.0017144243,0.7443216],"study_design_scores_gemma":[0.0012384125,0.00010255926,0.13630463,0.00012785714,0.000016346215,0.000005124619,0.004390987,0.8380329,0.0025239123,0.015884694,0.001146303,0.00022629106],"about_ca_topic_score_codex":0.0006638377,"about_ca_topic_score_gemma":0.00006259336,"teacher_disagreement_score":0.8112322,"about_ca_system_score_codex":0.0002828278,"about_ca_system_score_gemma":0.0021878425,"threshold_uncertainty_score":0.9997974},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4409720720","doi":"10.3758/s13428-025-02675-6","title":"English verbs semantic norms database: Concreteness, embodiment, imageability, valence and arousal ratings for 3,500 verbs","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"Western University; University of Calgary","funders":"","keywords":"Concreteness; Valence (chemistry); Arousal; Psychology; Natural language processing; Computer science; Cognitive psychology; Emotional valence; Artificial intelligence; Cognition; Social psychology","score_opus":0.14195791261475013,"score_gpt":0.5414649967519795,"score_spread":0.39950708413722935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409720720","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":[0.9240128,0.0031867106,0.056616046,0.00024530056,0.001902619,0.0037339344,0.00052000134,0.00022996563,0.009552625],"genre_scores_gemma":[0.82325065,0.00028978457,0.15457416,0.0004801554,0.00071418943,0.0065071406,0.000627766,0.00013554815,0.013420619],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9943195,0.002719034,0.00050032156,0.0010267433,0.00052234385,0.00091208844],"domain_scores_gemma":[0.99502987,0.0028565975,0.000094575065,0.0009722662,0.00084238086,0.00020432081],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010524684,0.00027411053,0.00046487892,0.00036674688,0.00047549067,0.00020584735,0.0005169119,0.00022303348,0.00062722096],"category_scores_gemma":[0.0030994213,0.00024760913,0.00013717599,0.00068569597,0.00065072934,0.00030643513,0.00043173213,0.00072713505,0.000030655312],"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":[0.0016485506,0.0013535998,0.065841466,0.0016624324,0.00035254238,0.00026621294,0.011904093,3.2866578e-7,0.27099434,0.028417392,0.01755362,0.60000545],"study_design_scores_gemma":[0.025756894,0.0044647777,0.30293638,0.001534796,0.0027435366,0.00019430304,0.06366005,0.0008154882,0.4378005,0.04389478,0.11225784,0.003940676],"about_ca_topic_score_codex":0.0007683318,"about_ca_topic_score_gemma":0.000041227904,"teacher_disagreement_score":0.59606475,"about_ca_system_score_codex":0.00010071754,"about_ca_system_score_gemma":0.00019980872,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W4410091307","doi":"10.3758/s13428-025-02652-z","title":"The Second Database of Emotional Videos from Ottawa (DEVO-2): Over 1300 brief video clips rated on valence, arousal, impact, and familiarity","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Media Influence and Health","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Privy Council Office; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CLIPS; Valence (chemistry); Arousal; Emotional valence; Computer science; Psychology; Cognitive psychology; Multimedia; Artificial intelligence; Cognition; Social psychology","score_opus":0.227521155550353,"score_gpt":0.5381123989237419,"score_spread":0.31059124337338884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410091307","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":[0.988551,0.0010327785,0.00014195261,0.00048752906,0.00048300787,0.00086493825,0.0020185995,0.000035299934,0.006384861],"genre_scores_gemma":[0.929523,0.003466032,0.012068673,0.0025841512,0.0018138408,0.0011575255,0.00087082764,0.0001348253,0.048381153],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9953509,0.0022007807,0.00058319455,0.0004929926,0.00075637735,0.00061573717],"domain_scores_gemma":[0.99366313,0.004696943,0.00012646058,0.00075922004,0.0005175134,0.00023675688],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006858026,0.00020982584,0.0003678366,0.0003214509,0.001102703,0.00027795494,0.0004544241,0.00011053443,0.0042747078],"category_scores_gemma":[0.0012553373,0.00014241265,0.00011005196,0.0002463836,0.0013191854,0.0003104284,0.00022887946,0.0010122134,0.000022855389],"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":[0.0013633773,0.00191963,0.24243337,0.0008929212,0.00035380994,0.00010808885,0.012413162,0.0000036049653,0.043460235,0.24219717,0.2773922,0.17746243],"study_design_scores_gemma":[0.0014389599,0.00059834146,0.5231599,0.0004736501,0.00006865249,0.0000026796695,0.0024953224,0.00026977083,0.0063919914,0.011474208,0.453294,0.00033247937],"about_ca_topic_score_codex":0.008949225,"about_ca_topic_score_gemma":0.005802634,"teacher_disagreement_score":0.28072655,"about_ca_system_score_codex":0.000111737754,"about_ca_system_score_gemma":0.000626827,"threshold_uncertainty_score":0.99765027},"labels":[],"label_agreement":null},{"id":"W4410106284","doi":"10.3758/s13428-025-02690-7","title":"Assessing autobiographical memory consistency: Machine and human approaches","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","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 Alberta; University of British Columbia","funders":"","keywords":"Autobiographical memory; Consistency (knowledge bases); Computer science; Human memory; Cognitive psychology; Psychology; Artificial intelligence; Natural language processing; Recall; Cognition; Neuroscience","score_opus":0.48539084858012965,"score_gpt":0.629412572268767,"score_spread":0.14402172368863736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410106284","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":[0.8859891,0.0050983643,0.00447985,0.00083297695,0.0009201175,0.000974518,0.000009266627,0.00017057754,0.10152517],"genre_scores_gemma":[0.95311797,0.00005082959,0.03236386,0.00010707216,0.00013678183,0.0005020331,0.000018220902,0.000046893347,0.013656366],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924529,0.005338156,0.00039211565,0.0007009143,0.00041540424,0.0007005195],"domain_scores_gemma":[0.9979743,0.00084505655,0.00005839125,0.00077624095,0.00016386635,0.00018213931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010387356,0.00021106463,0.00039578174,0.0011217318,0.0008746781,0.00037305107,0.00042899195,0.00029134803,0.00068693765],"category_scores_gemma":[0.00022678969,0.00019659915,0.00015373192,0.0010483224,0.0011699039,0.00016356778,0.00024217843,0.0011432671,0.000019363688],"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":[0.000082972154,0.0014774206,0.15423699,0.00011910315,0.0002151307,0.0002057593,0.0015921559,9.947788e-8,0.029835837,0.11866326,0.0018329751,0.6917383],"study_design_scores_gemma":[0.0016429824,0.000208183,0.96782714,0.00006257048,0.00012669599,0.000051301566,0.0048023676,0.000023508497,0.0031824375,0.014546053,0.0071798945,0.00034686917],"about_ca_topic_score_codex":0.0012563553,"about_ca_topic_score_gemma":0.00012665367,"teacher_disagreement_score":0.81359017,"about_ca_system_score_codex":0.000057692327,"about_ca_system_score_gemma":0.000118389,"threshold_uncertainty_score":0.8017081},"labels":[],"label_agreement":null},{"id":"W4410345373","doi":"10.3758/s13428-025-02688-1","title":"An equivalent illuminant analysis of lightness constancy with physical objects and in virtual reality","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Color Science and Applications","field":"Physics and Astronomy","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":"York University","funders":"","keywords":"Standard illuminant; Lightness; Subjective constancy; Color constancy; Virtual reality; Computer science; Computer graphics (images); Artificial intelligence; Computer vision; Perception; Psychology","score_opus":0.13359576943822876,"score_gpt":0.5824340243178263,"score_spread":0.44883825487959755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410345373","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":[0.9697903,0.000012864168,0.028400624,0.00009802751,0.000008643438,0.00033401145,0.000032263903,0.0000062900094,0.0013169794],"genre_scores_gemma":[0.9963802,0.0000023797302,0.0031841926,0.00000230662,0.0000117471345,0.00027430532,0.000011188429,0.0000035979565,0.0001300666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99836504,0.00056857255,0.00017982254,0.00034572274,0.00027184017,0.0002689961],"domain_scores_gemma":[0.998903,0.0003768319,0.00004173101,0.00041784145,0.00016944391,0.00009114689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018461235,0.000082584775,0.00028683548,0.00044093013,0.00012263634,0.0000390967,0.00022792863,0.000022646953,0.000032100488],"category_scores_gemma":[0.00001815968,0.00006417661,0.000054304357,0.0028554357,0.0004808691,0.00010281907,0.00010749522,0.0002023859,4.2903272e-7],"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":[0.000086181724,0.002266623,0.46859655,0.000017293318,0.00013236559,0.0000050102035,0.0022224255,0.00019324405,0.12906401,0.12522016,0.000014250269,0.27218187],"study_design_scores_gemma":[0.00045633383,0.0002548981,0.9162058,0.00004095201,0.0003070765,1.8022341e-7,0.0065009873,0.0065412633,0.06705852,0.0023395831,0.00013025304,0.00016410349],"about_ca_topic_score_codex":0.0008228971,"about_ca_topic_score_gemma":0.00021390061,"teacher_disagreement_score":0.4476093,"about_ca_system_score_codex":0.00002955646,"about_ca_system_score_gemma":0.00019126233,"threshold_uncertainty_score":0.26170462},"labels":[],"label_agreement":null},{"id":"W4410850616","doi":"10.3758/s13428-025-02663-w","title":"Cognition ratings for 8826 english words","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":4,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cognition; Cognitive psychology; Psychology; Natural language processing; Computer science","score_opus":0.3474396990473601,"score_gpt":0.6201960024926879,"score_spread":0.2727563034453278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410850616","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":[0.97143364,0.00015883971,0.011467052,0.00068148726,0.0013828703,0.0023245055,0.00006592273,0.0002763146,0.012209384],"genre_scores_gemma":[0.8516608,0.00007017934,0.121361814,0.002201619,0.0006432614,0.0027412234,0.00003456163,0.000061607156,0.021224918],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99598277,0.0022746099,0.00026362977,0.00061815925,0.0002691441,0.00059171533],"domain_scores_gemma":[0.9943502,0.004767331,0.00004620729,0.00036376927,0.00038376276,0.000088763714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047830995,0.00013172858,0.00020273449,0.00037175522,0.00047585895,0.00011132469,0.00044911762,0.00014546105,0.00011596849],"category_scores_gemma":[0.019068424,0.000116418545,0.000113494934,0.0007699923,0.00040717048,0.00011925567,0.00020357636,0.00055885874,0.000013287573],"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":[0.000062980536,0.0001290956,0.000092891234,0.000027242118,0.0000020993352,0.000078059405,0.00062713,9.664152e-8,0.8786975,0.0010214755,0.0014406304,0.11782078],"study_design_scores_gemma":[0.00055999047,0.00017767101,0.00018152935,0.000032803167,0.00002244591,0.000017881875,0.0005013422,0.000021905913,0.962555,0.0028883074,0.03291975,0.00012139965],"about_ca_topic_score_codex":0.000015706175,"about_ca_topic_score_gemma":0.000005123307,"teacher_disagreement_score":0.11977281,"about_ca_system_score_codex":0.00003775197,"about_ca_system_score_gemma":0.00014632536,"threshold_uncertainty_score":0.9891944},"labels":[],"label_agreement":null},{"id":"W4411363785","doi":"10.3758/s13428-025-02727-x","title":"Digital questionnaire response time (DQRT): A ubiquitous and low-cost digital assay of cognitive processing speed","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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":"Trinity College","funders":"H2020 European Research Council; Irish Research Council; Science Foundation Ireland; Irish Research eLibrary; Horizon 2020 Framework Programme; Global Brain Health Institute","keywords":"Cognition; Bootstrapping (finance); Measure (data warehouse); Task (project management); Computer science; Reliability (semiconductor); Elementary cognitive task; Range (aeronautics); Psychology; Applied psychology; Data mining; Psychiatry; Mathematics","score_opus":0.2004382962207022,"score_gpt":0.6228393463628408,"score_spread":0.4224010501421386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411363785","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":[0.9708775,0.001057469,0.0034203012,0.0006396458,0.00021112712,0.0030411778,0.00031254825,0.000109198605,0.02033102],"genre_scores_gemma":[0.95155984,0.000011435718,0.0019446779,0.00003771913,0.00007805913,0.00047251926,0.000053488126,0.000053332038,0.04578895],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9913751,0.0051994077,0.0006360773,0.00074995635,0.00096352433,0.0010759436],"domain_scores_gemma":[0.9936693,0.004364128,0.00012152355,0.0005076514,0.0008946113,0.00044283966],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010482144,0.00024612667,0.00045590196,0.00095005386,0.00034830917,0.00037791792,0.0004300076,0.00027953318,0.00033386843],"category_scores_gemma":[0.010215981,0.00023603656,0.000089808804,0.0013311568,0.0012012912,0.00047487265,0.00055295095,0.0011042962,0.00014756748],"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":[0.0031055803,0.0009039894,0.022475932,0.0002657673,0.000031855616,0.00020388518,0.0014037091,5.5489167e-8,0.0033548367,0.00019722531,0.0005555793,0.9675016],"study_design_scores_gemma":[0.0075985733,0.0037431128,0.9373904,0.0055824965,0.0001207933,0.0002846079,0.010394143,0.0006197897,0.019114986,0.002779539,0.011360437,0.001011138],"about_ca_topic_score_codex":0.00006702445,"about_ca_topic_score_gemma":0.000005542249,"teacher_disagreement_score":0.96649045,"about_ca_system_score_codex":0.00029348469,"about_ca_system_score_gemma":0.0008181087,"threshold_uncertainty_score":0.9981214},"labels":[],"label_agreement":null},{"id":"W4412406583","doi":"10.3758/s13428-025-02743-x","title":"Collecting behavioural data across countries during pandemics: Development of the COVID-19 Risk Assessment Tool","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"COVID-19 and Mental Health","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 Toronto","funders":"","keywords":"Blueprint; Pandemic; Government (linguistics); Coronavirus disease 2019 (COVID-19); Public health; Psychological intervention; Risk assessment; Work (physics); Psychology; Business; Public relations; Computer science; Engineering; Medicine; Computer security; Political science; Nursing; Infectious disease (medical specialty)","score_opus":0.6468616321629242,"score_gpt":0.7186630093676086,"score_spread":0.07180137720468438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412406583","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":[0.985539,0.00042539035,0.009457259,0.00060057396,0.0009885894,0.0019323637,0.00044131136,0.00006993845,0.0005455378],"genre_scores_gemma":[0.89830244,0.00013997506,0.08834072,0.0004942653,0.00008336842,0.001436956,0.00007990772,0.000055092256,0.011067305],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99143106,0.0047855373,0.00090604974,0.0008398796,0.0009362778,0.0011011874],"domain_scores_gemma":[0.99424875,0.0030021504,0.00026560703,0.0019500674,0.00028375373,0.0002496769],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.024222039,0.00022685964,0.00040750782,0.000264619,0.002554833,0.0001097559,0.0017235467,0.00021106646,0.0002930448],"category_scores_gemma":[0.0021591177,0.00018021517,0.00009518866,0.0012373499,0.00052448374,0.00014109828,0.0026539897,0.0013160051,0.00000798015],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000199899,0.00038153148,0.9213107,0.00026821232,0.000059875998,0.000017699938,0.007246385,0.0000012447,0.0023387007,0.00033252643,0.0010959677,0.0667472],"study_design_scores_gemma":[0.0016419616,0.00006399752,0.9283353,0.000081715436,0.00006500827,0.000016130305,0.009110569,0.000022378814,0.0051171216,0.0001201507,0.055226617,0.0001990683],"about_ca_topic_score_codex":0.0075221322,"about_ca_topic_score_gemma":0.0027881623,"teacher_disagreement_score":0.08723663,"about_ca_system_score_codex":0.002498669,"about_ca_system_score_gemma":0.0062661003,"threshold_uncertainty_score":0.9993675},"labels":[],"label_agreement":null},{"id":"W4412784629","doi":"10.3758/s13428-025-02762-8","title":"Reward as a facet of word meaning: Ratings of motivation for 8,601 English words","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language, Metaphor, and Cognition","field":"Psychology","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":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Concreteness; Cognitive psychology; Valence (chemistry); Pleasure; Semantic memory; Cognition","score_opus":0.22898201203849286,"score_gpt":0.5678840200943505,"score_spread":0.3389020080558576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412784629","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":[0.90100527,0.00040832465,0.048580006,0.00012652703,0.00075348024,0.0019678571,0.00005505435,0.00007262728,0.047030862],"genre_scores_gemma":[0.88258106,0.00001851242,0.10275243,0.000048388236,0.00014572738,0.0014572148,0.000058315392,0.00004018639,0.012898151],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957152,0.002320148,0.0005740873,0.00043122214,0.00049815915,0.00046117435],"domain_scores_gemma":[0.9957911,0.0019294714,0.00018507823,0.00054827065,0.0014659545,0.00008012352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008317621,0.00014767918,0.00041157464,0.0006596602,0.00011749549,0.000030178113,0.0003645008,0.00022301082,0.0007146935],"category_scores_gemma":[0.008251166,0.00013861383,0.0001878429,0.0011886879,0.00022308527,0.000100466525,0.00011339075,0.00042537614,0.000006084133],"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":[0.00081454363,0.0009794349,0.010000013,0.00029784368,0.00016814441,0.000009103645,0.030851832,8.084606e-7,0.17429382,0.039548215,0.004543774,0.7384925],"study_design_scores_gemma":[0.006310789,0.0019308076,0.10125928,0.00060456997,0.0004849375,0.000007015155,0.08206486,0.000039514707,0.7431425,0.04318879,0.020377342,0.00058958516],"about_ca_topic_score_codex":0.0004286017,"about_ca_topic_score_gemma":0.000016880163,"teacher_disagreement_score":0.7379029,"about_ca_system_score_codex":0.00006133431,"about_ca_system_score_gemma":0.00016232778,"threshold_uncertainty_score":0.9878012},"labels":[],"label_agreement":null},{"id":"W4413115497","doi":"10.3758/s13428-025-02768-2","title":"Single point estimation of a decision space","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Bayesian Modeling and Causal Inference","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 Winnipeg","funders":"","keywords":"Computer science; Point estimation; Decision theory; Sensitivity (control systems); Optimal decision; Fisher information; Expected utility hypothesis; A priori and a posteriori; Detection theory; False alarm; Mathematics; Artificial intelligence; Machine learning; Statistics; Decision tree","score_opus":0.2685580400148034,"score_gpt":0.5746600187935892,"score_spread":0.3061019787787858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413115497","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":[0.033073183,0.00017184136,0.9638244,0.00050751196,0.00016173272,0.00021395588,8.780717e-7,0.00006657591,0.0019799105],"genre_scores_gemma":[0.32729006,0.000007832552,0.67232376,0.000013085198,0.00000518101,0.00003765489,5.0364554e-7,0.000003645161,0.00031824765],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976232,0.0009178911,0.0002786915,0.0003520887,0.0005186403,0.00030947532],"domain_scores_gemma":[0.9976032,0.0010777583,0.000046848596,0.0007514355,0.00043292777,0.00008784427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005724078,0.00008668639,0.00017220034,0.00046202348,0.0001276654,0.00013552647,0.00086108246,0.00008504132,0.000016030155],"category_scores_gemma":[0.001315038,0.00007840479,0.000060771043,0.0013288526,0.00011356944,0.00025379355,0.00050074083,0.00030469935,0.000012906477],"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":[0.0000083981495,0.00015130587,0.00007011634,0.000013817506,0.0000024635447,0.000005894897,0.00015951759,0.0001472537,0.04589412,0.05608462,0.00032692056,0.89713556],"study_design_scores_gemma":[0.00039800163,0.000352572,0.004146366,0.00032949462,0.000013014105,0.000012461514,0.000094367446,0.38416633,0.42804116,0.18122473,0.0010188692,0.00020262475],"about_ca_topic_score_codex":0.000096058015,"about_ca_topic_score_gemma":0.0000032686733,"teacher_disagreement_score":0.89693296,"about_ca_system_score_codex":0.00008301866,"about_ca_system_score_gemma":0.0002158915,"threshold_uncertainty_score":0.31972545},"labels":[],"label_agreement":null},{"id":"W4414698255","doi":"10.3758/s13428-025-02826-9","title":"A year of nouns from English-learning infants’ daily lives: The SEEDLingS-Nouns dataset","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","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":"Concordia University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institutes of Health","keywords":"Comprehension; Metadata; Noun; Word (group theory); Reuse","score_opus":0.12907756743695148,"score_gpt":0.5538640880432741,"score_spread":0.42478652060632266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414698255","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":[0.94368714,0.0020149627,0.002814409,0.00030477275,0.0012379796,0.0012361481,0.0009191391,0.00013902264,0.047646444],"genre_scores_gemma":[0.78353065,0.00047809182,0.16798803,0.0007355045,0.0006839114,0.0018445504,0.0054422235,0.00019456378,0.03910249],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99473315,0.0032142461,0.00041685914,0.0005068885,0.0005273905,0.00060147204],"domain_scores_gemma":[0.99559367,0.0029746452,0.00009838171,0.0009245508,0.00030931932,0.00009942242],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00633272,0.00017524738,0.0003096187,0.00037698302,0.00030379483,0.00009841675,0.00094948325,0.00016347802,0.0038105347],"category_scores_gemma":[0.0030491594,0.00013099419,0.000094886855,0.0010176591,0.00041189083,0.00010742722,0.00046690594,0.0011319811,0.00015301214],"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":[0.00062805164,0.0010348617,0.56032866,0.00006157624,0.00045442034,0.00014826278,0.12368599,0.000004844931,0.007373631,0.0024931263,0.082991615,0.22079495],"study_design_scores_gemma":[0.00253721,0.00023266631,0.47206822,0.00013792624,0.0001744982,0.0000028360516,0.11999879,0.000027950327,0.0024660458,0.0008716403,0.40102345,0.00045877692],"about_ca_topic_score_codex":0.0044739298,"about_ca_topic_score_gemma":0.00014064329,"teacher_disagreement_score":0.31803182,"about_ca_system_score_codex":0.000044348762,"about_ca_system_score_gemma":0.0002426688,"threshold_uncertainty_score":0.9971001},"labels":[],"label_agreement":null},{"id":"W4414798325","doi":"10.3758/s13428-025-02812-1","title":"A systematic review of latent class analysis in psychology: Examining the gap between guidelines and research practice","year":2025,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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 British Columbia","funders":"Università Cattolica del Sacro Cuore","keywords":"Latent class model; Categorical variable; Class (philosophy); Flexibility (engineering); Systematic review; Quality (philosophy); Population; Inclusion (mineral)","score_opus":0.9062522744482858,"score_gpt":0.804378768394313,"score_spread":0.10187350605397283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414798325","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":[0.000005878719,0.9785708,0.00021612518,0.0016482535,0.00020690619,0.015274565,0.00013780594,0.000025971804,0.0039136647],"genre_scores_gemma":[0.0000010375463,0.96845305,0.014699428,0.00019830141,0.00013456344,0.012990775,0.000096563585,0.00007955547,0.0033467314],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8080196,0.17896047,0.005378,0.0018736332,0.0036046046,0.0021637226],"domain_scores_gemma":[0.91915184,0.07198784,0.0011301578,0.004115071,0.0031498133,0.00046526061],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2675776,0.0006074389,0.006393791,0.005970546,0.0004223735,0.00012564374,0.0029114725,0.0009581787,0.00042005867],"category_scores_gemma":[0.07330006,0.00039396985,0.0006860825,0.016387004,0.0011941186,0.00013119605,0.0018995941,0.007099729,0.00008026227],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013095917,0.00017015277,0.00012310618,0.53370595,0.00070830015,0.000096624164,0.00015861346,8.67105e-9,3.0760336e-7,0.00027306913,0.00209066,0.46266013],"study_design_scores_gemma":[0.00028772667,0.00039001228,0.00048205943,0.65191925,0.0072176545,0.00006463743,0.00064137584,0.0000024445767,5.250777e-7,0.00010591296,0.3385771,0.00031134253],"about_ca_topic_score_codex":0.0013274585,"about_ca_topic_score_gemma":0.00007423908,"teacher_disagreement_score":0.4623488,"about_ca_system_score_codex":0.00064418983,"about_ca_system_score_gemma":0.0015592492,"threshold_uncertainty_score":0.9998512},"labels":[],"label_agreement":null},{"id":"W4414872730","doi":"10.3758/s13428-025-02802-3","title":"Can you beat the music? Validation of a gamified rhythmic training in children with ADHD","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Children's Physical and Motor Development","field":"Psychology","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; Université de Montréal; Bell (Canada); International Laboratory for Brain, Music and Sound Research; Centre for Research on Brain Language and Music","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Rhythm; Beat (acoustics); Perception; Sensorimotor rhythm; Cognition; Affect (linguistics); Synchronization (alternating current); Metronome; Control (management)","score_opus":0.21568506785745156,"score_gpt":0.5133693839716763,"score_spread":0.29768431611422475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414872730","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":[0.9938771,0.000067969064,0.00063449895,0.000628751,0.00013569376,0.0014287962,0.00001793574,0.000024983201,0.0031842787],"genre_scores_gemma":[0.98839664,0.0000040407435,0.008434148,0.00004458202,0.00008232109,0.00097013975,0.00003136517,0.000021387375,0.0020153956],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99690425,0.0014104963,0.00032789452,0.0004292935,0.00042454683,0.0005034952],"domain_scores_gemma":[0.99871707,0.00046605675,0.00006343042,0.00054585666,0.00013471534,0.000072895484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034245716,0.00014979232,0.00028411104,0.0003744941,0.00013029683,0.000029800365,0.0003715228,0.00009289162,0.00021014063],"category_scores_gemma":[0.00013890701,0.00010046849,0.00006791343,0.001229528,0.00028484725,0.00003810805,0.00011527423,0.0006331555,0.000006810569],"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":[0.00030666325,0.00060937746,0.08240416,0.000017556506,0.00016918991,0.000017417464,0.036084834,0.0000072159855,0.016869167,0.00880566,0.0005137735,0.854195],"study_design_scores_gemma":[0.0012315504,0.00018276938,0.9757161,0.00007716915,0.000039226525,0.000016098447,0.0038967703,0.000003833474,0.016570004,0.0014512722,0.000670231,0.00014497887],"about_ca_topic_score_codex":0.0017753588,"about_ca_topic_score_gemma":0.00012255712,"teacher_disagreement_score":0.8933119,"about_ca_system_score_codex":0.000106012,"about_ca_system_score_gemma":0.0003038881,"threshold_uncertainty_score":0.4096986},"labels":[],"label_agreement":null},{"id":"W4415379075","doi":"10.3758/s13428-025-02806-z","title":"LexKO: A quick, reliable lexical test of Korean language proficiency","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","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; University of Toronto","funders":"Kyung Hee University; University of Manitoba; City University of Hong Kong","keywords":"Language proficiency; Test (biology); Korean language; Multilingualism; Language assessment; Foreign language","score_opus":0.17705806644686634,"score_gpt":0.5632092123204916,"score_spread":0.38615114587362526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415379075","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":[0.29941115,0.000938134,0.6863989,0.0015569926,0.0002319125,0.0015950043,0.00001214101,0.00023846915,0.00961724],"genre_scores_gemma":[0.63961023,0.000013815377,0.35573164,0.000024629511,0.000018401168,0.00032440227,0.0000035054254,0.0000073270317,0.0042660385],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969823,0.0010027702,0.00038370315,0.0005358201,0.0006110146,0.00048439016],"domain_scores_gemma":[0.9969004,0.0012927009,0.000057990175,0.0013353812,0.00029669184,0.00011685409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077816383,0.00010977587,0.00022632774,0.000395591,0.00020602794,0.00011423633,0.0014477486,0.00012068909,0.00003367712],"category_scores_gemma":[0.0018941769,0.00009536908,0.000087846165,0.0019960182,0.0003393605,0.00024750954,0.0005276887,0.000472116,0.000020465986],"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":[0.00001423325,0.0011718647,0.021575687,0.00011165641,0.000006523277,0.000010661566,0.0016946588,0.0000043468726,0.2918729,0.07390288,0.00084036886,0.6087942],"study_design_scores_gemma":[0.0006057603,0.00088371057,0.21470852,0.00012707445,0.000030828585,0.000016085503,0.001453008,0.009156548,0.74280304,0.009370979,0.020469114,0.00037533502],"about_ca_topic_score_codex":0.00058095204,"about_ca_topic_score_gemma":0.000013271799,"teacher_disagreement_score":0.6084189,"about_ca_system_score_codex":0.00008351919,"about_ca_system_score_gemma":0.0004422888,"threshold_uncertainty_score":0.38890386},"labels":[],"label_agreement":null},{"id":"W4415668209","doi":"10.3758/s13428-025-02783-3","title":"Errors-in-variables regression as a viable approach to mediation analysis with random error-tainted measurements: Estimation, effectiveness, and an easy-to-use implementation","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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":"University of Calgary","funders":"","keywords":"Regression analysis; Mediation; Observational error; Ordinary least squares; Regression; Regression diagnostic; Errors-in-variables models; Instrumental variable; Standard error; Linear regression","score_opus":0.3125196999863581,"score_gpt":0.6438098672918707,"score_spread":0.33129016730551264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415668209","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":[0.7216892,0.00009181197,0.2702223,0.0002371736,0.00014190658,0.006390641,0.000023983057,0.00006349978,0.0011394372],"genre_scores_gemma":[0.66115236,0.000010583437,0.32940015,0.00013427956,0.000033189724,0.008181375,0.00025891326,0.00004750471,0.00078161183],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9821609,0.013840805,0.00061434845,0.0010598784,0.001350708,0.00097335083],"domain_scores_gemma":[0.9956708,0.001633661,0.00010730423,0.0008368502,0.001170614,0.00058077305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024229122,0.00026796316,0.000580842,0.0029822437,0.00044046866,0.00020552626,0.00037876688,0.00018249115,0.0002899953],"category_scores_gemma":[0.0031875975,0.00022362241,0.00005647853,0.0058433693,0.00012907764,0.00045270333,0.0002156443,0.0005824628,0.000018175186],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006799325,0.0017577849,0.72586197,0.00037823504,0.00038555008,0.000024754609,0.003515694,0.0007837486,0.012756248,0.002586235,0.00044856797,0.24470189],"study_design_scores_gemma":[0.005626077,0.0010238875,0.9784393,0.00018693523,0.00019960223,0.0000033885003,0.003706413,0.0031526175,0.006003747,0.00062144233,0.0007467264,0.0002898905],"about_ca_topic_score_codex":0.012063454,"about_ca_topic_score_gemma":0.0014293587,"teacher_disagreement_score":0.2525773,"about_ca_system_score_codex":0.00085451745,"about_ca_system_score_gemma":0.00040004798,"threshold_uncertainty_score":0.9945153},"labels":[],"label_agreement":null},{"id":"W4415812611","doi":"10.3758/s13428-025-02871-4","title":"Publisher Correction: A systematic review of latent class analysis in psychology: Examining the gap between guidelines and research practice","year":2025,"lang":"en","type":"review","venue":"Behavior Research Methods","topic":"Mental Health Research Topics","field":"Psychology","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":"Latent class model; Class (philosophy); Practice research; Systematic review; Research design; Research methodology","score_opus":0.8840180937043264,"score_gpt":0.781607092634572,"score_spread":0.10241100106975443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415812611","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":[0.0000021147093,0.9734921,0.0002571939,0.001977174,0.0011906568,0.01352098,0.000043082426,0.000032795328,0.00948393],"genre_scores_gemma":[8.2514555e-7,0.9649065,0.007835089,0.00021030076,0.00018241015,0.013282507,0.00010689097,0.00007771279,0.013397738],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.837043,0.1511116,0.0046914555,0.0018098898,0.0034427382,0.0019013362],"domain_scores_gemma":[0.9298341,0.060584705,0.0011264785,0.0038023372,0.004187426,0.00046494344],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24089727,0.00058394286,0.005571902,0.0060822517,0.00046962142,0.00024922733,0.0025813354,0.0010137714,0.0005497825],"category_scores_gemma":[0.08213772,0.00038634133,0.0006305074,0.019173434,0.0010624783,0.00025447016,0.0016160693,0.0075762137,0.00006180266],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015299636,0.00018607633,0.0002439161,0.45704794,0.0006029302,0.0000675996,0.00014791434,1.4833037e-8,8.602605e-8,0.00011206398,0.028778816,0.51279736],"study_design_scores_gemma":[0.00025891844,0.00035477182,0.0005982823,0.46027026,0.0053808014,0.000091836744,0.00078888144,0.0000032582093,1.4489119e-7,0.00008413239,0.5318831,0.00028560832],"about_ca_topic_score_codex":0.0017197692,"about_ca_topic_score_gemma":0.00011759397,"teacher_disagreement_score":0.51251173,"about_ca_system_score_codex":0.00077064347,"about_ca_system_score_gemma":0.0016524788,"threshold_uncertainty_score":0.99985886},"labels":[],"label_agreement":null},{"id":"W4416118469","doi":"10.3758/s13428-025-02878-x","title":"Quantifying word informativeness and its impact on eye-movement reading behavior: Cross-linguistic variability and individual differences","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","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":"Azrieli Foundation; Israel Science Foundation; Hebrew University of Jerusalem","keywords":"Sentence; Reading (process); Meaning (existential); Centrality; Word (group theory); Affect (linguistics); Measure (data warehouse)","score_opus":0.37613696170262745,"score_gpt":0.6139571780082518,"score_spread":0.23782021630562433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416118469","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":[0.9977888,0.000116524214,0.00015774132,0.000055169305,0.00031543887,0.0009814595,0.000090232934,0.0000714723,0.00042314746],"genre_scores_gemma":[0.99760294,0.000081993276,0.001607972,0.00015311992,0.000043510954,0.00024264456,0.0000061025594,0.000015386157,0.00024633395],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9939071,0.0035243595,0.00048089286,0.00081359677,0.00053381023,0.00074024644],"domain_scores_gemma":[0.99378616,0.0052766176,0.00010935431,0.0004308559,0.00019074765,0.0002062888],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008339594,0.00029112826,0.00041892912,0.00052704575,0.0008201942,0.00044540543,0.00049633085,0.0001832522,0.0000624326],"category_scores_gemma":[0.009537114,0.00021733264,0.00007754173,0.00063336716,0.0007466548,0.00021905694,0.0007125196,0.0009787116,0.000004184071],"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":[0.00022165178,0.0004346976,0.36891165,0.00016025025,0.000016130713,0.00034893173,0.0032683478,0.000001330258,0.4917632,0.0020618383,0.0000072478056,0.13280472],"study_design_scores_gemma":[0.0006246959,0.00042586456,0.7268952,0.0001416341,0.000056752888,0.000035093253,0.00033900293,0.00010118728,0.2701472,0.00083209446,0.00011333911,0.00028794474],"about_ca_topic_score_codex":0.00008359561,"about_ca_topic_score_gemma":0.0000055488117,"teacher_disagreement_score":0.35798353,"about_ca_system_score_codex":0.00009300446,"about_ca_system_score_gemma":0.00016107339,"threshold_uncertainty_score":0.998806},"labels":[],"label_agreement":null},{"id":"W4416322110","doi":"10.3758/s13428-025-02787-z","title":"Spower: A general-purpose Monte Carlo simulation power analysis program","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","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":"Subroutine; Monte Carlo method; Software; Comparability; Function (biology); Software package; Population; Power (physics)","score_opus":0.6411716053274139,"score_gpt":0.6920635075483204,"score_spread":0.05089190222090645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416322110","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":[0.960839,0.0024213956,0.005105973,0.0005810989,0.0009313857,0.0023771224,0.000040689352,0.0003735909,0.027329778],"genre_scores_gemma":[0.9139219,0.000039584764,0.041601468,0.00017266707,0.00008503477,0.0031718449,0.000014415826,0.00003077559,0.040962335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9930427,0.0036552614,0.0005889461,0.0010119351,0.0006323356,0.0010688428],"domain_scores_gemma":[0.9972316,0.0008133453,0.00008730274,0.001043496,0.00058517297,0.00023907612],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004704586,0.00030850802,0.0006436354,0.0010262599,0.000485101,0.0001461833,0.0006044975,0.00038429105,0.00436091],"category_scores_gemma":[0.0002796976,0.00024265835,0.0005076056,0.004966651,0.00045059994,0.00008856398,0.0003262409,0.0009764572,0.00017571951],"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":[0.00028304965,0.0023792116,0.13557048,0.000007699277,0.0005132967,0.00014150327,0.0007836304,0.00011298316,0.0009769375,0.00105622,0.0040962687,0.8540787],"study_design_scores_gemma":[0.000601458,0.00051484705,0.8060501,0.0000104268065,0.0005894762,0.0000019253823,0.00054249313,0.00026527452,0.000117746815,0.00026891194,0.19075868,0.0002786153],"about_ca_topic_score_codex":0.00095481717,"about_ca_topic_score_gemma":0.00006898698,"teacher_disagreement_score":0.8538001,"about_ca_system_score_codex":0.00013650894,"about_ca_system_score_gemma":0.000037210084,"threshold_uncertainty_score":0.99654925},"labels":[],"label_agreement":null},{"id":"W4416887635","doi":"10.3758/s13428-025-02872-3","title":"The Subliminal Threshold Estimation Procedure (STEP): A calibration method tailored for estimating subliminal thresholds","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Tel Aviv University","keywords":"Subliminal stimuli; Stimulus (psychology); Calibration; Detection threshold; Psychophysics; Just-noticeable difference","score_opus":0.4554719485315771,"score_gpt":0.6203202001042937,"score_spread":0.1648482515727166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416887635","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":[0.19451027,0.00029082672,0.7876774,0.010214101,0.0015561657,0.004612062,0.000034481,0.00029591232,0.00080878305],"genre_scores_gemma":[0.20570718,0.00003171743,0.78362215,0.00040536094,0.00020576954,0.0055640354,0.000018703468,0.000058747893,0.004386321],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99417824,0.0020490866,0.00068495254,0.0011066502,0.0008541037,0.0011269727],"domain_scores_gemma":[0.99387175,0.0046183714,0.00018216387,0.00069457426,0.00047697604,0.00015616856],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0078856,0.0003463335,0.00039845135,0.0004641879,0.0031072062,0.0006070923,0.001011684,0.00023157228,0.000022344448],"category_scores_gemma":[0.005509276,0.00023667527,0.00020903804,0.0018139512,0.0008708105,0.00065491634,0.00041586044,0.0009862916,0.000007783583],"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":[0.0007462498,0.0004475898,0.00387799,0.00014092174,0.000015378593,0.000029861192,0.00029933074,0.00007174618,0.4933186,0.01641779,0.009057472,0.4755771],"study_design_scores_gemma":[0.0020311764,0.0012625011,0.010831022,0.00018131315,0.00027433963,0.0001454724,0.0012167479,0.24418736,0.7001414,0.034443248,0.004572714,0.00071276404],"about_ca_topic_score_codex":0.000050348906,"about_ca_topic_score_gemma":0.00005041491,"teacher_disagreement_score":0.47486433,"about_ca_system_score_codex":0.00013992153,"about_ca_system_score_gemma":0.00025254578,"threshold_uncertainty_score":0.99819064},"labels":[],"label_agreement":null},{"id":"W763189797","doi":"10.3758/s13428-015-0614-z","title":"Performance impact of stop lists and morphological decomposition on word–word corpus-based semantic space models","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Topic Modeling","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":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Word (group theory); Word lists by frequency; Space (punctuation); Semantics (computer science); Class (philosophy); Text corpus; Linguistics; Sentence","score_opus":0.4101321547628593,"score_gpt":0.5636734972443137,"score_spread":0.1535413424814544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W763189797","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":[0.6089865,0.00008903811,0.39028466,0.00012454952,0.00006140243,0.0002737973,0.0000019132588,0.000046531735,0.0001316185],"genre_scores_gemma":[0.63755405,0.000016252034,0.3622907,0.000011149334,0.000020616108,0.000042752232,0.0000017752984,0.00000946407,0.000053214913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624413,0.0015263227,0.00029070253,0.0005455705,0.00086272304,0.0005305765],"domain_scores_gemma":[0.9977715,0.00055357703,0.00008764344,0.0008291495,0.00039816633,0.00035998927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005877975,0.00017421064,0.00030330408,0.00037133702,0.00012667834,0.00011842221,0.0007325245,0.00012706294,0.000010222217],"category_scores_gemma":[0.00024467157,0.00013941707,0.00008855893,0.0005819659,0.00018864099,0.0003713302,0.00038352478,0.0005196849,0.0000068300255],"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":[0.00040101193,0.00086155586,0.029765803,0.0000847439,0.000020449976,0.00021129956,0.0012185635,0.05064173,0.06080185,0.0032970663,0.00021283282,0.8524831],"study_design_scores_gemma":[0.00066569296,0.0010387789,0.047048952,0.00007957193,0.000008146055,0.000049094262,0.000021811265,0.9372949,0.012128894,0.0014585769,0.000021637064,0.00018394977],"about_ca_topic_score_codex":0.0002890145,"about_ca_topic_score_gemma":0.0000031701497,"teacher_disagreement_score":0.8866532,"about_ca_system_score_codex":0.00022197347,"about_ca_system_score_gemma":0.00028453226,"threshold_uncertainty_score":0.5685263},"labels":[],"label_agreement":null},{"id":"W927394476","doi":"10.3758/s13428-015-0627-7","title":"The influence of base rates on correlations: An evaluation of proposed alternative effect sizes with real-world data","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Community Safety and Correctional Services; Royal Ottawa Mental Health Centre; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Mathematics; Correlation; Pearson product-moment correlation coefficient; Base (topology); Sample size determination; Statistic; Polychoric correlation; Econometrics; Mathematical analysis","score_opus":0.8490125083874293,"score_gpt":0.6913935802776402,"score_spread":0.15761892810978906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W927394476","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":[0.9949218,0.00021926103,0.00008762074,0.00015227724,0.00015304572,0.00185459,0.000065808345,0.000022606671,0.0025229636],"genre_scores_gemma":[0.9929828,0.000028250708,0.005858491,0.000007672702,0.00004448512,0.00058492855,0.000039059927,0.000017708157,0.00043661022],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98368806,0.013658266,0.0003937371,0.0005156975,0.001394305,0.0003499482],"domain_scores_gemma":[0.9926409,0.003980233,0.00024876182,0.001349,0.0016346399,0.00014643768],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030384062,0.00016259082,0.00032987818,0.00017444546,0.00022317335,0.000031645024,0.00087518094,0.000065259395,0.0001000117],"category_scores_gemma":[0.0023201301,0.00008379356,0.00003525503,0.0009227574,0.0012457784,0.00016687653,0.00021213165,0.00049301726,0.00001981519],"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":[0.0035375182,0.0015298299,0.3616383,0.000012808115,0.00009219862,0.000017010228,0.0020669647,0.0001585495,0.005177067,0.002104302,0.00067221426,0.62299323],"study_design_scores_gemma":[0.001590312,0.0055955206,0.9839983,0.000059551712,0.00015902604,0.0000025441107,0.001230399,0.0001831828,0.005727621,0.001003801,0.00031941338,0.00013030178],"about_ca_topic_score_codex":0.0038839476,"about_ca_topic_score_gemma":0.00077125983,"teacher_disagreement_score":0.62286294,"about_ca_system_score_codex":0.00007590417,"about_ca_system_score_gemma":0.00011644784,"threshold_uncertainty_score":0.99842364},"labels":[],"label_agreement":null}]}